Prompting method and device, automatic driving vehicle and storage medium

[0127] In order to make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings.

[0128] There are a large number of vehicles on the road, and the personalities and behaviors of the vehicle drivers are different, resulting in different driving operations performed by the vehicles. When an autonomous vehicle interacts with other vehicles, it must not only make reasonable decisions about its own driving operations, but also clearly express its own intentions to avoid misjudgments by other vehicles on the autonomous vehicle. In addition, autonomous vehicles also need to promptly remind other vehicles of abnormal driving operations, thereby reducing risk factors.

[0129] The current automatic driving scheme focuses on the decision-making, planning and control of the driving operation inherent in the autonomous vehicle, so that the autonomous vehicle can drive safely and effectively under different road conditions. However, these driving operations are not transparent to other vehicles, which inevitably leads to misunderstandings.

[0130] For example, a heavy-duty trailer is relatively large in size and the lane change process is relatively slow. A vehicle behind the heavy trailer may interpret the slow lane change of the heavy trailer as avoiding the rear vehicle, and then drive fast in the target lane of the heavy trailer. The rear vehicle may conflict with the heavy trailer, causing greater safety hazards. Or, the driver may deviate from the center of the lane due to fatigue driving, or drive slowly in the fast lane, or try to forcibly insert in front of the autonomous vehicle. At this time, self-driving vehicles need to give prompt reminders to warn the aforementioned vehicles and avoid risk factors. Furthermore, self-driving vehicles, especially heavy trucks, may affect the observation field of other vehicles. If self-driving vehicles can give necessary reminders to other vehicles whose fields of view are obscured, it can improve other vehicles' understanding of the behavior of self-driving vehicles.

[0131] In order to solve the above-mentioned problems, it is necessary for autonomous vehicles to actively interact with other vehicles using various means. This kind of interaction not only explicitly expresses the ideas, plans and actions of the autonomous vehicle, but also assists other vehicles in understanding the surrounding situation and the intention of the autonomous vehicle.

[0132] In related schemes, the vehicle usually adopts passive interaction methods. For example, other vehicles forcefully pass through the target lane of the vehicle during the lane change, and the vehicle passively cancels the lane change and turns off the turn signal to ensure safety, but before canceling the lane change It did not take the initiative to give necessary reminders and warnings to other vehicles. For another example, when the side encounters a risk, the vehicle often needs to borrow or even change lanes to the other side to avoid the risk. At this time, the usual solution is to turn on the turn signal and wait for the time to change lanes. However, because the vehicle in the target lane does not understand the motivation of the vehicle, it often ignores the turn signal of the vehicle and does not evade the vehicle, causing the vehicle to fail to avoid risks in time.

[0133] In summary, most of the current implementation solutions for interacting with other vehicles are passive and responsive, and the current automatic driving field lacks an overall solution for systematically interacting with other vehicles.

[0134] In the embodiments of the present application, a systematic solution is proposed for the problem of active interaction with other agents in the environment during the driving of the autonomous vehicle. Agents include all individuals or groups that have intelligence and can make decisions and actions based on various perceptual information. For example, the agents in the traffic environment are mainly humans, including drivers, pedestrians, engineering workers, service personnel in specific scenarios, etc., and can also include other autonomous vehicles.

[0135] The different behaviors of ordinary vehicles mainly refer to the different ideas, different actions and different performances of the drivers driving the vehicle. However, special vehicles, engineering operators, and service personnel in specific scenarios often have special behavior patterns and specifications. The behavior of pedestrians is more random than other human agents. Generally speaking, human behavior is generally predictable, while the behavior of other autonomous vehicles may have huge differences.

[0136] In order to solve the problem of actively interacting with other agents, the following sub-problems need to be solved: (1) When to interact; (2) Who to interact with; (3) How to interact; (4) How to deal with feedback after interaction. The following text will specifically expand the solutions to the above problems.

[0137] See figure 1 , The active interaction process proposed in the embodiment of this application includes the following steps:

[0138] (1) Identify surrounding agents

[0139] In the embodiments of the present application, the autonomous vehicle can use agent classification and abnormal behavior discrimination to identify surrounding agents, so as to guide the process of active interaction. Different types of agents have different behavioral abilities and behavior patterns, and behaviors beyond their general abilities and patterns are abnormal behaviors.

[0140] The process of identifying surrounding agents is as follows figure 2 As shown, the self-driving vehicle collects multi-sensor information through the configured multi-sensor, recognizes obstacles based on the multi-sensor information, can identify nearby obstacles, and classifies the identified obstacles using intelligent body classification technology to determine The category of the agent that exists around, then the agent can be tracked, and the behavior of the agent can be predicted, and whether it is abnormal behavior can be identified according to the behavior of the agent.

[0141] (2) Assess environmental risks

[0142] The process of assessing environmental risks such as image 3 As shown, the self-driving vehicle of the present application collects environmental information through configured multi-sensors, thereby acquiring the current road structure, reconstructing the road structure, and using the reconstructed road structure to determine the road passable area. In addition, it will also determine the area where the current road structure is inconsistent with the known road structure, perform scene recognition on the area, determine the scene of the area, such as construction scene, vehicle failure scene, road occlusion scene, etc., and evaluate the traffic risk of the area .

[0143] (3) Choose the timing of interaction

[0144] The self-driving vehicle detects the state of the self-driving vehicle or the state of other agents, and selects an appropriate interaction time based on the detected state information.

[0145] (4) Scheduling interaction means: the autonomous driving vehicle is equipped with output devices, including at least one of a display screen, a speaker, or a reminder light. The self-driving vehicle outputs information matching the state type of the self-driving vehicle through the configured output device.

[0146] (5) Collect interactive feedback: Other agents will give feedback on the driving operation of the autonomous vehicle. The autonomous vehicle collects information from other agents through the multi-sensor configuration, and then determines the behavior of other agents.

[0147] (6) Adjust the behavior of the autonomous vehicle: The autonomous vehicle re-plans the operation of the autonomous vehicle based on the detected behavior of other agents. For example, when the autonomous vehicle detects that other agents occupy the lane of the autonomous vehicle, the autonomous vehicle performs a parking operation or slows down to avoid.

[0148] Such as figure 1 As shown, through the identification of surrounding agents and environmental risk assessment, the autonomous vehicle has a complete understanding of the environmental conditions, and then how to take active interaction means to interact with other agents. A round of active interaction process includes several steps such as selecting interaction timing, scheduling interaction means, collecting interaction feedback, and adjusting the behavior of autonomous vehicles. This application divides the interaction timing into five categories: a) prompting the status of autonomous vehicles; b) avoiding special vehicles; c) avoiding dangerous environments; d) reducing the risk of meeting cars; e) warning abnormal agents, different interaction timings can be simultaneous occur. The following text will explain the active interaction process at different times.

[0149] The first interactive method: prompts the status of the autonomous vehicle.

[0150] Figure 4 It is a flowchart of a state prompting method according to an exemplary embodiment, which is applied to an automatic driving vehicle, such as Figure 4 As shown, the method includes:

[0151] 401. The autonomous vehicle detects the current state information of the autonomous vehicle in real time.

[0152] In the embodiment of the present application, the self-driving vehicle detects the current state information of the self-driving vehicle in real time, and then determines the state type to which it belongs based on the state information, and outputs prompt information corresponding to the state type according to the state type.

[0153] Among them, self-driving vehicles may include self-driving cars, self-driving trucks, and self-driving motorcycles.

[0154] The state information of the autonomous vehicle is used to indicate the state of the autonomous vehicle. The status information includes the driving speed, driving distance, remaining fuel amount, the operating status of each component, and the on and off status of the prompt light of the autonomous vehicle.

[0155] Among them, components in autonomous vehicles include engines, chassis, and body accessories. Body accessories include car networking wireless devices, sound receivers, mechanical or electronic whistle, fuel tanks, tires, car shells, doors, car glass, car mirrors, and license plates Frames, seats and seat accessories, automobile bearings, armrests, handles, handles, cab and cab accessories, airbags, seat belts, window regulators, antennas, wipers, mufflers, horns, car weather strip bumpers, Suitcase, exhaust pipe, etc. Autonomous vehicles can detect the operating status of different components.

[0156] Autonomous vehicles need a combination of software systems and hardware systems to realize autonomous driving. The software system includes a perception module, a positioning module, and a decision-making module. The perception module and the positioning module identify and classify other agents. The decision-making module judges whether other agents are special vehicles, whether they are meeting with autonomous vehicles, whether there are abnormalities, etc. based on the behaviors of other agents, and then interact with them through active interaction methods. Other agents interact. The hardware system includes components equipped with autonomous vehicles to interact with other agents, including prompt lights, car whistle, display screens, speakers, and car networking wireless devices.

[0157] 402. The autonomous vehicle determines the state type to which the state information belongs.

[0158] According to each detected state information, the self-driving vehicle determines whether the self-driving vehicle has the ability to automatically drive and pull over, and then determine the state type of the self-driving vehicle, so that the output device of the self-driving vehicle can output the state type The corresponding prompt information.

[0159] In one possible implementation, the autonomous vehicle pre-sets the conditions that the state information should meet when it has automatic driving capabilities. When the autonomous vehicle detects the state information, it determines whether the state information meets the preset conditions, and then determines the automatic Whether the driving vehicle has automatic driving capability. For example, if an autonomous vehicle is preset under the condition that the door is closed and the autonomous vehicle is capable of automatic driving, the autonomous vehicle detects the status information of the autonomous vehicle and detects that the door of the autonomous vehicle is not closed, which does not meet the preset conditions , So it is determined that the autonomous vehicle does not have the capability of autonomous driving.

[0160] The ability to pull over refers to the ability of an autonomous vehicle to drive from its current position to the edge of the current road and then stop. For example, an autonomous vehicle is currently located in a lane on the side of the road and can drive a short distance to reach the edge of the current road. Alternatively, the self-driving vehicle is currently located in a lane in the middle of the road and can perform a lane change operation to reach the edge of the current road.

[0161] The self-driving vehicle presets the conditions that the state information should meet when it has the ability to pull over. The self-driving vehicle detects the state information and determines whether the state information meets the preset conditions, and then determines whether the self-driving vehicle has the ability to pull over. For example, if the self-driving vehicle presets that the remaining fuel amount is not less than the first preset threshold but not greater than the second preset threshold, the self-driving vehicle has the ability to pull over but does not have the self-driving ability, the self-driving vehicle detects The state information of the self-driving vehicle detects that the remaining fuel amount of the self-driving vehicle is less than the first preset threshold and does not meet the preset conditions, so it is determined that the self-driving vehicle does not have the ability to pull over.

[0162] The self-driving vehicle classifies the state of the self-driving vehicle into a normal state type, a first failure state type, and a second failure state type according to whether it has the ability to automatically drive and whether it has the ability to pull to the side.

[0163] The normal state type indicates that the autonomous vehicle has no faults and can continue to drive without intervention in the driving operation of the autonomous vehicle. When the state information indicates that the self-driving vehicle has automatic driving capability, the state type is determined to be the normal state type.

[0164] The first fault state type indicates that the autonomous vehicle has a primary fault, which may affect the normal driving of the autonomous vehicle, but it can still be pulled over and parked. When the state information indicates that the self-driving vehicle does not have the ability to automatically drive, but has the ability to pull over, the state type is determined to be the first failure state type.

[0165] The second failure state type indicates that the autonomous vehicle has a serious failure and does not have the ability to pull over. When the state information indicates that the self-driving vehicle does not have the ability to automatically drive and pull to the side, the state type is determined to be the second fault state type.

[0166] It should be noted that the embodiment of the present application only divides the state types into normal state types, first failure state types, and second failure state types based on whether the autonomous vehicle has automatic driving capability and parking capability. In another embodiment , The status types can also be divided according to other criteria.

[0167] It should be noted that the embodiment of the present application only uses the state information of the autonomous vehicle to determine whether the autonomous vehicle has the capability of autonomous driving and the ability to park sideways, and then determine the state type of the autonomous vehicle. In another embodiment, Determine the state type of the autonomous vehicle according to other methods.

[0168] The status information can include multiple dimensions of information, such as the driving speed, the opening and closing status of the door, and the temperature of the vehicle. In a possible implementation manner, the autonomous vehicle establishes a corresponding relationship between state information and state types in multiple dimensions, and when any state information is obtained, the corresponding relationship is queried to obtain the state type corresponding to the state information.

[0169] The automatic driving vehicle pre-establishes the priorities of the normal state type, the first failure state type, and the second failure state type, and the priority of the three state types increases in order. Then, when the state types determined according to the state information of different dimensions of the autonomous vehicle are different, the state type with the higher priority among the determined state types is selected.

[0170] For example, an autonomous vehicle determines that the autonomous vehicle is in the normal state according to the state information of the door closed, and determines that the autonomous vehicle is the first fault state based on the state information that the vehicle temperature is higher than the preset temperature. The priority of the first fault state type and the second fault state type are successively increased, and the priority of the first fault state is higher than that of the normal state, when the automatic driving vehicle is determined to be the normal state type and the first fault state type according to the two state information. When it is determined that the state type of the autonomous vehicle is the first failure state type.

[0171] 403. When the state type is the normal state type, output the prompt information corresponding to the normal state type through the output device of the autonomous vehicle.

[0172] The self-driving vehicle is equipped with an output device, and the output device includes at least one of a display screen, a speaker, a car whistle, or a warning light. Wherein, the number of display screens may be one or more, and the facing directions may include front, rear, left, right, and top, so as to realize the function of displaying information in the multiple directions. And the display screen can include multiple types of display screens such as subtitle screens and video screens. There can be one or more speakers, which can be installed on the roof or side of the car. The car whistle can include a mechanical whistle or an electronic whistle. The warning lights include turn signals, fog lights, and position lights.

[0173] The autonomous vehicle can establish the corresponding relationship between the normal state type and the prompt information. When the autonomous vehicle determines that the state information belongs to the normal state type, the corresponding relationship is queried, and the prompt information corresponding to the normal state type is obtained. The output device outputs the prompt information corresponding to the normal state type.

[0174] In a possible implementation manner, outputting prompt information corresponding to the normal state type through the output device may include at least one of the following:

[0175] (1) For the display screen, when the autonomous vehicle determines that the state type to which the current state information belongs is the normal state type, the first prompt information is displayed through the display screen, and the first prompt information is used to prompt the automatic driving vehicle to drive normally.

[0176] By configuring the display screen, during the driving of the autonomous vehicle, the display screen of the autonomous vehicle displays the first prompt information. When other agents view the first prompt information of the autonomous vehicle, it can be determined that the current autonomous vehicle is running normally. There is no fault.

[0177] In a possible implementation manner, the first prompt information may include text information or picture information. For example, the text information may be "I am all normal now", and the picture information may be any picture that can reflect that the autonomous vehicle is driving normally.

[0178] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information displayed by the autonomous vehicle.

[0179] (2) Regarding the speaker, when the autonomous vehicle determines that the state type to which the current state information belongs is the normal state type, the second prompt information is played through the speaker, and the second prompt information is used to prompt the autonomous vehicle to drive normally.

[0180] Wherein, the second prompt information is voice information. By configuring a speaker, the speaker of the self-driving vehicle will play the second prompt information during the driving of the autonomous vehicle, so that other agents can listen to the second prompt information and learn about the automatic The driving vehicle is currently driving normally.

[0181] In one possible implementation, one or more speakers can be set up, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. In addition, the speakers can also be placed in the front, rear, left or right of the car. side.

[0182] (3) For the reminder lights, during the driving operation of the autonomous vehicle, the reminder light corresponding to the currently executed driving operation is lit, so that other agents can clarify the driving operation being executed by the autonomous vehicle. For example, the driving operation currently performed by an autonomous vehicle can be straight, turning, changing lanes, reversing, accelerating, braking, parking, etc. When parking, the autonomous vehicle can light up hazard warning flashes (dual flashing lights), and when changing lanes When the time, the self-driving vehicle can light up the turn signal.

[0183] (4) For the reminder lights, the autonomous vehicle can detect the current environment information during the driving operation, and light up the reminder lights corresponding to the current environment information, so that other agents can clarify the location of the autonomous vehicle.

[0184] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0185] In addition, the prompt information output by the self-driving vehicle may also include at least one of the current driving speed of the self-driving vehicle, the currently performed driving operation, or the distance between the self-driving vehicle and the obstacle.

[0186] Among them, the driving operation currently performed by the self-driving vehicle can be straight, turning, changing lanes, reversing, accelerating, braking, etc. The self-driving vehicle can prompt any driving operation currently performed through a display screen or a speaker.

[0187] Alternatively, the self-driving vehicle has preset dangerous driving operations, which may be high-speed driving, lane changing, collision with other vehicles, too close to obstacles, and so on. When it is detected that the autonomous driving vehicle is performing a dangerous driving operation, the above-mentioned output device may be used to output prompt information corresponding to the above-mentioned dangerous operation. For example, other vehicles are notified through the speaker that the autonomous vehicle is currently driving too fast.

[0188] 404. When the state type is the first fault state type, output the prompt information corresponding to the first fault state type through the output device of the autonomous vehicle.

[0189] The self-driving vehicle can establish the corresponding relationship between the first failure state type and the prompt information. When the self-driving vehicle determines that the state information belongs to the first failure state type, the corresponding relationship is queried to obtain the prompt information corresponding to the first failure state type , Through the output device of the self-driving vehicle, output the prompt information corresponding to the first fault state type.

[0190] In a possible implementation manner, outputting the prompt information corresponding to the first fault state type through the output device may include at least one of the following:

[0191] (1) For the display screen, when the autonomous vehicle determines that the state type to which the current state information belongs is the first fault state type, the third prompt information is displayed on the display screen, and the third prompt information is used to prompt the automatic driving vehicle to malfunction.

[0192] By configuring the display screen, during the driving process of the autonomous vehicle, the display screen of the autonomous vehicle displays the third prompt information. When other agents view the third prompt information of the autonomous vehicle, they can determine the current state of the autonomous vehicle It is the first fault state type.

[0193] In a possible implementation manner, the third prompt information may include text information or picture information. For example, the text information may be "I have a fault now", and the picture information may be any picture that can reflect the failure of the autonomous vehicle.

[0194] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information of autonomous vehicles.

[0195] (2) For the speaker, when the autonomous vehicle determines that the state type to which the current state information belongs is the first fault state type, the fourth prompt message is played through the speaker, and the fourth prompt message is used to prompt the autonomous vehicle to pull over.

[0196] Among them, the fourth prompt information is voice information. By configuring a speaker, the speaker of the self-driving vehicle plays the fourth prompt information during the driving of the autonomous vehicle, so that other agents can listen to the fourth prompt information and learn about the automatic The driving vehicle is currently pulling over and parking.

[0197] In one possible implementation, one or more speakers can be set up, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. In addition, the speakers can also be placed in the front, rear, left or right of the car. side.

[0198] (3) For the car horn, when the state type of the self-driving vehicle is the first fault state type, the whistle operation can be performed according to the first whistle rhythm.

[0199] Among them, the self-driving vehicle is equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or the electronic whistle. Autopilot vehicles can set the number of whistle sounds in each fixed period to determine the whistle rhythm. Different state types correspond to different whistle rhythms. The period can be one second or one minute, etc.

[0200] In addition, the first whistle rhythm may be a preset rhythm. Alternatively, the self-driving vehicle may establish the corresponding relationship between the first fault state type and the whistle rhythm, and when the self-driving vehicle determines that the state information belongs to the first fault state type, the corresponding relationship is queried to obtain the corresponding relationship with the first fault state type The first whistle rhythm of, and the whistle operation is performed according to the first whistle rhythm corresponding to the first fault state type, so that other agents can learn the current state of the autonomous vehicle.

[0201] The self-driving vehicle can automatically perform the whistle operation, or there is a whistle button on the steering wheel, and the driver will also perform the whistle operation when pressed.

[0202] (4) Regarding the prompt light, during the process of the driving operation of the self-driving vehicle, the prompt light corresponding to the current driving operation is turned on, so that other agents can clarify the driving operation being performed by the self-driving vehicle. For example, the driving operation currently performed by an autonomous vehicle can be straight, turning, changing lanes, reversing, accelerating, braking, parking, etc. When parking, the autonomous vehicle can light up hazard warning flashes (dual flashing lights), and when changing lanes When the time, the self-driving vehicle can light up the turn signal.

[0203] (5) For the reminder lights, the autonomous vehicle can detect the current environment information during the driving operation, and light up the reminder lights corresponding to the current environment information, so that other agents can identify the location of the autonomous vehicle.

[0204] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0205] 405. After the autonomous vehicle continues to drive to the edge of the current road, perform a parking operation. Proceed to step 408.

[0206] When it is determined that the self-driving vehicle state type is the first fault state type, and the self-driving vehicle does not have the ability to automatically drive but still has the ability to pull over, the self-driving vehicle will continue to drive to the edge of the current road before performing the parking operation.

[0207] 406. When the state type is the second fault state type, output the prompt information corresponding to the second fault state type through the output device of the autonomous vehicle.

[0208] The self-driving vehicle can establish the corresponding relationship between the second fault state type and the prompt information. When the self-driving vehicle determines that the state information belongs to the second fault state type, the corresponding relationship is queried to obtain the prompt information corresponding to the second fault state type , Through the output device of the self-driving vehicle, output the prompt information corresponding to the second fault state type.

[0209] In a possible implementation manner, outputting the prompt information corresponding to the second fault state type through the output device may include at least one of the following:

[0210] (1) For the display screen, when the autonomous vehicle determines that the state type of the current state information belongs to the second fault state type, the fifth prompt message is displayed on the display screen, and the fifth prompt message is used to prompt the automatic driving vehicle to have a serious failure .

[0211] By configuring the display screen, during the driving of the autonomous vehicle, the display screen of the autonomous vehicle displays the fifth prompt information. When other agents view the fifth prompt information of the autonomous vehicle, they can determine the current state of the autonomous vehicle It is the second fault state type.

[0212] In a possible implementation manner, the fifth prompt information may include text information or picture information. For example, the text information may be "I have a serious failure now", and the picture information may be any picture that can reflect a serious failure of the autonomous vehicle.

[0213] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information of autonomous vehicles.

[0214] (2) Regarding the speaker, when the autonomous vehicle determines that the state type to which the current state information belongs is the second fault state type, the sixth prompt message is played through the speaker, and the sixth prompt message is used to prompt the autonomous vehicle to maintain a distance between vehicles.

[0215] Wherein, the sixth prompt information is voice information. By configuring a speaker, the speaker of the self-driving vehicle will play the sixth prompt information during the driving of the autonomous vehicle, so that other agents can listen to the sixth prompt information, thereby interacting with the automatic Drive the vehicle to maintain a distance between vehicles.

[0216] In one possible implementation, one or more speakers can be set up, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. In addition, the speakers can also be placed in the front, rear, left or right of the car. side.

[0217] (3) For the car horn, when the state type of the autonomous vehicle is the second fault state type, the whistle operation can be performed according to the second whistle rhythm.

[0218] Among them, the self-driving vehicle is equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or the electronic whistle. Autopilot vehicles can set the number of whistle sounds in each fixed period to determine the whistle rhythm. Different state types correspond to different whistle rhythms. The period can be one second or one minute, etc.

[0219] In addition, the second whistle rhythm may be a preset rhythm. Alternatively, the self-driving vehicle can establish the correspondence between the second fault state type and the whistle rhythm, and when the self-driving vehicle determines that the state information belongs to the second fault state type, the correspondence relationship is queried to obtain the correspondence with the second fault state type According to the horn rhythm of the second fault state type, the horn operation is performed according to the horn rhythm corresponding to the second fault state type, so that other agents can understand the current state of the autonomous vehicle.

[0220] The self-driving vehicle can automatically perform the whistle operation, or there is a whistle button on the steering wheel, and the driver will also perform the whistle operation when pressed.

[0221] (4) Regarding the prompt light, during the process of the driving operation of the self-driving vehicle, the prompt light corresponding to the current driving operation is turned on, so that other agents can clarify the driving operation being performed by the self-driving vehicle. For example, the driving operation currently performed by an autonomous vehicle can be straight, turning, changing lanes, reversing, accelerating, braking, parking, etc. When parking, the autonomous vehicle can light up hazard warning flashes (dual flashing lights), and when changing lanes When the time, the self-driving vehicle can light up the turn signal.

[0222] (5) For the reminder lights, the autonomous vehicle can detect the current environment information during the driving operation, and light up the reminder lights corresponding to the current environment information, so that other agents can identify the location of the autonomous vehicle.

[0223] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0224] 407. The self-driving vehicle performs a parking operation in the current lane.

[0225] When it is detected that the self-driving vehicle state type is the second fault state type, the self-driving vehicle does not have the ability to automatically drive and does not have the ability to pull to the side, the self-driving vehicle continues to drive in the current lane, and after driving a certain distance in the current lane Carry out the parking operation, or directly execute the parking operation in the current lane.

[0226] 408. The self-driving vehicle outputs prompt information corresponding to the parking state type through the output device.

[0227] Automatically driving vehicles can establish the corresponding relationship between the parking state type and the prompt information. When the automatic driving vehicle determines that the state information belongs to the parking state type, the corresponding relationship is inquired to obtain the prompt information corresponding to the parking state type. The output device outputs the prompt information corresponding to the parking state type.

[0228] In a possible implementation manner, outputting prompt information corresponding to the parking state type through the output device may include at least one of the following:

[0229] (1) For the display screen, when the autonomous vehicle determines that the current state information belongs to the parking state type, the display screen displays the parking prompt information and the parking sign, and the parking prompt information and parking sign are used to prompt the self-driving vehicle to stop. .

[0230] By configuring the display screen, when the self-driving vehicle is parked, the display screen of the self-driving vehicle displays the parking prompt information and parking sign. When other agents view the parking prompt information and parking sign of the self-driving vehicle, the current self-driving vehicle can be determined The status type at is the parking status type.

[0231] In a possible implementation manner, the parking prompt message may be "Please note when parking", and the parking sign may be any sign that can reflect the parking of the autonomous vehicle.

[0232] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information of autonomous vehicles.

[0233] (2) Regarding the speaker, when the autonomous vehicle determines that the state type to which the current state information belongs is the parking state type, the parking prompt information is played through the speaker, and the parking prompt information is used to prompt the autonomous vehicle to park.

[0234] By configuring the speaker, during the driving of the autonomous vehicle, the speaker of the autonomous vehicle will play voice prompts, so that other agents can listen to it and understand the current state of the autonomous vehicle.

[0235] In one possible implementation, one or more speakers can be set up. The speakers can be placed on the roof of an autonomous vehicle. The sound diffusion effect will be better. The speakers can also be placed on the front, back, or right side of the car. The diffusion effect will be relatively close.

[0236] (3) For the car horn, when the state type of the autonomous vehicle is the parking state type, the whistle operation can be performed according to the third whistle rhythm.

[0237] Among them, the self-driving vehicle is equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or the electronic whistle. Autopilot vehicles can set the number of whistle sounds in each fixed period to determine the whistle rhythm. Different state types correspond to different whistle rhythms. The period can be one second or one minute, etc.

[0238] In addition, the third whistle rhythm may be a preset rhythm. Alternatively, the self-driving vehicle can establish the corresponding relationship between the parking state type and the whistle rhythm, and when the self-driving vehicle determines that the state information belongs to the parking state type, the corresponding relationship is inquired to obtain the whistle rhythm corresponding to the parking state type, and follow The whistle tempo corresponding to the type of parking state executes the whistle operation, so that other agents can understand the current state of the autonomous vehicle.

[0239] Self-driving vehicles can automatically perform the whistle operation, or a whistle button is provided on the steering wheel, and the driver will also perform the whistle operation when pressed.

[0240] (4) Regarding the prompt light, during the process of the driving operation of the self-driving vehicle, the prompt light corresponding to the current driving operation is turned on, so that other agents can clarify the driving operation being performed by the self-driving vehicle. For example, the driving operation currently performed by an autonomous vehicle can be straight, turning, changing lanes, reversing, accelerating, braking, parking, etc. When parking, the autonomous vehicle can light up hazard warning flashes (dual flashing lights), and when changing lanes When the time, the self-driving vehicle can light up the turn signal.

[0241] (5) For the reminder lights, the autonomous vehicle can detect the current environment information during the driving operation, and light up the reminder lights corresponding to the current environment information, so that other agents can identify the location of the autonomous vehicle.

[0242] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0243] In addition, the self-driving vehicle can establish a connection with the management server, log in to the management server, and report location information and status information to the management server. And the management server will also control the self-driving vehicle, and can send control instructions to the self-driving vehicle, and the self-driving vehicle will perform corresponding driving operations in accordance with the control instruction. Managers can remotely control autonomous vehicles by controlling the management server to realize overall management of one or more autonomous vehicles.

[0244] In a possible implementation, when the state type is determined to be the first fault state type or the second fault state type during driving, the autonomous vehicle sends a help message to the management server connected to the autonomous vehicle through the wireless network, and calls for help Information is used to indicate that the autonomous vehicle is malfunctioning. The management server receives the distress message of the self-driving vehicle and sends out an alarm message. The management personnel can view the alarm information and rescue the self-driving vehicle in time.

[0245] Among them, self-driving vehicles can be equipped with car networking wireless devices, and communicate with other devices through car networking wireless devices.

[0246] Among them, the help message carries the location information and status type of the autonomous vehicle. Through the location information, managers can clearly know the location of the autonomous vehicle, and through the state type, can understand the failure of the autonomous vehicle.

[0247] Wherein, issuing the alarm information may include: the management server sends the alarm information to the control terminal, the control terminal displays the alarm information, the management personnel holding the control terminal view the alarm information, the alarm information carries the location information of the autonomous vehicle, and the management personnel Go to the location of the autonomous vehicle, drive the autonomous vehicle away, and repair the autonomous vehicle.

[0248] Optionally, the management server sends alarm information to the nearest control terminal, which can notify the nearest management personnel, so as to realize the rescue of the autonomous vehicle in the fastest time.

[0249] Other agents can include smart devices, such as mobile phones, computers, car networking wireless devices, etc. The smart devices can establish a connection with the management server, log in to the management server, and after the autonomous vehicle reports the help information to the management server, the management server will ask for help The information is forwarded to the smart device that logs in to the management server, and the smart device obtains the help information of the autonomous vehicle, knows the location information and status information of the autonomous vehicle, and the user of the smart device can go to the location of the autonomous vehicle. Self-driving vehicles perform maintenance. Or, the risk of the road section where the autonomous vehicle is located can be predicted, so that it can bypass or decelerate in advance, which improves traffic safety and reduces traffic accidents.

[0250] Such as Figure 5 As shown, the state types of the autonomous driving vehicle are divided into three types: normal, fault, and serious fault, and the prompt modes under the three state types are respectively given.

[0251] First, when the autonomous vehicle is running normally, the five-direction display screen can display text prompt information, prompt the dangerous driving operation of the autonomous vehicle through the speaker, and light up the prompt lamp corresponding to the driving operation or environmental information.

[0252] Secondly, when the autonomous vehicle fails, you can drive to the edge of the road and stop. During the driving, the five-direction display screen displays text prompts, and the speaker prompts the autonomous vehicle to pull over and make a rhythmic sound. The whistle warns, lights up the prompt light corresponding to driving operation or environmental information, and sends distress messages through the wireless network. After parking, the five-direction display screen displays text prompt information, prompts the self-driving vehicle to stop through the speaker, sounds the horn rhythmically, lights up the prompt lamp corresponding to the parking state and the prompt lamp corresponding to environmental information, and wirelessly Send help messages online.

[0253] Once again, when an autonomous vehicle has a serious breakdown, keep driving in the current lane and then park in the lane. In the process of driving, the five-direction display screen displays text prompt information, prompts other vehicles to keep the distance through the speaker, sounds the horn rhythmically, lights up the prompt light corresponding to driving operation or environmental information, and passes wireless network Send a distress message. After parking in the current lane, text prompts are displayed on the display screen in five directions, the automatic driving vehicle is prompted to stop through the speaker, the siren is tuned in rhythm, and the warning lights corresponding to the parking state and the warning lights corresponding to environmental information are lit , And send distress messages via wireless network.

[0254] The method provided by the embodiments of this application determines the state type to which the current state information of the self-driving vehicle belongs through real-time detection of the current state information of the self-driving vehicle, and outputs the prompt information corresponding to the state type through the output device of the self-driving vehicle, so that other intelligent The body accurately and fully understands the current state of the autonomous vehicle, can perform operations according to the current state of the autonomous vehicle, avoids conflicts between the operation of other agents and the driving operation of the autonomous vehicle as much as possible, and can reduce the occurrence of traffic accidents Probability, improve safety. Moreover, autonomous vehicles can eliminate misunderstandings, reduce risks, improve traffic safety, and reduce traffic accidents by actively interacting with other agents.

[0255] In addition, the state information of the autonomous vehicle is used to determine whether the autonomous vehicle has automatic driving capability and the ability to pull to the side, thereby determining the state type of the autonomous vehicle, and clarifying the division method of different state types, so as to facilitate subsequent output according to the state type. Prompt information.

[0256] In addition, through the display screen, speaker, reminder light or car whistle, other agents are reminded of the state type of the autonomous vehicle, and the specific reminder method and content are clarified, so other agents can clearly understand the state of the autonomous vehicle. Type, and can perform corresponding operations according to the state of the self-driving vehicle, which can reduce the probability of traffic accidents and improve the safety of the self-driving vehicle.

[0257] In addition, when the self-driving vehicle determines that the state type is the first fault state type during driving, it continues to drive to the edge of the current road and performs a parking operation, and the self-driving vehicle determines that the state type is the second fault state type during the driving process At the time, the parking operation is performed in the current lane, and the prompt information corresponding to the parking state type is output through the output device, which expands the parking state type of the self-driving vehicle, the function is more complete, and the safety of the self-driving vehicle is improved.

[0258] In addition, when the self-driving vehicle determines that the state type is the first fault state type or the second fault state type during the driving process, the distress message is sent to the management server connected to the self-driving vehicle through the wireless network, and the distress message is used to indicate automatic driving When the vehicle fails, you can request the help of the management server in time, or send the state type of the autonomous vehicle to other agents through the management server, so that other agents can know the state of the autonomous vehicle, avoid possible risks, and improve The safety of autonomous vehicles.

[0259] The second interactive mode: prompts the dangerous area within the range of the autonomous vehicle.

[0260] Image 6 It is a flowchart of a prompt method according to an exemplary embodiment, which is applied to an autonomous vehicle, such as Image 6 As shown, the method includes:

[0261] 601. The autonomous vehicle collects environmental information in the current range, and executes step 602 or 608.

[0262] Self-driving vehicles may include self-driving cars, self-driving trucks, and self-driving motorcycles. Components in autonomous vehicles include engine, chassis and body accessories. Body accessories include car networking wireless devices, sound receivers, mechanical or electronic whistle, fuel tanks, tires, car shells, doors, car glass, car mirrors, license plate holders, Seat and seat accessories, car bearings, armrests, handles, handles, cab and cab accessories, airbags, seat belts, window regulators, antennas, wipers, mufflers, horns, car seals, bumpers, luggage compartments , Exhaust pipe, etc.

[0263] Autonomous vehicles need a combination of software systems and hardware systems to realize autonomous driving. The software system includes a perception module, a positioning module, and a decision-making module. The perception module and the positioning module identify and classify other agents. The decision-making module judges whether other agents are special vehicles, whether they are meeting with autonomous vehicles, whether there are abnormalities, etc. based on the behaviors of other agents, and then interact with them through active interaction methods. Other agents interact. The hardware system includes components equipped with autonomous vehicles to interact with other agents, including prompt lights, car whistle, display screens, speakers, and car networking wireless devices.

[0264] In the embodiments of the present application, considering that an autonomous vehicle may encounter a dangerous area during driving, when the dangerous area is in the lane where the autonomous vehicle is currently located or in front of the autonomous vehicle, it will hinder the movement of the autonomous vehicle. Self-driving vehicles need to change the driving route or perform parking operations to avoid traffic accidents.

[0265] Therefore, in order to detect the dangerous area in time and realize safe automatic driving, the automatic driving vehicle needs to collect the environmental information in the current range while driving. For example, an autonomous vehicle can be equipped with a collection device, and the environment information of the current environment can be collected through the collection device.

[0266] Among them, the current range of the autonomous vehicle refers to the range in which the autonomous vehicle can collect environmental information, which can be determined according to the maximum distance at which the acquisition device of the autonomous vehicle collects environmental information. It can be centered on the autonomous vehicle to collect environmental information. The maximum distance of environmental information is a circular area composed of a radius, or a fan-shaped area composed of an autonomous vehicle as the center, the maximum distance of collecting environmental information as the radius, and the collection angle of the collection device as the vertex angle.

[0267] The collection device may include at least one of a camera, a lidar, a millimeter wave radar, an infrared sensor, a humidity sensor, or a temperature sensor, and different types of environmental information can be collected through different collection devices. For example, the environmental information may include temperature, humidity, road surface roughness, the width of the road passable area, the distance between the obstacle and the autonomous vehicle, and the shape information of nearby vehicles.

[0268] 602. When the autonomous vehicle determines that there is a preset dangerous area in the first lane currently located according to the environmental information, it re-determines the passable area, executes step 603 or 605, and executes step 607.

[0269] The preset dangerous area refers to the area that hinders the passage of vehicles, and can include the area where the faulty vehicle is located, the road construction area, or the road closed area.

[0270] In one possible implementation, the preset dangerous area may be an area with a safe passage width less than the preset lane width. When the detected environmental information is that the passable width of the road ahead is less than the preset lane width, it is determined that the front is a preset danger area.

[0271] In another possible implementation, the autonomous vehicle can reconstruct the road structure according to the road information contained in the environmental information, and determine whether the reconstructed road structure is consistent with the road structure stored by the autonomous vehicle, if not, Determine the area in the road where the road structure changes, perform scene recognition on the area, determine the current scene of the area, and determine whether the area is a preset dangerous area. For example, if it is determined through scene recognition that the area is in a construction scene and temporarily impassable, it is determined that the area is a preset dangerous area, or it is determined through scene recognition that a traffic accident has occurred in the area and it is in a vehicle breakdown scene and other vehicles cannot pass. Make sure that the area is a preset dangerous area.

[0272] The self-driving vehicle can determine the conditions that the environmental information of the preset dangerous area should meet. When the self-driving vehicle is driving in the first lane and the environmental information is collected, it can determine whether the environmental information of the first lane meets the preset conditions. When the environmental information meets the preset condition, it is determined that there is a preset dangerous area in the first lane where the autonomous vehicle is currently located. When the environmental information does not meet the preset condition, it is determined that there is no preset dangerous area in the first lane where the autonomous vehicle is currently located.

[0273] Or the autonomous vehicle determines the environmental characteristics corresponding to the environmental information of the preset dangerous area. When the autonomous vehicle is driving in the first lane and collects the environmental information of the first lane, the environmental characteristics corresponding to the environmental information are It is assumed that the environmental characteristics corresponding to the dangerous area are matched, and when the similarity between the two is higher than the preset threshold, it is determined that there is a preset dangerous area in the first lane where the autonomous vehicle is currently located. When the similarity between the two is not higher than the preset threshold, it is determined that there is no preset dangerous area in the first lane where the autonomous vehicle is currently located.

[0274] When an autonomous vehicle determines that there is a preset dangerous area in the first lane, in order to ensure safety, it is necessary to re-determine the passing area.

[0275] For example, an autonomous vehicle can determine an area with a passable width greater than a preset lane width based on the collected environmental information as the re-determined pass area.

[0276] In one possible implementation, the autonomous vehicle determines that there is a preset dangerous area in the first lane currently located according to the environmental information. At this time, the autonomous vehicle determines the first lane currently located, detects the lane boundary, and determines The second lane adjacent to the first lane.

[0277] Since the first lane is adjacent to the second lane, part of the second lane is also within the current range of the autonomous vehicle. Therefore, the environmental information collected by the autonomous vehicle includes the environmental information of the first lane and the environment of the second lane Information, the lane dividing line can be detected according to the collected environmental information and the second lane can be determined.

[0278] Further, after the autonomous vehicle determines the second lane, it can be determined whether there is a preset dangerous area in the second lane. The method of determining whether there is a preset dangerous area in the second lane is similar to the above-mentioned method of determining whether there is a preset dangerous area in the first lane, and will not be repeated here. When there is no preset dangerous area in the second lane, it is determined that the second lane is the pass area of ​​the autonomous vehicle. When there is also a preset dangerous area in the second lane, the second lane is no longer determined as a passable area.

[0279] In another possible implementation, the autonomous vehicle determines that there is a preset dangerous area in the first lane currently located according to the environmental information. At this time, the autonomous vehicle can determine whether there is a space other than the current road based on the environmental information. Passable area. For example, detecting the dividing line between the road and the free space road surface outside the road, determining the width of the free space road surface area, when the width of the free space road surface is greater than the width of the autonomous vehicle, the free space road surface area can be passed Determined as a passable area for autonomous vehicles.

[0280] Through the above two methods, there are two types of traffic areas, one is the second lane adjacent to the first lane in the current road, and the other is the free space road surface outside the road. It should be noted that the priority of lanes is higher than that of free-space pavements, that is, when it is detected that an existing lane can be used as a passable area, and a free-space pavement that is not in any lane can be used as a passable area, the priority is selected as the lane Passable area.

[0281] Depending on the type of the determined passing area, the following step 603 or 605 can be performed.

[0282] 603. When the traffic area is a second lane different from the first lane, the autonomous driving vehicle drives from the first lane to the second lane.

[0283] When the autonomous vehicle detects that there is a preset dangerous area in front of the current lane, and the re-determined traffic area is a second lane different from the first lane, it executes a lane change operation and drives from the first lane to the second lane.

[0284] 604. In the process of driving from the first lane to the second lane, the self-driving vehicle outputs prompt information corresponding to the lane changing operation through the output device.

[0285] The self-driving vehicle is equipped with an output device, and the output device includes at least one of a display screen, a speaker, a car whistle, or a warning light. Wherein, the number of display screens may be one or more, and the facing directions may include front, rear, left, right, and top, so as to realize the function of displaying information in the multiple directions. And the display screen can include multiple types of display screens such as subtitle screens and video screens. There can be one or more speakers, which can be installed on the roof or side of the car. The car whistle can include a mechanical whistle or an electronic whistle. The warning lights include turn signals, fog lights, and position lights.

[0286] The autonomous vehicle can establish the corresponding relationship between the lane change operation and the prompt information. When the autonomous vehicle performs the lane change operation, the corresponding relationship is inquired to obtain the prompt information corresponding to the lane change operation. Through the output device of the autonomous vehicle, The prompt information corresponding to the lane changing operation is output.

[0287] In a possible implementation manner, the output of the prompt information corresponding to the lane changing operation through the output device may include at least one of the following:

[0288] (1) Regarding the display screen, when the autonomous vehicle performs a lane change operation, the lane change prompt information is displayed on the display screen, and the lane change prompt information is used to prompt the autonomous vehicle to change lanes.

[0289] By configuring the display screen, the display screen of the autonomous vehicle displays the lane change prompt information during the lane change process of the autonomous vehicle. When other agents view the lane change prompt information of the autonomous vehicle, it can be determined that the current autonomous vehicle is changing Lane.

[0290] In one possible implementation, the lane change prompt information may include text information or picture information. For example, the text information may be "I am changing lanes", and the picture information may be any picture that can reflect that the autonomous vehicle is changing lanes.

[0291] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information displayed by the autonomous vehicle.

[0292] (2) For the speaker, when the autonomous vehicle performs the lane change operation, the lane change prompt message is played through the speaker, and the lane change prompt message is used to prompt the autonomous vehicle to change lanes.

[0293] Among them, the lane change prompt information is voice information. By configuring a speaker, the speaker of the autonomous vehicle plays the lane change prompt information during the lane change process of the autonomous vehicle, so that other agents can listen to the lane change prompt information and understand The autonomous vehicle is currently changing lanes.

[0294] In one possible implementation, one or more speakers can be set up, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. In addition, the speakers can also be placed in the front, rear, left or right of the car. side.

[0295] (3) For the warning lights, when the autonomous vehicle is performing a lane-changing driving operation, turn on the turn signal corresponding to the currently executed lane-changing driving operation, so that other agents can make it clear that the autonomous vehicle is changing lanes.

[0296] Among them, the warning lights include turn signals, fog lights, and outline lights.

[0297] After changing to the second lane, the self-driving vehicle will drive in the second lane. At this time, the self-driving vehicle does not need to input the prompt information corresponding to the lane change operation, but it can also output the current state information of the self-driving vehicle or the current execution For the prompt information corresponding to the driving operation, the embodiment of this application does not limit the output prompt information.

[0298] 605. When the passage area is not in any lane, the autonomous vehicle drives from the first lane to the passage area.

[0299] 606. During the process of driving from the first lane to the passable area and during the process of driving in the passable area, the autonomous driving vehicle outputs the prompt information for maintaining the distance between the vehicles through the output device.

[0300] When the self-driving vehicle detects that there is a preset dangerous area in front of the current lane, and the re-determined pass area is on a free space pavement and not in any lane, the self-driving vehicle will drive from the first lane to the pass area, and then Drive in this passable area.

[0301] During the process of driving from the first lane to the passage area and in the passage area, the self-driving vehicle lacks lane constraints, has a higher probability of unknown risks, and has poor safety. Therefore, when driving from the first lane to the passage area In the process of driving and driving in the traffic area, it is necessary to output the prompt message to maintain the distance between the vehicles through the output device.

[0302] In a possible implementation manner, outputting the prompt information corresponding to maintaining the distance between vehicles through the output device may include at least one of the following:

[0303] (1) Regarding the display screen, when the autonomous vehicle is driving from the first lane to the passage area and driving in the passage area, the display screen will display the reminder information of keeping the distance between vehicles, and the reminder information of keeping the distance between vehicles will be used to remind others The agent maintains a distance between the vehicle and the autonomous vehicle.

[0304] By configuring the display screen, during the driving process of the autonomous vehicle, the display screen of the autonomous vehicle displays the reminding message of keeping the distance. When other agents check the reminding information of keeping the distance of the autonomous vehicle, it can determine the current need and automatic driving The vehicle maintains a distance between vehicles.

[0305] In one possible implementation, the prompt information for maintaining the distance between vehicles may include text information or image information. For example, the text information may be "please maintain the distance between vehicles", and the image information may be any information that reflects the need to maintain a distance between the vehicle and the autonomous vehicle. image.

[0306] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information displayed by the autonomous vehicle.

[0307] (2) For the speaker, when the autonomous vehicle is driving from the first lane to the pass area and in the pass area, the speaker will play the distance keeping prompt message, and the distance keeping prompt information will be used to remind other intelligences. Maintain a distance between the body and the autonomous vehicle.

[0308] Wherein, the distance-maintaining prompt information is voice information. By configuring a speaker, the speaker of the self-driving vehicle will play the distance-maintaining prompt information during the driving of the autonomous vehicle so that other agents can listen to the distance-maintaining prompt information. Understand the current need to maintain a distance between autonomous vehicles.

[0309] In one possible implementation, one or more speakers can be set up, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. In addition, the speakers can also be placed in the front, rear, left or right of the car. side.

[0310] 607. During the process of driving from the first lane to the passable area and during the process of driving in the passable area, output the prompt information corresponding to the preset dangerous area through the output device of the autonomous vehicle.

[0311] The prompt information corresponding to the preset dangerous area includes text with dangerous words, the picture of the preset dangerous area, the location information of the preset dangerous area, the voice information that the dangerous area is broadcast, and the whistle prompts the dangerous area to exist.

[0312] In a possible implementation manner, outputting prompt information corresponding to the preset dangerous area through the output device may include at least one of the following:

[0313] (1) For the display screen, when a preset dangerous area exists in the first lane where the autonomous vehicle is currently located, the first prompt information is displayed on the display screen, and the first prompt information is used to prompt the location of the preset dangerous area.

[0314] By configuring the display screen, during the driving of the autonomous vehicle, the display screen of the autonomous vehicle displays the first prompt information. When other agents view the first prompt information of the autonomous vehicle, they can determine the current location of the autonomous vehicle There is a preset danger zone in the first lane.

[0315] In a possible implementation manner, the first prompt information may include text information or picture information, for example, the text information may be "the road ahead is blocked", and the picture information may be any picture that can reflect the location of the preset dangerous area.

[0316] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information of autonomous vehicles.

[0317] In one possible implementation manner, displaying the first prompt information on the display screen includes: displaying text information on the first display screen, and the text information is used to prompt the location of the preset dangerous area; and displaying the image on the second display screen Information, image information is used to prompt the current dangerous area; the first display screen is the display screen on the side of the self-driving vehicle close to the preset dangerous area, and the second display screen is the display on the side of the self-driving vehicle far away from the preset dangerous area screen.

[0318] Prompt messages are displayed on the side of the autonomous vehicle near the preset danger zone and the side far from the preset danger zone. The display screen on the side close to the preset danger zone displays text information, prompting the location of the preset danger zone so that it is close to the preset danger zone. It is assumed that other agents on the side of the dangerous area learn about the dangerous situation early, and avoid giving way or slow down as soon as possible, which reduces the probability of traffic accidents. The display screen on the side far from the preset dangerous area displays image information, prompting that there is a dangerous area, so that other agents on the side far from the preset dangerous area can better understand the driving behavior of the autonomous vehicle, give way in time, and improve safety Sex.

[0319] (2) Regarding the speaker, when the autonomous vehicle determines that the current first lane has a preset dangerous area, the second prompt message is played through the speaker, and the second prompt information is used to prompt the location of the preset dangerous area.

[0320] Wherein, the second prompt information is voice information. By configuring a speaker, the speaker of the self-driving vehicle plays the second prompt information during the driving of the autonomous vehicle, so that other agents can listen to the second prompt information and learn about the prediction. Set the location of the hazardous area.

[0321] In one possible implementation, one or more speakers can be set up, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. In addition, the speakers can also be placed in the front, rear, left or right of the car. side.

[0322] (3) For car horns, when there is a preset dangerous area in the first lane where the autonomous vehicle is currently located, the whistle can be performed in accordance with the whistle rhythm.

[0323] Among them, the self-driving vehicle is equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or the electronic whistle. Autopilot vehicles can set the number of whistle sounds in each fixed period to determine the whistle rhythm. Different state types correspond to different whistle rhythms. The period can be one second or one minute, etc.

[0324] It should be noted that step 607 can be executed simultaneously with steps 603-604 or steps 605-606, and the output device can output different types of prompt information at the same time, for example, when driving from the first lane to the second lane, it can output The prompt information corresponding to the lane changing operation can also output the prompt information corresponding to the preset dangerous area. For example, the prompt message can be "There is a construction area ahead and lanes are being changed".

[0325] 608. When it is determined according to the environmental information that there is a preset dangerous area in the first lane currently located, but there is no passable area within the preset range, the autonomous vehicle performs a parking operation.

[0326] When it is determined according to the environmental information that there is a preset dangerous area in the first lane, but there is no passable area within the preset range, the autonomous vehicle cannot pass. To ensure safety, the autonomous vehicle performs a parking operation.

[0327] 609. Through the output device, the self-driving vehicle outputs prompt information corresponding to the parking operation.

[0328] In a possible implementation manner, outputting the prompt information corresponding to the parking operation through the output device may include at least one of the following:

[0329] (1) Regarding the display screen, when the self-driving vehicle performs a parking operation, the display screen displays the parking text prompt information and the parking sign. The parking text prompt information and the parking sign are used to prompt the self-driving vehicle to stop.

[0330] By configuring the display screen, when the self-driving vehicle performs parking operations, the display screen of the self-driving vehicle displays the parking text prompt information and parking sign. When other agents view the parking text prompt information and parking sign of the self-driving vehicle, it can be determined The driving operation currently performed by the autonomous vehicle is a parking operation.

[0331] In a possible implementation manner, the parking text prompt information may be "Please note when parking", and the parking sign may be any sign that can reflect the parking of the autonomous vehicle.

[0332] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information of autonomous vehicles.

[0333] (2) For the speaker, when the autonomous vehicle performs a parking operation, the parking voice prompt information is played through the speaker, and the parking voice prompt information is used to prompt the autonomous vehicle to stop.

[0334] By configuring the speaker, when the self-driving vehicle performs a parking operation, the speaker of the self-driving vehicle will play the parking voice prompt information, so that other agents can listen to the parking voice prompt information and learn that the self-driving vehicle is currently parking.

[0335] In a possible implementation, one or more speakers can be set, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. The speakers can also be placed on the front, back, or right side of the car. The diffusion effect will be relatively close.

[0336] (3) For the reminder light, when the autonomous vehicle performs a parking operation, the reminder light corresponding to the parking operation is lit, so that other agents can make it clear that the autonomous vehicle is parking.

[0337] In the embodiment of the present application, the autonomous driving vehicle may establish a connection with the management server, log in to the management server, and report location information and status information to the management server. And the management server will also control the self-driving vehicle, and can send control instructions to the self-driving vehicle, and the self-driving vehicle will perform corresponding driving operations in accordance with the control instruction. Managers can remotely control autonomous vehicles by controlling the management server to realize overall management of one or more autonomous vehicles.

[0338] In a possible implementation, when it is determined that the autonomous vehicle is impassable during driving, the autonomous vehicle sends a distress message to the management server connected to the autonomous vehicle through the wireless network, and the distress message is used to indicate that the autonomous vehicle is impassable . The management server receives the distress message of the self-driving vehicle and sends out an alarm message. The management personnel can view the alarm information and rescue the self-driving vehicle in time.

[0339] Among them, self-driving vehicles can be equipped with car networking wireless devices, and communicate with other devices through car networking wireless devices.

[0340] Among them, the help message carries the location information and status information of the autonomous vehicle. Through the location information, managers can clearly know the location of the autonomous vehicle, and through the status information, they can understand that the autonomous vehicle is impassable.

[0341] Wherein, issuing the alarm information may include: the management server sends the alarm information to the control terminal, the control terminal displays the alarm information, the management personnel holding the control terminal view the alarm information, the alarm information carries the location information of the autonomous vehicle, and the management personnel Go to the location of the autonomous vehicle to process the autonomous vehicle.

[0342] Optionally, the management server sends an alarm message to the nearest control terminal, which can notify the nearest management personnel, so that the automatic driving vehicle can be processed in the fastest time.

[0343] Other agents can include smart devices, such as mobile phones, computers, car networking wireless devices, etc. The smart devices can establish a connection with the management server, log in to the management server, and after the autonomous vehicle reports the help information to the management server, the management server will ask for help The information is forwarded to the smart device that logs in to the management server, and the smart device obtains the help information of the autonomous vehicle, knows the location information and status information of the autonomous vehicle, and the user of the smart device can go to the location of the autonomous vehicle. Preset dangerous areas for processing. Or, it can be predicted that there is a preset dangerous area on the road section where the autonomous vehicle is located, so that it can bypass in advance, which improves the safety of traffic and reduces traffic accidents.

[0344] In the embodiment of the present application, during the driving of the autonomous vehicle, the current state information of the autonomous vehicle is also detected in real time, and the prompt information corresponding to the state information is output through the output device. And this process can be executed in parallel in the process of executing the above 601-609.

[0345] Among them, the state information of the autonomous vehicle is used to indicate the state of the autonomous vehicle. The status information includes the driving speed, driving distance, remaining fuel amount, the operating status of each component, and the on and off status of the prompt light of the autonomous vehicle.

[0346] Wherein, outputting the prompt information corresponding to the status information through the output device may include at least one of the following:

[0347] (1) During the driving operation of the self-driving vehicle, the prompt light corresponding to the current driving operation is turned on, so that other agents can identify the driving operation being performed by the self-driving vehicle. For example, the driving operation currently performed by an autonomous vehicle can be straight, turning, changing lanes, reversing, accelerating, braking, parking, etc. When parking, the autonomous vehicle can light up hazard warning flashes (dual flashing lights), and when changing lanes When the time, the self-driving vehicle can light up the turn signal.

[0348] (2) During the driving operation of the self-driving vehicle, it can detect the current environmental information and light up the reminder light corresponding to the current environmental information, so that other agents can clarify the location of the self-driving vehicle.

[0349] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0350] Such as Figure 7 As shown, according to the difference in the passage area determined by the automatic driving vehicle, it is divided into three situations: lane, free space road surface and no-passing area, and the prompt ways of the automatic driving vehicle in the three situations are respectively given.

[0351] First, when the traffic area is the lowest risk lane, the autonomous vehicle avoids the preset dangerous area and changes lanes from the current lane to the lane. In the process of changing lanes, the lane change prompt message is displayed on the display screen, the location of the dangerous area is displayed on the display screen on the side close to the dangerous area, and the dangerous image is displayed on the display screen on the side away from the dangerous area; other vehicles are notified through the speaker Maintain the distance between vehicles and prompt the location of the preset dangerous area; turn on the turn signal corresponding to the operation of changing lanes; sound the horn to warn rhythmically.

[0352] Secondly, when the traffic area is a free-space road, the autonomous vehicle drives on a free-space road. The display screen displays the warning message to keep the distance between vehicles and the display screen on the side close to the dangerous area prompts the location of the dangerous area. The display screen on the side of the area displays dangerous images; through the loudspeaker, other vehicles are reminded to maintain the distance between the vehicles and the position of the preset dangerous area; the horns are sounded rhythmically.

[0353] Third, when there is no passable area, the self-driving vehicle parks on the road. The display screen displays the parking text prompt message and the parking sign to prompt the self-driving vehicle to stop, and the display screen near the dangerous area prompts the location of the dangerous area. The display screen on the side away from the dangerous area displays dangerous images; the position of the preset dangerous area is prompted by the loudspeaker; the whistle is rhythmically warned; and the distress message is sent through the wireless network.

[0354] The method provided by the embodiment of the present application collects environmental information in the current range, and determines the preset dangerous area in the first lane currently located according to the environmental information, and then re-determines the passable area, and when driving from the first lane to In the passable area and during driving in the passable area, the output device outputs the prompt information corresponding to the preset dangerous area, so that other agents can learn the existence of the preset dangerous area and better understand the driving operation of the autonomous vehicle. Corresponding operations can be performed according to the driving operation of the autonomous vehicle, and the conflict between the operation of other agents and the driving operation of the autonomous vehicle can be avoided as much as possible, the probability of traffic accidents can be reduced, and the safety can be improved. Moreover, autonomous vehicles can eliminate misunderstandings, reduce risks, improve traffic safety, and reduce traffic accidents by actively interacting with other agents.

[0355] In addition, the prompt information displayed on the display screen, the speaker voice broadcasts the prompt information, the rhythmic whistle, and the diversified prompt channels can increase the probability of other agents receiving the prompt information, and avoid the failure to output the prompt information due to a failure of an output device. This in turn causes traffic accidents and improves the safety of autonomous driving.

[0356] In addition, prompt messages are displayed on the side of the autonomous vehicle near the preset danger area and the side far from the preset danger area, and the display screen on the side near the preset danger area displays text information, prompting the location of the preset danger area so that it is located Other agents on the side of the pre-determined dangerous area learn early that there is a dangerous situation, and avoid giving way or slowing down early, which reduces the probability of traffic accidents. The display screen on the side far from the preset dangerous area displays image information, prompting that there is a dangerous area, so that other agents on the side far from the preset dangerous area can better understand the driving behavior of the autonomous vehicle, give way in time, and improve safety Sex.

[0357] In addition, when the traffic area is a second lane that is different from the first lane, during the process of driving from the first lane to the second lane, the output device prompts that the autonomous vehicle is performing lane change operations, which can make other agents understand Self-driving vehicles act and give way.

[0358] In addition, when the passable area is not in any lane, when driving from the first lane to the passable area and during the process of driving in the passable area, the output device prompts to maintain the distance information, which improves the free space of the autonomous vehicle The safety of driving in.

[0359] In addition, when it is determined based on the environmental information that there is a preset dangerous area in the first lane, but there is no passable area within the preset range, the distress message is sent to the management server connected to the autonomous vehicle through the wireless network. It is used to indicate that the autonomous vehicle is unable to pass, and can obtain the help of the management server in time. It can also send the status of the autonomous vehicle to other agents through the management server, so that other agents can know the status of the autonomous vehicle in advance and avoid possible occurrences. Risks improve the safety of autonomous vehicles.

[0360] The third interaction method: prompts the target vehicle within the range of the autonomous vehicle.

[0361] Figure 8 Is a flow chart of a prompt method according to an exemplary embodiment, such as Figure 8 As shown, the method includes:

[0362] 801. The self-driving vehicle acquires the vehicle characteristics of any vehicle in the current range.

[0363] Self-driving vehicles may include self-driving cars, self-driving trucks, and self-driving motorcycles. Components in autonomous vehicles include engine, chassis and body accessories. Body accessories include car networking wireless devices, sound receivers, mechanical or electronic whistle, fuel tanks, tires, car shells, doors, car glass, car mirrors, license plate holders, Seat and seat accessories, car bearings, armrests, handles, handles, cab and cab accessories, airbags, seat belts, window regulators, antennas, wipers, mufflers, horns, car seals, bumpers, luggage compartments , Exhaust pipe, etc.

[0364] Autonomous vehicles need a combination of software systems and hardware systems to realize autonomous driving. The software system includes a perception module, a positioning module, and a decision-making module. The perception module and the positioning module identify and classify other agents. The decision-making module judges whether other agents are special vehicles, whether they are meeting with autonomous vehicles, whether there are abnormalities, etc. based on the behaviors of other agents, and then interact with them through active interaction methods. Other agents interact. The hardware system includes components equipped with autonomous vehicles to interact with other agents, including prompt lights, car whistle, display screens, speakers, and car networking wireless devices.

[0365] There are many special types of vehicles in daily life, including ambulances, fire trucks, police cars, etc. These types of vehicles need to perform tasks and require priority in the road. Therefore, when an ordinary vehicle encounters this type of vehicle, it needs to make an evasion and cannot hinder the normal driving of this type of vehicle.

[0366] In the embodiments of this application, in order to solve the above-mentioned problems, the autonomous vehicle will set the conditions that the target vehicle belonging to the preset avoidance type should meet, so as to identify the target vehicle belonging to the preset avoidance type during driving. When the target vehicle is in automatic The driving vehicle is currently in the lane or in the lane adjacent to the lane where the autonomous vehicle is currently located. The autonomous vehicle may hinder the normal driving of the target vehicle. The autonomous vehicle needs to accelerate, decelerate and avoid, or change lanes Driving operation to avoid affecting the normal driving of the target vehicle.

[0367] Among them, the target vehicle may include an ambulance, a fire engine, a police car, or other special types of vehicles.

[0368] In order to recognize the target vehicle in time without affecting the normal driving of the target vehicle, the autonomous vehicle needs to obtain the vehicle characteristics of any vehicle in the current range during the driving process, so as to determine whether the vehicle is the target vehicle based on the vehicle characteristics .

[0369] Optionally, the self-driving vehicle can be equipped with a collection device, and the vehicle characteristics of any vehicle in the current range can be obtained through the collection device.

[0370] Among them, the current range of the autonomous vehicle refers to the range in which the autonomous vehicle can recognize environmental information. It can be determined according to the maximum distance at which the acquisition device of the autonomous vehicle collects environmental information. It can be centered on the autonomous vehicle to collect information. The maximum distance of environmental information is a circular area composed of a radius, or a fan-shaped area composed of an autonomous vehicle as the center, the maximum distance of collecting environmental information as the radius, and the collection angle of the collection device as the vertex angle.

[0371] The acquisition device may include at least one of a camera, a lidar, a millimeter wave radar, an infrared sensor, a humidity sensor, or a temperature sensor, and different types of vehicle characteristics can be acquired through different acquisition devices. For example, the vehicle characteristics may include appearance characteristics, lamp status, whistle status, and the like.

[0372] 802. The autonomous driving vehicle matches the vehicle characteristics with the preset vehicle characteristics corresponding to the preset avoidance type.

[0373] The self-driving vehicle can set the preset vehicle characteristics corresponding to the preset avoidance type according to the characteristics of the target vehicle belonging to the preset avoidance type. When the autopilot vehicle is in the driving process and obtains the vehicle characteristics in the current range, the vehicle characteristics are matched with the preset vehicle characteristics corresponding to the preset avoidance type to determine whether the vehicle belongs to the target of the preset avoidance type vehicle.

[0374] For example, for a police car, an autonomous vehicle can determine the preset vehicle characteristics of a police car, including: iconic text drawn on the body, colored lights on the roof, flashing lights during driving, and siren sounds.

[0375] 803. When the similarity between the vehicle feature and the preset vehicle feature is greater than the preset threshold, the autonomously driving vehicle determines that the vehicle is a target vehicle of a preset avoidance type.

[0376] When the similarity between the acquired vehicle feature and the preset vehicle feature is greater than the preset threshold, it is determined that the vehicle is a target vehicle belonging to the preset avoidance type. When the similarity between the two is not higher than the preset threshold, it is determined that the vehicle is not a target vehicle of the preset avoidance type. The preset threshold may be determined according to the requirement of recognition accuracy, which is not limited in the embodiment of the present application.

[0377] It should be noted that the above steps 801-803 are optional steps. The automated driving vehicle may use steps 801-803 to determine the target vehicle belonging to the preset avoidance type, but other methods may also be used to determine the target vehicle belonging to the preset avoidance type.

[0378] In a possible implementation manner, the shape feature and the status of the prompt light of any vehicle within the range are acquired. When the shape feature of the vehicle matches the preset shape feature corresponding to the preset avoidance type, and the status of the prompt light is on, it is determined that the vehicle is a target vehicle belonging to the preset avoidance type.

[0379] The appearance characteristics of the vehicle may include the outline of the vehicle, the color of the vehicle body, the size of the vehicle, the logo of the vehicle, the number of wheels, etc. The prompt light includes the warning light of the vehicle, the hazard warning flashlight, etc.

[0380] The self-driving vehicle can set the preset appearance characteristics of the target vehicle and the reminder lights that the target vehicle should light up when performing tasks. Then when the self-driving vehicle is in the process of driving, it obtains the shape feature and the status of the warning light of the vehicle in the current range, matches the shape feature of the vehicle with the preset shape feature, and judges whether the similarity between the two is higher than The preset threshold is used to determine that the vehicle's reminder light state is on. If the similarity between the vehicle's appearance feature and the preset shape feature is higher than the preset threshold, and the vehicle's reminder light state is on, confirm The vehicle is a target vehicle belonging to the preset avoidance type.

[0381] Among them, the self-driving vehicle can be equipped with a camera to collect the vehicle's appearance characteristics and the status of the reminder light through the camera, and the reminder light is a reminder light used to remind the task being performed in the target vehicle, such as a reminder light on the roof.

[0382] In another possible implementation manner, the shape feature and whistle state of any vehicle within the range are acquired. When the shape feature of the vehicle matches the preset shape feature corresponding to the preset avoidance type, and the whistle state is a whistle state, it is determined that the vehicle is a target vehicle belonging to the preset avoidance type.

[0383] The self-driving vehicle can set preset shape characteristics that the shape of the target vehicle should meet, and the target vehicle should perform a whistle operation when performing tasks. Then when the self-driving vehicle is in the process of driving, it obtains the shape characteristics and the whistle state of the vehicle in the current range, matches the shape characteristics of the vehicle with the preset shape characteristics, and judges whether the similarity between the two is higher than Preset threshold; determine whether the whistle state of the vehicle is the whistle state, if the similarity between the vehicle's appearance feature and the preset appearance feature is higher than the preset threshold, and the vehicle is currently in the whistle state, determine the vehicle It is a target vehicle belonging to the preset avoidance type.

[0384] Among them, the self-driving vehicle can be equipped with a camera to collect the appearance characteristics of the vehicle through the camera, and it can also be equipped with a sound receiver to collect the sound of the vehicle through the sound receiver.

[0385] Optionally, considering that the sound emitted by the vehicle may include whistle sound and horn sound, in addition, the environment may also include other noises. Therefore, in order to improve the accuracy, the self-driving vehicle can also set the preset whistle feature that the target vehicle should whistle when performing the task. Then, when the self-driving vehicle is driving, the shape feature of the vehicle in the current range is obtained When matching the sound feature, match the shape feature of the vehicle with the preset shape feature, determine whether the similarity between the shape feature and the preset shape feature is higher than the preset threshold; match the sound feature with the preset whistle feature, Determine whether the similarity between the sound feature and the preset sound feature is higher than the preset threshold, if the similarity between the shape feature and the preset shape feature is higher than the preset threshold, and the sound feature is similar to the preset sound feature Above the preset threshold, it is determined that the vehicle is a target vehicle of the preset avoidance type.

[0386] In another possible implementation manner, the shape feature, prompt light state, and whistle state of any vehicle within the range are acquired. When the shape feature of the vehicle matches the preset shape feature corresponding to the preset avoidance type, the prompt light state is on, and the whistle state is the whistle state, it is determined that the vehicle is a target vehicle of the preset avoidance type. The specific process is similar to the above two possible implementations, and will not be repeated here.

[0387] When it is determined that there is a target vehicle of the preset avoidance type in the current area of ​​the autonomous vehicle, if the autonomous vehicle is driving towards the target vehicle, but the autonomous vehicle will not meet the target vehicle, the autonomous vehicle will drive normally. No need to avoid the target vehicle.

[0388] Or, when it is determined that there is no target vehicle belonging to the preset avoidance type within the current range of the automatic driving vehicle, the automatic driving vehicle runs normally without avoiding the target vehicle.

[0389] 804. The self-driving vehicle performs a driving operation for avoiding the target vehicle.

[0390] When the autonomous vehicle determines that there is a target vehicle of the preset avoidance type in the current range, the autonomous vehicle needs to perform different driving operations to avoid the target vehicle in different situations.

[0391] Therefore, the foregoing step 804 may include the following implementation manners (1)-(3):

[0392] (1) If the autonomous driving vehicle and the target vehicle are traveling in the same direction, and the autonomous driving vehicle is located behind the target vehicle, keep driving behind the target vehicle.

[0393] For example, if an autonomous vehicle recognizes the rear of the target vehicle through a camera located in the front, it can be determined that the autonomous vehicle is driving in the same direction as the target vehicle, and the autonomous vehicle is located behind the target vehicle and keeps driving behind the target vehicle. That's it.

[0394] (2) If the self-driving vehicle is traveling in the same direction as the target vehicle, and the self-driving vehicle is in front of the target vehicle, avoid the target vehicle.

[0395] For example, if an autonomous vehicle recognizes the front of the target vehicle through a camera located at the rear, it can be determined that the autonomous vehicle is driving in the same direction as the target vehicle, and the autonomous vehicle is in front of the target vehicle, and the target vehicle needs to be avoided at this time.

[0396] Further, the self-driving vehicle may also consider the current lane and the lane where the target vehicle is currently located, and determine whether to avoid the target vehicle according to the lane.

[0397] In one possible implementation, if the autonomous vehicle and the target vehicle are traveling in the same direction, the autonomous vehicle is in front of the target vehicle, and the autonomous vehicle and the target vehicle are in different lanes, the autonomous vehicle does not need to avoid the target in the current lane Vehicles, when the subsequent automatic driving vehicle meets the target vehicle, perform the deceleration operation to avoid the target vehicle.

[0398] In another possible implementation, if the autonomous vehicle is driving in the same direction as the target vehicle, the autonomous vehicle is in front of the target vehicle, and the autonomous vehicle and the target vehicle are in the same lane, the acceleration operation or lane change operation is performed. At least one.

[0399] At this time, the autonomous driving vehicle will affect the driving of the target vehicle. In order to ensure the normal driving of the target vehicle, the autonomous driving vehicle can perform an acceleration operation to ensure that the driving speed of the target vehicle will not be affected by the driving speed of the target vehicle. In addition, self-driving vehicles can also perform lane-changing operations to change to other lanes so that the target vehicle can pass.

[0400] In one possible implementation, if the autonomous vehicle and the target vehicle are driving in the same direction, the autonomous vehicle is in front of the target vehicle, and the autonomous vehicle and the target vehicle are in the same lane, and there is a traffic area in the adjacent lane, the lane change is executed operating;

[0401] In another possible implementation, if the autonomous vehicle and the target vehicle are driving in the same direction, the autonomous vehicle is in front of the target vehicle, and the autonomous vehicle and the target vehicle are in the same lane, but there is no passable area in the adjacent lane, execute Accelerate, until there is a traffic area in the adjacent lanes, perform lane change operations.

[0402] (3) If the self-driving vehicle and the target vehicle are driving opposite to each other, when the self-driving vehicle does not meet the target vehicle, it can drive normally without avoiding the target vehicle. When the self-driving vehicle meets the target vehicle, the deceleration operation is performed.

[0403] 805. In the process of performing the driving operation, output the prompt information of the target vehicle through the output device of the self-driving vehicle.

[0404] The self-driving vehicle is equipped with an output device, and the output device includes at least one of a display screen, a speaker, a car whistle, or a warning light. Wherein, the number of display screens may be one or more, and the facing directions may include front, rear, left, right, and top, so as to realize the function of displaying information in the multiple directions. And the display screen can include multiple types of display screens such as subtitle screens and video screens. There can be one or more speakers, which can be installed on the roof or side of the car. The car whistle can include a mechanical whistle or an electronic whistle. The warning lights include turn signals, fog lights, and position lights.

[0405] Step 805 may include at least one of the following steps (1) or (2):

[0406] (1) Through the output device, output prompt information related to the location of the target vehicle.

[0407] (1-1) see Picture 9 , Through the display screen, the first prompt information is displayed, and the first prompt information is used to prompt the location of the target vehicle of other agents.

[0408] By configuring the display screen, during the driving of the autonomous vehicle, the display screen of the autonomous vehicle displays the first prompt information. When other agents view the first prompt information of the autonomous vehicle, they can determine the current location of the autonomous vehicle There is a target vehicle in the range, and other agents can also avoid the target vehicle so that the target vehicle can drive normally.

[0409] In a possible implementation manner, the first prompt information may include text information or picture information. For example, the text information may be "avoid the target vehicle", and the picture information may be any picture that can reflect the characteristics of the target vehicle.

[0410] (1-2) See Picture 9 , The second prompt message is played through the speaker, and the second prompt message is used to prompt the location of the target vehicle of other agents.

[0411] Wherein, the second prompt information is voice information. By configuring a speaker, the speaker of the self-driving vehicle plays the second prompt information during the driving of the autonomous vehicle, so that other agents can listen to the second prompt information and learn about the target The location of the vehicle, and other agents can also avoid the target vehicle so that the target vehicle can drive normally.

[0412] In one possible implementation, one or more speakers can be set up, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. In addition, the speakers can also be placed in the front, rear, left or right of the car. side.

[0413] (1-3) See Picture 9 , Lights up the prompt light corresponding to the driving operation.

[0414] During the driving operation of the self-driving vehicle, the prompt light corresponding to the current driving operation is turned on, so that other agents can clarify the driving operation being performed by the self-driving vehicle. For example, the driving operation currently performed by an autonomous vehicle can be straight, turning, changing lanes, reversing, accelerating, braking, parking, etc. When performing a deceleration operation, the brake light corresponding to the deceleration operation is turned on, and when a parking operation is performed, The self-driving vehicle can light up the hazard warning flashlight (dual flashing light), and when the lane change operation is performed, the self-driving vehicle can light up the turn signal corresponding to the lane change operation.

[0415] (1-4) See Picture 9 , To perform the whistle operation according to the whistle rhythm corresponding to the target vehicle.

[0416] Self-driving vehicles are equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or electronic whistle. Autopilot vehicles can set the number of whistle honking times in each fixed period to determine the whistle rhythm. Different target vehicles correspond to different whistle whistle rhythms. The period can be one second or one minute, etc.

[0417] After the self-driving vehicle detects the target vehicle, it can classify the target vehicle type according to the characteristics of the target vehicle. The self-driving vehicle can establish the corresponding relationship between different types of target vehicles and the horn rhythm. When the self-driving vehicle recognizes the target vehicle, confirm the target vehicle type , Query the corresponding relationship to obtain the whistle rhythm corresponding to the target vehicle type, and perform the whistle operation according to the whistle rhythm corresponding to the target vehicle type, so that other agents can learn about the current location of the autonomous vehicle Target vehicle type.

[0418] (2) Output the prompt information corresponding to the driving operation performed by the autonomous vehicle through the output device.

[0419] (2-1) see Picture 9 , When the driving operation is a deceleration operation, through the output device, output the prompt information of the deceleration avoidance target vehicle.

[0420] If the autonomous vehicle and the target vehicle are traveling in the same direction, the autonomous vehicle is in front of the target vehicle, and the autonomous vehicle and the target vehicle are in different lanes, then the autonomous vehicle and the target vehicle will perform a deceleration operation to avoid the target vehicle when they meet. In addition, if the self-driving vehicle and the target vehicle are driving toward each other, the deceleration operation will be performed when the self-driving vehicle and the target vehicle meet.

[0421] In the process of performing the deceleration operation, the prompt information corresponding to the deceleration operation is output through at least one of the display screen, the speaker, and the prompt lamp.

[0422] For the display screen, when the autonomous vehicle performs a deceleration operation, the display screen displays the prompt message of decelerating and avoiding the target vehicle. The deceleration prompt information is used to prompt the autonomous vehicle to slow down. When other agents view the deceleration prompt of the autonomous vehicle Information, it can be determined that the current autonomous vehicle is decelerating.

[0423] In one possible implementation manner, the deceleration prompt information may include text information or picture information. For example, the text information may be "decelerating, avoid ambulance", and the picture information may be any picture that can reflect the deceleration operation performed by the autonomous vehicle.

[0424] For the speaker, when the self-driving vehicle performs a deceleration operation, the speaker will play the prompt message of decelerating and avoiding the target vehicle. The deceleration prompt information is a voice message, which is used to prompt the self-driving vehicle to slow down so that other agents can listen to the deceleration prompt information , Understand that the autonomous vehicle is currently decelerating.

[0425] Regarding the prompt light, during the deceleration driving operation of the self-driving vehicle, the brake light corresponding to the deceleration operation currently performed is turned on, so that other agents can know that the self-driving vehicle is decelerating.

[0426] (2-2) See Picture 9 , When the driving operation is an acceleration operation, the output device is used to output a prompt message requesting a lane change to avoid the target vehicle.

[0427] If the autonomous vehicle and the target vehicle are driving in the same direction, the autonomous vehicle is in front of the target vehicle, and the autonomous vehicle and the target vehicle are in the same lane, but there is no traffic area in the adjacent lane, the acceleration operation is performed until there is traffic in the adjacent lane When in the area, perform lane change operations.

[0428] In the process of performing the acceleration operation, at least one of the display screen, the speaker, and the warning light is used to output a warning message requesting a lane change to avoid the target vehicle.

[0429] For the display screen, when the autonomous vehicle performs an acceleration operation, the display screen displays the prompt information requesting to change lanes to avoid the target vehicle. When other agents view the prompt information of the autonomous vehicle, the current autonomous vehicle can be determined If the lane changing operation needs to be performed, the vehicles in the adjacent lanes can understand the intention and reason of the automatic driving vehicle to change lanes, so as to actively avoid the automatic driving vehicle, and facilitate the automatic driving vehicle to perform the lane changing operation.

[0430] In one possible implementation, the prompt information corresponding to the acceleration operation may include text information or picture information. For example, the text information may be "accelerating, need to change lanes as soon as possible to avoid ambulances", and the picture information may be anything that can reflect A picture of an operation performed by an autonomous vehicle.

[0431] For the speaker, when the autonomous vehicle performs an acceleration operation, the speaker will play a prompt message requesting to change lanes to avoid the target vehicle. The prompt message is voice information. Other agents can listen to the prompt information and understand that the autonomous vehicle needs to execute With the lane changing operation, the vehicles in the adjacent lanes can understand the intention and reason of the automatic driving vehicle to change lanes, so as to actively avoid the automatic driving vehicle and facilitate the automatic driving vehicle to perform the lane changing operation.

[0432] (2-3) See Picture 9 , When the driving operation is a lane change operation, the output device outputs a prompt message for changing lanes to avoid the target vehicle.

[0433] If the autonomous vehicle and the target vehicle are traveling in the same direction, the autonomous vehicle is in front of the target vehicle, the autonomous vehicle and the target vehicle are in the same lane, and there is a traffic area in the adjacent lane, the autonomous vehicle performs a lane change operation.

[0434] In the process of executing the lane changing operation, at least one of the display screen, the loudspeaker, and the reminder light is used to output the reminder information of changing lanes to avoid the target vehicle.

[0435] For the display screen, when the autonomous vehicle performs the lane change operation, the display screen displays the prompt information of changing lanes to avoid the target vehicle. When other agents view the prompt information of the autonomous vehicle, they can determine that the current autonomous vehicle is Change lanes.

[0436] In a possible implementation, the prompt information may include text information or picture information. For example, the text information may be "Change lanes, avoiding ambulances", and the picture information may be any information that can reflect the lane changing operation performed by the autonomous vehicle. image.

[0437] For the speaker, when the autonomous vehicle performs the lane change operation, the speaker will play the prompt message of changing lane to avoid the target vehicle. The lane change prompt information is voice information. Other agents can listen to the prompt information and learn about the current situation of the autonomous vehicle Change lanes.

[0438] For the warning lights, when the autonomous vehicle is performing the lane changing operation, turn on the turn signal corresponding to the lane changing driving operation, so that other agents can make it clear that the autonomous vehicle is changing lanes.

[0439] Such as Picture 9 As shown, by first judging whether there is a target vehicle of the preset avoidance type within the current range of the autonomous vehicle, if so, the position of the target vehicle is displayed on the display screen, and the position of the target vehicle is played through the speaker. Picture 9 The processing flow shown in sequence determines the driving direction and relative position of the autonomous vehicle and the target vehicle, whether they are in the same lane, whether the vehicle will meet, and the situation in the adjacent lane of the autonomous vehicle to determine which driving operation the autonomous vehicle performs. The driving vehicle is equipped with display screens, speakers, warning lights, and car whistle to prompt the driving operations performed by the autonomous vehicle.

[0440] It should be noted that when the self-driving vehicle itself is the target vehicle, the self-driving vehicle runs normally and does not need to avoid other target vehicles of the preset avoidance type within the current range, so there is no need to execute the prompt method provided in the embodiment of the present application. Or, if the autonomous vehicle itself is the target vehicle, but is not currently performing a task, it still has to avoid other target vehicles of the preset avoidance type within the current range, so the method provided in the embodiment of the present application can be used.

[0441] The method provided by the embodiment of the present application executes driving operations for avoiding the target vehicle by identifying the target vehicle belonging to the preset avoidance type within the current range. In the process of performing the driving operation, the output device of the automatic driving vehicle is used, Output the prompt information of the target vehicle so that other agents can learn about the existence of the target vehicle, actively avoid the target vehicle, and have a better understanding of the driving operation of the autonomous vehicle, and can perform corresponding operations according to the driving operation of the autonomous vehicle, as far as possible This avoids the conflict between the operation of other intelligent bodies and the driving operation of the autonomous vehicle, which can reduce the probability of traffic accidents and improve safety. Moreover, autonomous vehicles can eliminate misunderstandings, reduce risks, improve traffic safety, and reduce traffic accidents by actively interacting with other agents.

[0442] In addition, by matching the vehicle characteristics with the preset vehicle characteristics corresponding to the preset avoidance type, the target vehicle belonging to the preset avoidance type can be identified, which improves the recognition accuracy.

[0443] In addition, it can also be determined whether the vehicle is the target vehicle according to the appearance characteristics of the vehicle and the status of the reminder light or the appearance characteristics and the whistle state. It provides a way to identify the target vehicle. The identification channels are diversified. The use of diversified identification methods can also improve the accuracy of recognition. rate.

[0444] In addition, according to the driving direction of the autonomous vehicle and the target vehicle, the relative position, whether they are in the same lane, whether the vehicle will meet, and the situation of the adjacent lane of the autonomous vehicle to determine the final driving operation of the autonomous vehicle. It is clarified that when the target vehicle is recognized, how the self-driving vehicle can avoid the target vehicle so that the target vehicle can pass without obstruction.

[0445] In addition, the display screen, speakers, reminder lights, and car whistle are used to provide prompts, and the prompt channels are diversified, which can increase the probability of other agents receiving prompt information, and avoid the failure to output prompt information due to a failure of an output device. This in turn causes traffic accidents and improves the safety of autonomous driving.

[0446] In addition, the output device outputs the prompt information corresponding to the driving operation performed by the autonomous vehicle, so that other agents understand the driving operation of the autonomous vehicle better, and can perform corresponding operations according to the driving operation of the autonomous vehicle, avoiding as much as possible The conflict between the operation of other agents and the driving operation of the autonomous vehicle can reduce the probability of traffic accidents and improve safety.

[0447] The fourth interaction method: prompts the meeting state of the autonomous vehicle and the target vehicle.

[0448] Picture 10 Is a flow chart of a prompt method according to an exemplary embodiment, such as Picture 10 As shown, applied to an autonomous vehicle, the method includes:

[0449] 1001. The autonomous driving vehicle recognizes a target vehicle, and the target vehicle is a vehicle whose driving route and the driving route of the autonomous driving vehicle intersect.

[0450] There are many vehicles on the road. According to the driving direction, they are divided into vehicles driving in the same direction as the autonomous vehicle and vehicles driving opposite to the autonomous vehicle. According to the driving lane, they are divided into vehicles in the same lane as the autonomous vehicle and vehicles in the same lane as the autonomous vehicle. Vehicles in adjacent lanes and vehicles in non-adjacent lanes to autonomous vehicles. Vehicles in non-adjacent lanes to autonomous vehicles will not intersect with autonomous vehicles and therefore will not affect the driving of autonomous vehicles, while vehicles in the same lane as autonomous vehicles and vehicles in adjacent lanes to autonomous vehicles It is possible to intersect with autonomous vehicles. In order to drive safely, autonomous vehicles need to comprehensively consider the conditions of autonomous vehicles and meeting vehicles to determine which driving operation to perform.

[0451] Therefore, in order to achieve a safe meeting, the self-driving vehicle needs to identify the target vehicle, that is, the vehicle whose driving route and the driving route of the self-driving vehicle intersect. It is divided into the following situations:

[0452] (1-1) When performing the operation of changing from the first lane to the second lane, recognize the vehicle in the second lane as the target vehicle.

[0453] When an autonomous vehicle is driving in the first lane it is currently in, it may encounter a closed, road repair or abnormally blocked situation in front of the current first lane. The autonomous vehicle needs to merge into the adjacent lane, that is, from the current lane. The first lane is changed to the adjacent second lane to achieve normal driving. Before changing lanes, the autonomous vehicle needs to identify whether there are other vehicles in the second lane and use the vehicle in the second lane as the target vehicle.

[0454] (1-2) Identify the vehicle traveling from other lanes to the first lane where it is currently located as the target vehicle. Or, identify a vehicle in the lane adjacent to the first lane where the vehicle is currently in the first lane, and use it as the target vehicle.

[0455] When an autonomous vehicle is currently driving in the first lane, it may encounter a situation where other vehicles in the adjacent lane merge into the first lane and prepare to drive in front of the autonomous vehicle. When other vehicles merge, it may affect the automatic The normal driving of the driving vehicle, or the situation in which other vehicles in the adjacent lanes are pointing to the first lane, means that the vehicle is driving toward the first lane and may merge into the first lane.

[0456] In order to achieve safe driving, autonomous vehicles need to recognize whether there are other vehicles in the adjacent lanes ready to merge or are in the process of merging, and use such vehicles as the target vehicle.

[0457] (1-3) Identify the current vehicle in the first lane that is located in front of the autonomous vehicle and whose driving speed is lower than that of the autonomous vehicle, as the target vehicle.

[0458] When an autonomous vehicle is currently driving in the first lane, it may encounter a situation where the driving speed of the front vehicle in the same lane is lower than the driving speed of the autonomous vehicle. At this time, the autonomous vehicle will perform an operation to overtake the preceding vehicle. In order to ensure safe driving during the overtaking process, the autonomous vehicle needs to identify the vehicle that is in front of the autonomous vehicle and whose driving speed is lower than that of the autonomous vehicle as the target vehicle.

[0459] (1-4) Identify the current vehicle in the first lane, which is located behind the autonomous vehicle and whose driving speed is greater than that of the autonomous vehicle, as the target vehicle.

[0460] When an autonomous vehicle is currently driving in the first lane, it may encounter a situation where the driving speed of the rear vehicle in the same lane is greater than the driving speed of the autonomous vehicle. At this time, the rear vehicle may perform driving overtaking the autonomous vehicle Operation, in order to drive safely, the autonomous vehicle needs to take the initiative to avoid conflicts with the driving operation of the rear vehicle. In order to avoid in time, the autonomous vehicle needs to recognize that the current first lane is behind the autonomous vehicle And the vehicle whose driving speed is greater than the driving speed of the autonomous vehicle is regarded as the target vehicle.

[0461] 1002. According to the location of the autonomous vehicle and the location of the target vehicle, the autonomous vehicle performs a driving operation.

[0462] After the autonomous vehicle determines that there is a driving route intersection with the target vehicle, it needs to decide which driving operation to perform according to the location of the autonomous vehicle and the location of the target vehicle to achieve safe autonomous driving.

[0463] Optionally, the self-driving vehicle can also decide which driving operation to perform according to the position of the self-driving vehicle and the location of the target vehicle, the speed of the self-driving vehicle and the speed of the target vehicle, and the actual conditions of the road to achieve safe automatic driving. .

[0464] Optionally, for the case of the above step (1-1), step 1002 may include the following steps:

[0465] (2-1) Perform a waiting operation at the junction of the first lane and the second lane;

[0466] The automatic driving vehicle merges into the adjacent lane, that is, when changing from the current first lane to the adjacent second lane, it is necessary to determine the merging time according to the position of the autonomous vehicle and the target vehicle. Under vehicle conditions, the autonomous vehicle performs a waiting operation at the junction of the first lane and the second lane.

[0467] In addition, not only the location of the autonomous vehicle and the location of the target vehicle, but also the speed of the autonomous vehicle and the target vehicle can be considered when determining the timing of merging.

[0468] In a possible implementation, when there are other vehicles that are close to the autonomous vehicle and have a faster speed in the second lane adjacent to the first lane where the autonomous vehicle is located, the autonomous vehicle needs to be in the first lane. The waiting operation is performed at the intersection of the lane and the second lane.

[0469] (2-2) When the position of the self-driving vehicle and the position of the target vehicle meet the meeting conditions, the operation of driving from the first lane to the second lane is performed.

[0470] When the autonomous vehicle determines that the meeting conditions are met, that is, when there is no target vehicle that is close to the autonomous vehicle and has a faster speed in the second lane, the autonomous vehicle executes the operation from the first lane to the second lane.

[0471] In view of the above step (1-2), step 1002 may include the following steps:

[0472] (2-3) Perform deceleration operation, lane change operation or maintain current driving operation according to the position of the autonomous vehicle and the position of the target vehicle.

[0473] The target vehicle in the adjacent lane of the autonomous vehicle merges into the first lane and is ready to drive to the front of the autonomous vehicle. The autonomous vehicle needs to determine the driving operation that the autonomous vehicle needs to perform based on the location of the autonomous vehicle and the location of the target vehicle.

[0474] In one possible implementation, the autonomous vehicle determines that the autonomous vehicle needs to stay in the current lane according to the location of the autonomous vehicle and the location of the target vehicle, but needs to slow down and avoid the target vehicle that is about to merge. Perform deceleration operations to avoid.

[0475] For example, the self-driving vehicle determines that the target vehicle that is about to merge in the adjacent lane is close to the self-driving vehicle and is at a faster speed. For safety reasons, the self-driving vehicle performs a deceleration operation to avoid the target vehicle.

[0476] In one possible implementation, the autonomous vehicle determines the autonomous vehicle based on the location of the autonomous vehicle and the location of the target vehicle, the speed of the autonomous vehicle and the target vehicle, and whether the adjacent lane on the other side meets the conditions for changing lanes. When it is necessary to change lanes to avoid the target vehicle that is about to merge, the autonomous vehicle performs a lane change operation to avoid.

[0477] For example, the self-driving vehicle determines that the target vehicle that is ready to merge in the adjacent lanes is relatively close to the self-driving vehicle, and the speed is faster, and the other side of the adjacent lane of the self-driving vehicle meets the conditions for changing lanes. For safety, the self-driving vehicle Perform lane change operations to avoid the target vehicle. Changing lanes for avoidance can also prevent the sudden deceleration operation from affecting the normal driving of the rear vehicles in the first lane, and avoid rear-end collisions caused by the sudden deceleration of the autonomous vehicle before the rear vehicles have time to respond to the sudden deceleration of the autonomous vehicle, which can improve safety.

[0478] In one possible implementation, the autonomous vehicle determines that the autonomous vehicle does not need to avoid avoidance according to the location of the autonomous vehicle and the location of the target vehicle and the speed of the autonomous vehicle and the target vehicle. The autonomous vehicle maintains the current driving operation , Do not avoid the target vehicle.

[0479] For example, when an autonomous vehicle determines that the target vehicle that is ready to merge in an adjacent lane is far away from the autonomous vehicle, and the autonomous vehicle will not affect the merging of the target vehicle, the autonomous vehicle maintains the current driving operation and does not need to The target vehicle evades.

[0480] In view of the above step (1-3), step 1002 may include the following steps:

[0481] (2-4) Perform operations to overtake the target vehicle.

[0482] In the first lane where the self-driving vehicle is currently located, when there is a target vehicle in front of the self-driving vehicle whose driving speed is lower than the driving speed of the self-driving vehicle, the self-driving vehicle performs a driving operation to overtake the target vehicle.

[0483] Among them, the execution of the operation of overtaking the target vehicle includes: the autonomous driving vehicle drives from the first lane to the adjacent lane, and performs an acceleration operation to overtake the target vehicle. When the autonomous driving vehicle is in front of the target vehicle, then from the adjacent lane Drive into the first lane and drive to the front of the target vehicle.

[0484] (2-5) After the execution of overtaking the target vehicle is completed, continue to execute the driving operation in the first lane.

[0485] In view of the above steps (1-4), step 1002 may include the following steps:

[0486] (2-6) Perform operations to avoid the target vehicle.

[0487] In the first lane where the autonomous vehicle is currently located, if there is a target vehicle behind the autonomous vehicle with a driving speed greater than that of the autonomous vehicle, if the rear vehicle performs an overtaking driving operation, the autonomous vehicle performs an operation to avoid the target vehicle.

[0488] (2-7) After the target vehicle passes the autonomous vehicle, continue to perform the driving operation in the first lane.

[0489] When the target vehicle performs an operation to overtake the self-driving vehicle, the target vehicle will drive from the first lane to the adjacent lane and perform an acceleration operation. At this time, the self-driving vehicle can perform the deceleration operation or can drive normally without performing the deceleration operation. After that, when the target vehicle is in front of the autonomous vehicle, it drives from the adjacent lane to the first lane. At this time, the autonomous vehicle can perform a deceleration operation to avoid the target vehicle until the target vehicle merges into the first lane. , The self-driving vehicle can restore the original driving speed and drive safely behind the target vehicle.

[0490] 1003. During the driving operation of the autonomous vehicle, the output device of the self-driving vehicle outputs prompt information. The prompt information is used to prompt the meeting state of the self-driving vehicle and the target vehicle. The output devices include a display screen, a speaker, and a vehicle. At least one of a flute or a reminder light.

[0491] The self-driving vehicle is equipped with an output device, and the output device includes at least one of a display screen, a speaker, a car whistle, or a warning light. Wherein, the number of display screens may be one or more, and the facing directions may include front, rear, left, right, and top, so as to realize the function of displaying information in the multiple directions. And the display screen can include multiple types of display screens such as subtitle screens and video screens. There can be one or more speakers, which can be installed on the roof or side of the car. The car whistle can include a mechanical whistle or an electronic whistle. The warning lights include turn signals, fog lights, and position lights.

[0492] Wherein, the meeting state may include the distance between the self-driving vehicle and the target vehicle, the driving operation currently performed by the self-driving vehicle, whether the self-driving vehicle is currently avoiding, and so on.

[0493] In view of the above step (2-1), step 1003 may include the following steps:

[0494] (3-1) In the process of performing the waiting operation, output the first prompt information through the output device. The first prompt information is used to prompt that the autonomous driving vehicle is waiting to merge into the second lane, and may include at least one of the following.

[0495] (a) See Picture 11 For the display screen, when the automatic driving vehicle performs the waiting operation, the first prompt information is displayed through the display screen. When other agents view the first prompt information of the automatic driving vehicle, it can be determined that the automatic driving vehicle is waiting for import The second lane to avoid the autonomous vehicle.

[0496] In one possible implementation, the first prompt information corresponding to the waiting operation may include text information or picture information. For example, the text information may be "Waiting to be imported", and the picture information may be any information that can reflect the waiting operation of an autonomous vehicle. Picture of the operation.

[0497] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information displayed by the autonomous vehicle.

[0498] (b) See Picture 11 , For the speaker, when the autonomous vehicle performs the waiting operation, the first prompt information is played through the speaker. The first prompt information is voice information. Other agents can listen to the first prompt information and learn that the autonomous vehicle is currently waiting It merges into the lane to avoid the autonomous vehicle.

[0499] In one possible implementation, one or more speakers can be set up, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. In addition, the speakers can also be placed in the front, rear, left or right of the car. side.

[0500] (c) See Picture 11 For the warning lights, during the waiting operation of the autonomous vehicle, turn on the turn signal corresponding to the waiting operation, so that other agents can know that the autonomous vehicle is waiting to merge into the lane, so as to avoid the autonomous vehicle.

[0501] (d) See Picture 11 For the reminder lights, during the waiting operation of the autonomous vehicle, the current environmental information can be detected, and the reminder lights corresponding to the current environmental information can be lit, so that other agents can clarify the location of the self-driving vehicle. The vehicle evaded.

[0502] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0503] (e) See Picture 11 For car horns, during the waiting operation of the automatic driving vehicle, the horn operation can be performed according to the horn rhythm corresponding to the waiting operation.

[0504] Among them, the self-driving vehicle is equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or the electronic whistle. The self-driving vehicle can set the number of whistle honking in each fixed period to determine the whistle rhythm. The period can be one second or one minute, etc.

[0505] The autonomous vehicle can establish the corresponding relationship between the waiting operation and the whistle rhythm. When the automatic driving vehicle performs the waiting operation, the corresponding relationship is inquired, and the whistle rhythm corresponding to the waiting operation is obtained. The whistle rhythm performs the whistle operation, so that other agents can understand that the autonomous vehicle is currently waiting to merge into the lane, so as to avoid the autonomous vehicle.

[0506] Optionally, when the self-driving vehicle starts to perform the waiting operation, the whistle operation is not performed temporarily, and the waiting time is counted. When the waiting time exceeds the preset time, it means that the waiting time is too long, and the whistle operation is performed at this time.

[0507] Self-driving vehicles can automatically perform the whistle operation, or a whistle button is provided on the steering wheel, and the driver will also perform the whistle operation when pressed.

[0508] For the above step (2-2), step 1003 may include the following steps:

[0509] (3-2) During the execution of the operation from the first lane to the second lane, the second prompt information is output through the output device. The second prompt information is used to prompt that the autonomous vehicle is merging into the second lane, which may include At least one of the following.

[0510] (a) See Picture 11 For the display screen, when the autonomous vehicle is driving from the first lane to the second lane, the second prompt information is displayed on the display screen. When other agents view the second prompt information of the autonomous vehicle, it can It is determined that the current autonomous vehicle is driving from the first lane to the second lane, so as to avoid the autonomous vehicle. In addition, the second prompt information can also prompt the target vehicle to maintain a distance between the autonomous vehicle and the target vehicle.

[0511] In one possible implementation, the second prompt information corresponding to the operation from the first lane to the second lane may include text information or picture information. For example, the text information may be "merging into the first lane", and the picture information may It is any picture that can reflect the operation of the autonomous vehicle from the first lane to the second lane.

[0512] (b) See Picture 11 For the speaker, when the autonomous vehicle performs the operation from the first lane to the second lane, the second prompt information is played through the speaker. The second prompt information is voice information, and other agents can listen to the second prompt information. Know that the autonomous vehicle is currently merging into the first lane, so as to avoid the autonomous vehicle.

[0513] (c) See Picture 11 For the warning lights, when the autonomous vehicle is operating from the first lane to the second lane, turn on the turn signal corresponding to the operation from the first lane to the second lane, so that other agents can clearly drive automatically The vehicle is merging into the first lane to avoid the autonomous vehicle.

[0514] (d) See Picture 11 For the warning lights, the autonomous vehicle can detect the current environment information during the operation from the first lane to the second lane, and light up the reminder lights corresponding to the current environment information, so that other agents can clearly drive automatically The location of the vehicle to avoid the autonomous vehicle.

[0515] (e) See Picture 11 For car horns, during the process of driving from the first lane to the second lane of the autonomous vehicle, the horn operation can be performed according to the horn rhythm corresponding to the lane change operation.

[0516] The autonomous vehicle can establish the corresponding relationship between the lane change operation and the horn rhythm. When the autonomous vehicle executes the operation from the first lane to the second lane, the corresponding relationship is inquired and the horn rhythm corresponding to the lane change operation is obtained. , Perform the whistle operation according to the whistle rhythm corresponding to the lane change operation, so that other agents can understand that the autonomous vehicle is currently changing lanes and merge into the second lane.

[0517] Regarding the above step (2-3), step 1003 may include the following steps:

[0518] (3-3) In the process of performing the deceleration operation, outputting the third prompt information through the output device, the third prompt information is used to prompt the autonomous driving vehicle to avoid the target vehicle, and may include at least one of the following.

[0519] (a) See Picture 11 For the display screen, when the autopilot vehicle performs the deceleration operation, the third prompt information is displayed through the display screen. When other agents view the third prompt information of the autopilot vehicle, it can be determined that the current autopilot vehicle is decelerating and avoiding Target vehicle.

[0520] In one possible implementation, the third prompt information corresponding to the deceleration operation may include text information or picture information. For example, the text information may be “decelerating and avoiding”, and the picture information may be any information that can reflect the deceleration operation performed by the autonomous vehicle. picture of.

[0521] Optionally, the first display screen displays the prompt information that the target vehicle is decelerating and avoiding the target vehicle, and the second display screen displays the image of the target vehicle. Among them, the first display screen and the second display screen are different display screens of the autonomous driving vehicle, and may be located on different sides of the autonomous driving vehicle.

[0522] (b) See Picture 11 For the speaker, when the self-driving vehicle performs a deceleration operation, the third prompt information is played through the speaker. The third prompt information is voice information. Other agents can listen to the third prompt information and learn that the self-driving vehicle is currently decelerating Avoid target vehicles.

[0523] (c) See Picture 11 , For the reminder light, during the deceleration operation of the autonomous vehicle, the brake light corresponding to the deceleration operation is turned on, so that other agents can know that the autonomous vehicle is decelerating to avoid the target vehicle.

[0524] (d) See Picture 11 For the reminder lights, during the deceleration operation of the self-driving vehicle, the current environmental information can be detected, and the reminder light corresponding to the current environmental information can be lit, so that other agents can clarify the location of the self-driving vehicle.

[0525] (e) See Picture 11 For car horns, during the deceleration operation of the self-driving vehicle, the whistle operation can be performed according to the whistle rhythm corresponding to the deceleration operation.

[0526] Automatically driving vehicles can establish the corresponding relationship between the deceleration operation and the whistle rhythm. When the automatic driving vehicle performs the deceleration operation, query the corresponding relationship to obtain the whistle rhythm corresponding to the deceleration operation, and follow the whistle rhythm corresponding to the deceleration operation. The whistle rhythm performs the whistle operation, so that other agents can understand that the autonomous vehicle is currently decelerating.

[0527] Regarding the above step (2-3), step 1003 may include the following steps:

[0528] (3-4) In the process of executing the lane changing operation, the fourth prompt information is output through the output device. The fourth prompt information is used to prompt that the autonomous vehicle is changing lanes, and may include at least one of the following.

[0529] (a) See Picture 11 For the display screen, when the autonomous vehicle performs the lane change operation, the fourth prompt information is displayed on the display screen. When other agents view the fourth prompt information of the autonomous vehicle, it can be determined that the current autonomous vehicle is changing Lane.

[0530] In a possible implementation manner, the fourth prompt information corresponding to the lane changing operation may include text information or picture information. For example, the text information may be "Always changing lanes to avoid", and the picture information may be any automatic driving vehicle execution. Picture of lane change operation.

[0531] (b) See Picture 11 For the speaker, when the autonomous vehicle performs the lane change operation, the fourth prompt information is played through the speaker. The fourth prompt information is voice information. Other agents can listen to the fourth prompt information and learn that the autonomous vehicle is currently Change lanes.

[0532] (c) See Picture 11 For the warning lights, when the autonomous vehicle is performing the lane changing operation, turn on the turn signal corresponding to the lane changing operation, so that other intelligent agents can make it clear that the autonomous vehicle is changing lanes.

[0533] (d) See Picture 11 For the warning lights, during the process of changing lanes, the autonomous vehicle can detect the current environment information and light up the warning lights corresponding to the current environment information, so that other agents can clarify the location of the autonomous vehicle.

[0534] (e) See Picture 11 For car horns, during the process of lane change operations performed by the autonomous vehicle, the horn operation can be performed in accordance with the whistle rhythm corresponding to the lane change operations.

[0535] The autonomous vehicle can establish the corresponding relationship between the lane change operation and the whistle rhythm. When the autonomous vehicle performs the lane change operation, the corresponding relationship is inquired to obtain the whistle rhythm corresponding to the lane change operation. Operate the corresponding whistle rhythm to perform the whistle operation, so that other agents can understand that the autonomous vehicle is currently changing lanes.

[0536] Regarding the above step (2-3), step 1003 may include the following steps:

[0537] (3-5) In the process of maintaining the current driving operation, the fifth prompt information is output through the output device. The fifth prompt information is used to prompt that the autonomous vehicle has not made an avoidance, and may include at least one of the following.

[0538] (a) See Picture 11 For the display screen, when the autonomous vehicle maintains the current driving operation, the fifth prompt information is displayed through the display screen. When other agents view the fifth prompt information of the autonomous vehicle, it can be determined that the current autonomous vehicle is normal Driving without avoiding.

[0539] In a possible implementation manner, the fifth prompt information may include text information or picture information. For example, the text information may be "don't evade", and the picture information may be any picture that can reflect the normal driving of the autonomous vehicle.

[0540] Optionally, the prompt information that the current driving is being maintained is displayed on the first display screen, and the picture of the target vehicle is displayed on the second display screen. Among them, the first display screen and the second display screen are different display screens of the autonomous driving vehicle, and may be located on different sides of the autonomous driving vehicle.

[0541] (b) See Picture 11 For the speaker, when the autonomous vehicle maintains the current driving operation, the fifth prompt message is played through the speaker. The fifth prompt information is voice information. Other agents can listen to the fifth prompt information and learn that the autonomous vehicle is currently running. Drive normally without avoiding.

[0542] (c) See Picture 11 For the reminder light, while the autonomous vehicle maintains the current driving operation, the reminder light corresponding to the current driving operation is turned on, so that other agents can make it clear that the autonomous vehicle is driving normally and has not made an avoidance.

[0543] (d) See Picture 11 For the reminder lights, the autonomous vehicle can detect the current environment information while maintaining the current driving operation, and light up the reminder lights corresponding to the current environment information, so that other agents can identify the location of the autonomous vehicle.

[0544] (e) See Picture 11 For the car whistle, while the autonomous vehicle maintains the current driving operation, the whistle operation can be performed according to the whistle rhythm corresponding to the current driving operation.

[0545] The automatic driving vehicle can establish the corresponding relationship between the current driving operation and the whistling rhythm. When the automatic driving vehicle maintains the current driving operation, query the corresponding relationship to obtain the whistle rhythm corresponding to the current driving operation. , Perform the whistle operation according to the whistle rhythm corresponding to the keeping current driving operation, so that other agents can understand that the autonomous driving vehicle is currently keeping the current driving and has not made an avoidance.

[0546] In view of the above step (2-4), step 1003 may include the following steps:

[0547] (3-6) In the process of performing the operation of overtaking the target vehicle, the sixth prompt information is output through the output device. The sixth prompt information is used to prompt that the autonomous vehicle is overtaking, and may include at least one of the following.

[0548] (a) See Picture 11 For the display screen, when the self-driving vehicle performs the overtaking operation, the sixth prompt information is displayed through the display screen. When other agents view the sixth prompt information of the self-driving vehicle, it can be determined that the current self-driving vehicle is overtaking .

[0549] In one possible implementation, the sixth prompt information corresponding to the overtaking operation may include text information or picture information. For example, the text information may be "overtaking", and the picture information may be any operation that can reflect the overtaking performed by the autonomous vehicle. picture of.

[0550] (b) See Picture 11 For the speaker, when the self-driving vehicle performs an overtaking operation, the sixth prompt information is played through the speaker. The sixth prompt information is voice information. Other agents can listen to the sixth prompt information and learn that the self-driving vehicle is currently overtake.

[0551] (c) See Picture 11 For the warning lights, the lane change operation is involved during the overtaking operation of the self-driving vehicle, and the turn signal corresponding to the lane change operation is turned on, so that other agents can make it clear that the self-driving vehicle is overtaking.

[0552] (d) See Picture 11 For the reminder lights, during the overtaking operation of the self-driving vehicle, the current environment information can be detected, and the reminder light corresponding to the current environment information can be lit, so that other agents can determine the location of the self-driving vehicle.

[0553] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0554] (e) See Picture 11 For the reminder lights, during the overtaking operation of the self-driving vehicle, the high beam and the low beam can be changed at night to remind the target vehicle so that other agents can determine the location of the self-driving vehicle.

[0555] (f) For the car whistle, during the process of the overtaking operation of the self-driving vehicle, the whistle operation can be performed according to the whistle rhythm corresponding to the overtaking operation.

[0556] The self-driving vehicle can establish the corresponding relationship between the overtaking operation and the whistle rhythm. When the self-driving vehicle performs the overtaking operation, the corresponding relationship is inquired to obtain the whistle rhythm corresponding to the overtaking operation, according to the corresponding overtaking operation The honking rhythm executes the honking operation, so that other agents can understand that the autonomous vehicle is currently overtaking.

[0557] The self-driving vehicle can establish the corresponding relationship between the distance and the whistle rhythm. When the self-driving vehicle performs the overtaking operation, the distance between the self-driving vehicle and the target vehicle is obtained, the corresponding relationship is queried, and the corresponding distance is obtained. The whistle rhythm, the whistle operation is performed according to the whistle rhythm corresponding to the distance, so that other agents can understand the distance between the autonomous vehicle and the target vehicle.

[0558] In view of the above step (2-5), step 1003 may include steps:

[0559] (3-7) After the operation of overtaking the target vehicle is completed, the seventh prompt information is output through the output device. The seventh prompt information is used to prompt the automatic driving vehicle to drive normally, and may include at least one of the following.

[0560] (a) See Picture 11 For the display screen, when the automatic driving vehicle is driving normally, the seventh prompt message is displayed through the display screen. When other agents view the seventh prompt information of the automatic driving vehicle, it can be determined that the current automatic driving vehicle is driving normally.

[0561] In one possible implementation, the seventh prompt information corresponding to the overtaking operation may include text information or picture information. For example, the text information may be "normal driving", and the picture information may be any picture that can reflect the normal driving of the autonomous vehicle. .

[0562] (b) See Picture 11 For the speaker, when the autonomous vehicle is driving normally, the seventh prompt message is played through the speaker. The seventh prompt message is voice information. Other agents can listen to the seventh prompt message and learn that the autonomous vehicle is currently driving normally.

[0563] (c) See Picture 11 , For the warning lights, during the normal driving of the autonomous vehicle, turn on the turn signal corresponding to the normal driving operation, so that other agents can make it clear that the autonomous vehicle is running normally.

[0564] (d) See Picture 11 For the reminder lights, during the normal driving of the autonomous vehicle, the current environmental information can be detected, and the reminder light corresponding to the current environmental information can be lit, so that other agents can identify the location of the autonomous vehicle.

[0565] (e) See Picture 11 , For the car horn, during the normal driving of the autonomous vehicle, the whistle operation can be performed according to the whistle rhythm corresponding to the normal driving operation.

[0566] Autonomous vehicles can establish the corresponding relationship between normal driving operations and the honking rhythm. When the autonomous vehicle is running normally, query the corresponding relationship to obtain the horn rhythm corresponding to the normal driving operation, and follow the normal driving operation Perform the whistle operation at the rhythm of the whistle, so that other agents can understand that the autonomous vehicle is currently driving normally.

[0567] Regarding the above step (2-6), step 1003 may include the following steps:

[0568] (3-8) In the process of performing the operation of avoiding the target vehicle, the eighth prompt information is output through the output device. The eighth prompt information is used to prompt that the autonomous driving vehicle is avoiding, or the eighth prompt information is used to prompt the target vehicle and the automatic Driving a vehicle to maintain a distance between vehicles may include at least one of the following.

[0569] (a) See Picture 11 For the display screen, when the automatic driving vehicle performs the avoidance operation, the eighth prompt message is displayed through the display screen. When other agents view the eighth prompt message of the automatic driving vehicle, it can be determined that the current automatic driving vehicle is avoiding . Or the eighth prompt information may be to prompt the target vehicle to maintain a distance between the autonomous vehicle and the target vehicle. When other agents view the eighth prompt information of the autonomous vehicle, pay attention to maintaining the distance between the autonomous vehicle and the autonomous vehicle.

[0570] In a possible implementation manner, the eighth prompt information corresponding to the avoidance operation may include text information or picture information. For example, the text information may be "avoiding" or "please keep the distance between vehicles", and the picture information may be any that can reflect A picture of an autonomous vehicle performing an avoidance operation or prompting to maintain a distance between vehicles.

[0571] (b) See Picture 11 For the speaker, when the autonomous vehicle performs an avoidance operation, the eighth prompt message is played through the speaker. The eighth prompt message is voice information. Other agents can listen to the eighth prompt message and learn that the autonomous vehicle is currently Avoid or make it clear that the current vehicle distance should be maintained.

[0572] (c) See Picture 11 For the warning lights, during the avoidance operation of the autonomous vehicle, the warning lights corresponding to the avoidance operation are lit, so that other agents can make it clear that the autonomous vehicle is avoiding or that the distance between the vehicles should be maintained.

[0573] (d) See Picture 11 For the reminder lights, during the process of avoiding the operation of the autonomous vehicle, the current environment information can be detected, and the reminder light corresponding to the current environment information can be lit, so that other agents can determine the location of the autonomous vehicle.

[0574] (e) See Picture 11 For car horns, during the evasive operation of the self-driving vehicle, the whistle operation can be performed according to the whistle rhythm corresponding to the evasive operation.

[0575] The automatic driving vehicle can establish the corresponding relationship between the avoidance operation and the whistle rhythm. When the automatic driving vehicle performs the avoidance operation, the corresponding relationship is inquired, and the whistle rhythm corresponding to the avoidance operation is obtained, and according to the corresponding avoidance operation The honking rhythm performs the honking operation, so that other agents can understand that the autonomous vehicle is currently avoiding.

[0576] In the process of the target vehicle overtaking the self-driving vehicle, if the distance between the target vehicle and the self-driving vehicle is less than the preset distance, the ninth prompt message is output through the output device. The ninth prompt message is used to prompt that the vehicle is too close. Include at least one of the following.

[0577] (a) See Picture 11 For the display screen, when the target vehicle surpasses the autonomous vehicle, the autonomous vehicle displays the ninth prompt message through the display screen. When other agents view the ninth prompt message of the autonomous vehicle, they can determine the current and The self-driving vehicle is too close.

[0578] In one possible implementation, the ninth prompt information corresponding to the overtaking operation may include text information or picture information. For example, the text information may be "the distance between vehicles is too close", and the picture information may be any information that can reflect the distance between vehicles too close. image.

[0579] (b) See Picture 11 For the speaker, when the target vehicle surpasses the autonomous vehicle, the autonomous vehicle plays the ninth prompt message through the speaker. The ninth prompt message is voice information. Other agents can listen to the ninth prompt message and learn about the current The distance to the autonomous vehicle is too close.

[0580] (c) See Picture 11 For the reminder light, when the target vehicle surpasses the autonomous vehicle, the autonomous vehicle lights up the reminder light corresponding to the distance between the vehicles, so that other agents can know that the distance between the vehicle and the autonomous vehicle is too close.

[0581] (d) See Picture 11 For the reminder lights, when the target vehicle surpasses the autonomous vehicle, the autonomous vehicle can detect the current environment information and light up the reminder light corresponding to the current environment information, so that other agents can determine the location of the autonomous vehicle.

[0582] (e) See Picture 11 For the car whistle, when the target vehicle surpasses the self-driving vehicle, the self-driving vehicle can perform the whistle operation according to the whistle rhythm.

[0583] The autonomous vehicle can establish the corresponding relationship between the distance and the whistle rhythm. When the target vehicle surpasses the autonomous vehicle, the autonomous vehicle obtains the distance between the autonomous vehicle and the target vehicle, and queries the corresponding relationship to obtain the distance The corresponding whistle rhythm, the whistle operation is performed according to the whistle rhythm corresponding to the distance, so that other agents can understand the distance between the autonomous vehicle and the target vehicle.

[0584] Or, when the target vehicle is overtaking the self-driving vehicle, the self-driving vehicle obtains the distance between the self-driving vehicle and the target vehicle, and when the distance is less than the preset distance, the whistle operation is performed according to the whistle rhythm. And when the distance is not less than the preset distance, no longer perform whistle operation.

[0585] After the target vehicle overtakes, the self-driving vehicle outputs the prompt information corresponding to normal driving through the output device.

[0586] Such as Picture 11 As shown, the situations in which the road is driving in the same direction and the driving route intersects on the road are divided into the following four types: the autonomous vehicle merges into the adjacent lane, the adjacent lane vehicle merges into the autonomous vehicle lane, and the autonomous vehicle overtakes , Other vehicles overtaking, automatic driving vehicles merge into adjacent lanes are divided into two situations: waiting process and merge process, adjacent lane vehicles merge into autonomous vehicle lanes are divided into autonomous vehicles slowing down and avoiding, changing lanes and avoiding There are three situations of avoidance. Autopilot overtaking is divided into two situations before overtaking and after overtaking. Other vehicles overtaking are divided into two situations before overtaking and after overtaking, and the prompt methods in various situations are given respectively.

[0587] The method provided by the embodiments of the present application recognizes the target vehicle whose driving route and the driving route of the autonomous vehicle intersect, and executes driving operations according to the position of the autonomous vehicle and the position of the target vehicle, so that the autonomous vehicle can be based on the meeting vehicle’s Perform corresponding driving operations on the driving route to improve safety. In the process of performing driving operations, the output device of the self-driving vehicle outputs prompt information. The prompt information is used to prompt the meeting state of the self-driving vehicle and the target vehicle, so that the meeting vehicle and other intelligent agents can accurately and fully understand the automatic driving The driving operation performed by the vehicle avoids as much as possible the conflict between the operation of the meeting vehicle and other intelligent bodies and the driving operation of the self-driving vehicle, which can reduce the probability of traffic accidents and improve safety. In addition, autonomous vehicles can eliminate misunderstandings, reduce risks, improve traffic safety, and reduce traffic accidents by actively interacting with meeting vehicles and other intelligent bodies.

[0588] In addition, according to the driving speed of the autonomous vehicle and other vehicles and the lane in which it is located, the situation where the road is driving in the same direction and the driving route intersects on the road is subdivided into four types, which clarifies that the autonomous vehicle is the same as other vehicles. Convergence will occur when driving, which is convenient for subsequent autonomous vehicles to perform corresponding driving operations according to various situations.

[0589] In addition, through the output device, the driving operation of other vehicles is prompted, and other agents can clearly understand the driving operation being performed by the self-driving vehicle, and can perform corresponding operations according to the driving operation of the self-driving vehicle. Reduce the probability of traffic accidents and improve the safety of autonomous vehicles.

[0590] Picture 12 Is a flow chart of a prompt method according to an exemplary embodiment, such as Picture 12 As shown, applied to an autonomous vehicle, the method includes:

[0591] 1201. The self-driving vehicle recognizes a vehicle on the current road in which the driving direction of the self-driving vehicle is opposite, and uses it as a target vehicle.

[0592] There are many vehicles on the road. Vehicles that are on the same road as the self-driving vehicle and in the opposite direction to the self-driving vehicle will meet the self-driving vehicle, which will affect the driving of the self-driving vehicle. Therefore, in order to meet the vehicle safely, realize safe autonomy During driving, an autonomous vehicle needs to identify the target vehicle, that is, the vehicle that is currently on the road in the opposite direction to the autonomous vehicle.

[0593] 1202. The autonomous vehicle determines the meeting position of the autonomous vehicle and the target vehicle according to the location of the autonomous vehicle and the location of the target vehicle.

[0594] When there are no obstacles in front of the autonomous vehicle in the lane where the autonomous vehicle is located, the autonomous vehicle can determine the meeting vehicle based on the location of the autonomous vehicle and the location of the target vehicle, as well as the speed of the autonomous vehicle and the target vehicle position.

[0595] When there is an obstacle in front of the self-driving vehicle in the lane where the self-driving vehicle is located, the self-driving vehicle needs to determine the position of the obstacle in front of the self-driving vehicle, and determine the position based on the position of the obstacle, the position of the self-driving vehicle and the target vehicle The meeting position, the meeting position can be located behind the obstacle, that is, the autonomous vehicle first completes the meeting with the target vehicle, and then drives through the obstacle. The meeting position can also be located in front of the obstacle, that is, the autonomous driving vehicle first passes through the obstacle, and then meets with other vehicles. Specifically divided into the following two situations:

[0596] (1-1) The meeting position is behind the obstacle.

[0597] In a possible implementation manner, the autonomous driving vehicle determines that other vehicles driving in opposite directions are close to the obstacle and have a faster speed, and the autonomous driving vehicle determines that the meeting position is behind the obstacle.

[0598] (1-2) The meeting position is in front of the obstacle.

[0599] In one possible implementation, the autonomous vehicle determines that other vehicles driving in the opposite direction are farther away from the obstacle and slower, and the autonomous vehicle is closer to the obstacle, then the autonomous vehicle determines that the meeting position is in front of the obstacle .

[0600] When the road where the self-driving vehicle is located is blocked, such as a curve or winding road, the self-driving vehicle cannot determine whether there is a target vehicle driving in the front and whether there is an obstacle ahead, the self-driving vehicle needs to perform a deceleration operation to Realize safe driving, and output the prompt information corresponding to the deceleration operation through the output device, for example, the whistle operation can be performed according to the whistle rhythm corresponding to the deceleration operation.

[0601] Autonomous vehicles need to comprehensively use multiple methods to identify vehicles on the road in the sheltered area of ​​the autonomous vehicle that are in the opposite direction to the autonomous vehicle, as the target vehicle, the specific process includes at least one of the following:

[0602] (1) Monitor the whistle sound emitted by the vehicle, and set the vehicle that emits the whistle sound as the target vehicle.

[0603] When there is an obscured area in front of the road where the autonomous vehicle is driving, the autonomous vehicle can monitor the whistle sound of other vehicles, and when it receives the whistle sound of other vehicles, it can determine that there are other vehicles ahead.

[0604] The self-driving vehicle can set the whistle feature corresponding to the whistle sound of the vehicle. The self-driving vehicle can monitor the sound in the current environment and determine whether the similarity between the voice feature and the whistle feature is higher than the preset threshold. If the similarity between the voice feature and the whistle feature is higher than the preset threshold, it is determined that there are other vehicles in the current environment. Alternatively, if the similarity between the sound feature and the whistle sound feature is higher than a preset threshold, and the source direction of the sound is in front of the autonomous driving vehicle, it is determined that there are other vehicles ahead.

[0605] (2) Identify the light emitted by the vehicle, and use the vehicle emitting the light as the target vehicle.

[0606] When there is an obscured area in front of an autonomous vehicle driving road, the autonomous vehicle can recognize the lights emitted by other vehicles, and when it receives the lights emitted by other vehicles, it can be determined that there are other vehicles ahead.

[0607] Autopilot vehicles can set the corresponding light characteristics of the lights emitted by the vehicle. Autopilot vehicles can take pictures of the front environment, extract the light characteristics in the picture, and determine whether the similarity between the light characteristics and the set light characteristics is higher than the preset threshold , If it is higher than the preset threshold, it is determined that there are other vehicles ahead.

[0608] (3) Send a vehicle identification request to the car networking wireless device, receive the vehicle information returned by the car networking wireless device, and use the vehicle corresponding to the vehicle information as the target vehicle.

[0609] When there is a covered area in front of the road where the autonomous vehicle is driving, the autonomous vehicle can send a vehicle identification request to the IoV wireless device, and the IoV wireless device receives the request of the autonomous vehicle, and screens the vehicles within the preset range of the location of the autonomous vehicle The information is returned to the self-driving vehicle. The self-driving vehicle receives the vehicle information returned by the car networking wireless device to determine whether there are other vehicles ahead.

[0610] Among them, the preset range is a circular area with the autonomous vehicle as the center and the preset distance as the radius, or the autonomous vehicle as the center, the preset distance as the radius, and the preset angle as the vertex angle And constitute the fan-shaped area and so on.

[0611] The car networking wireless device can be street lights, charging piles or other public facilities installed on the roadside, or can also be a management server for logging in to autonomous vehicles. The car networking wireless device can collect vehicle information sent by multiple devices and send the vehicle information to other devices to realize the sharing of vehicle information.

[0612] The vehicle information may include the location of the vehicle. When the autonomous driving vehicle receives the vehicle information, it can determine the vehicle that exists in the preset range and the specific location of the vehicle.

[0613] In addition, the autonomous vehicle can also detect obstacles in front of the autonomous vehicle and in the sheltered area of ​​the autonomous vehicle. Among them, the covered area refers to the area before the field of view of the autonomous vehicle. Optionally, a convex mirror may be provided in the road, and the convex mirror has a reflection effect, and obstacles in the area covered by the autonomous vehicle may be reflected in the convex mirror. When the convex mirror is within the field of view of the autonomous vehicle, the autonomous vehicle can photograph the convex mirror to obtain the convex mirror image, and identify the position of the obstacle contained in the convex mirror image.

[0614] Among them, the self-driving vehicle can obtain the relative position between itself and the convex mirror, and can also obtain the position and angle of the obstacle in the convex mirror image, so as to determine the relative position of the obstacle and the self-driving vehicle.

[0615] Convex mirrors will be installed in places with poor visibility such as winding roads or bends. The driver can see the scene in the blind zone through the convex mirror, which can reduce the blind zone. The autonomous vehicle can recognize the image in the convex mirror according to the convex mirror. The screen to determine whether there is an obstacle ahead and identify the location of the obstacle.

[0616] After that, the autonomous vehicle can plan the meeting position according to the location of the autonomous vehicle, the location of the target vehicle, and the location of obstacles. After the location of the target vehicle and the location of the obstacle are clarified, the method of planning the meeting position is similar to the above method, and will not be repeated here.

[0617] 1203. The autonomous vehicle performs driving operations according to the meeting position.

[0618] In view of the absence of obstacles in the above step 1202, after the autonomous vehicle determines the meeting position, when it reaches the meeting position within the preset distance, it performs the deceleration operation and can also drive to the edge of the road. Leave room for the meeting of the target vehicle.

[0619] Regarding the situation of (1-1) in step 1202 above, step 1203 may include (2-1) and (2-2):

[0620] (2-1) When the meeting position is behind an obstacle, if the autonomous vehicle is far away from the obstacle, the autonomous vehicle will perform a deceleration operation.

[0621] (2-2) When the meeting position is behind an obstacle, if the autonomous vehicle is close to the obstacle, the autonomous vehicle will perform a parking operation.

[0622] Regarding the situation of (1-2) in step 1202 above, step 1203 may include (2-3):

[0623] (2-3) When the meeting position is in front of an obstacle, the autonomous vehicle performs an acceleration operation, quickly bypassing the obstacle and meeting the target vehicle.

[0624] When there are no obstacles in front of the autonomous vehicle, and when the autonomous vehicle meets the target vehicle, for safety reasons, the autonomous vehicle needs to slow down to avoid the target vehicle.

[0625] In one possible implementation, during the meeting, the autonomous vehicle obtains the distance between the autonomous vehicle and the target vehicle. When the distance between the two is not less than the preset distance, the autonomous vehicle runs normally. The distance between the self-driving vehicle and the target vehicle is getting closer and closer. When the distance between the two is less than the preset distance, the deceleration operation is performed so that the self-driving vehicle and the target vehicle can meet safely. The farther you come, when the distance between the two is not less than the preset distance, the deceleration operation will be stopped, and the normal driving speed can be restored at this time.

[0626] In one possible implementation method, when the autonomous vehicle meets the target vehicle, if the target vehicle does not decelerate in advance, and the risk of meeting the vehicle is higher when driving in opposite directions at high speed, the autonomous vehicle is forced to stop and avoid and need to be parked and driven. Operate to achieve a safe meeting, and output the prompt information corresponding to the parking driving operation through the output device. The prompt method is similar to the above (2-2), and will not be repeated here.

[0627] 1204. During the driving operation of the autonomous vehicle, the output device of the self-driving vehicle outputs prompt information. The prompt information is used to prompt the meeting state of the self-driving vehicle and the target vehicle. The output devices include display screens, speakers, and vehicles. At least one of a flute or a reminder light.

[0628] Wherein, the meeting state may include the distance between the self-driving vehicle and the target vehicle, the driving operation currently performed by the self-driving vehicle, whether the self-driving vehicle is currently avoiding, and so on.

[0629] Regarding the situation of (2-1) in step 1203 above, step 1204 may include:

[0630] (3-1) During the deceleration operation, see Figure 13 , Through the output device of the self-driving vehicle, output the prompt information of the self-driving vehicle to avoid, which may include at least one of the following:

[0631] (a) See Figure 13 , For the display screen, when the autonomous vehicle performs a deceleration operation, the display screen displays the prompt information of the deceleration avoidance target vehicle. The prompt information of the deceleration avoidance target vehicle is used to prompt the automatic driving vehicle to decelerate and avoid the target vehicle. When viewing the prompt information, it can be determined that the current autonomous vehicle is decelerating and avoiding the target vehicle, or the prompt information may be prompt information that prompts the other party to pass.

[0632] In one possible implementation, the prompt information of the decelerating and avoiding target vehicle may include text information or image information. For example, the text information may be "Slowing down, please go first", and the image information may be any deceleration operation that can reflect the automatic driving vehicle. picture of.

[0633] (b) See Figure 13 , For the speaker, when the self-driving vehicle performs the deceleration operation, the prompt message of the deceleration avoidance target vehicle is played through the speaker. The prompt information of the deceleration avoidance target vehicle is voice information, which is used to prompt the automatic driving vehicle to slow down so that the target vehicle can listen This prompt information indicates that the autonomous vehicle is currently decelerating.

[0634] (c) See Figure 13 , For the warning light, during the deceleration operation of the self-driving vehicle, the brake light corresponding to the deceleration operation currently performed is turned on, so that the target vehicle can be clear that the self-driving vehicle is decelerating.

[0635] (d) See Figure 13 For the reminder lights, during the deceleration operation of the self-driving vehicle, the current environmental information can be detected, and the reminder light corresponding to the current environmental information can be lit, so that other agents can clarify the location of the self-driving vehicle.

[0636] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0637] Among them, when meeting cars, in order to drive safely, autonomous vehicles need to ensure that the high beams are turned off.

[0638] Regarding the situation of (2-2) in step 1203 above, step 1204 may include:

[0639] (3-2) During the execution of the parking operation, see Figure 13 , Through the output device of the self-driving vehicle, output the prompt information of the self-driving vehicle to stop and avoid.

[0640] (a) See Figure 13 For the display screen, when the self-driving vehicle is parked, the display screen of the self-driving vehicle displays the prompt information and parking sign of the parking avoidance target vehicle, when other agents view the prompt information and parking sign of the parking avoidance target vehicle of the self-driving vehicle , You can determine the current automatic driving vehicle to perform the parking operation.

[0641] In a possible implementation manner, the parking prompt information may be "stop and avoid, please go first", and the parking sign may be any sign that can reflect the parking of the autonomous vehicle.

[0642] (b) See Figure 13 , For the speaker, when the autonomous vehicle performs a parking operation, the speaker will play the prompt information of the parking avoidance target vehicle. The prompt information is voice information, used to prompt the autonomous vehicle to stop, so that the target vehicle can listen to the prompt information and understand To the current stop of the autonomous vehicle.

[0643] (c) See Figure 13 For the warning lights, during the parking operation of the autonomous vehicle, the brake lights and hazard warning flashes (dual flashing lights) corresponding to the currently executed parking operation are turned on, so that the target vehicle can clearly identify that the autonomous vehicle is parking.

[0644] (d) See Figure 13 For the warning lights, during the process of parking the autonomous vehicle, the current environment information can be detected, and the warning lights corresponding to the current environment information can be lit, so that other agents can identify the location of the autonomous vehicle.

[0645] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0646] Among them, when meeting cars, in order to drive safely, autonomous vehicles need to ensure that the high beams are turned off.

[0647] Regarding the situation of (2-3) in step 1203 above, step 1204 may include:

[0648] (3-3) During the acceleration operation, see Figure 13 , Through the output device of the self-driving vehicle, output prompt information requesting the target vehicle to avoid.

[0649] (a) See Figure 13 For the display screen, when the autonomous vehicle performs an acceleration operation, the display screen displays the prompt information requesting the target vehicle to avoid. When the target vehicle views the prompt information of the automatic driving vehicle, it can be determined that the automatic driving vehicle needs to be avoided. Then the target vehicle can actively avoid the self-driving vehicle, or the prompt information can be prompt information prompting the self-driving vehicle to accelerate and detour.

[0650] In one possible implementation, the prompt information requesting the target vehicle to avoid can include text information or image information. For example, the text information can be "accelerating, please avoid", and the image information can be any acceleration operation that can reflect the automatic driving vehicle. picture of.

[0651] (b) See Figure 13 , For the speaker, when the autonomous vehicle performs an acceleration operation, the speaker will play the prompt message requesting the target vehicle to avoid. The prompt message is voice information. The target vehicle can listen to the prompt information and understand that the automatic driving vehicle needs to be avoided. The vehicle can actively avoid the autonomous vehicle.

[0652] (c) See Figure 13 For the reminder lights, during the acceleration operation of the autonomous vehicle, the current environmental information can be detected, and the reminder lights corresponding to the current environmental information can be lit, so that other agents can identify the location of the autonomous vehicle.

[0653] Among them, the environmental information may include temperature, humidity, rainfall, haze index, etc. For example, when there is foggy weather and the fog density is greater than a preset threshold, the fog lamp is turned on, and the outline lamp is turned on in a dark condition or when the field of view is not clear.

[0654] Among them, when meeting cars, in order to drive safely, autonomous vehicles need to ensure that the high beams are turned off.

[0655] When there is no obstacle in front of the autonomous vehicle, and when there is no obstacle in front of the autonomous vehicle, the autonomous vehicle performs the deceleration operation and the operation of avoiding near the edge of the road, and the corresponding prompt information is output through the output device. The prompt method is as in step 1204 (3-1) in is similar, so I won't repeat it here.

[0656] Such as Figure 13 As shown, when the self-driving vehicle and the target vehicle are driving opposite to each other, if the road where the self-driving vehicle is located is unobstructed, the meeting position is planned according to whether there are obstacles in front of the self-driving vehicle and the position of the self-driving vehicle and the target vehicle. If the road where the self-driving vehicle is located is blocked, the self-driving vehicle needs to perform the deceleration operation and sound the siren to warn other vehicles to pay attention, and recognize obstacles in the obscured area of ​​the self-driving vehicle on the road through the convex mirror, and monitor through the whistle and light recognition Screening and identifying the target vehicle that is opposite to the driving direction of the self-driving vehicle with the Internet of Vehicles wireless device. After identifying the target vehicle, the meeting location is planned according to the location of the self-driving vehicle, the location of the target vehicle and the location of obstacles.

[0657] When there is no obstacle in front of the self-driving vehicle or there is an obstacle in front of the self-driving vehicle and the meeting position is behind the obstacle, the self-driving vehicle will slow down or stop when meeting the vehicle. When there is an obstacle in front of the self-driving vehicle and meeting the vehicle When the position is in front of an obstacle, the automatic driving vehicle performs an acceleration operation, and the automatic driving vehicle outputs prompt information corresponding to the driving operation of the automatic driving vehicle through the output device.

[0658] The method provided by the embodiments of the present application recognizes the target vehicle whose driving route and the driving route of the autonomous vehicle intersect, and executes driving operations according to the position of the autonomous vehicle and the position of the target vehicle, so that the autonomous vehicle can be based on the meeting vehicle’s Perform corresponding driving operations on the driving route to improve safety. In the process of performing driving operations, the output device of the self-driving vehicle outputs prompt information. The prompt information is used to prompt the meeting state of the self-driving vehicle and the target vehicle, so that the meeting vehicle and other intelligent agents can accurately and fully understand the automatic driving The driving operation performed by the vehicle avoids as much as possible the conflict between the operation of the meeting vehicle and other intelligent bodies and the driving operation of the self-driving vehicle, which can reduce the probability of traffic accidents and improve safety. In addition, autonomous vehicles can eliminate misunderstandings, reduce risks, improve traffic safety, and reduce traffic accidents by actively interacting with meeting vehicles and other intelligent bodies.

[0659] In addition, determining the meeting position according to the position of the autonomous driving vehicle and the target vehicle and the location of the obstacle can prevent the obstacle from affecting the meeting between the automatic driving vehicle and the target vehicle and improve the safety of the meeting.

[0660] In addition, during the driving operation of the autonomous vehicle, the output device can output prompt information to make the target vehicle clarify the driving intention of the autonomous vehicle, give way to avoid conflict with the driving operation of the autonomous vehicle, and improve safety .

[0661] In addition, when there is obstruction on the road where the autonomous vehicle is located, the position of the obstacle is identified through the convex mirror, and the possible risks in the road can be clarified through the whistle monitoring, light recognition and car networking screening. Carry out driving operations to improve safety.

[0662] The fifth interactive mode: prompts abnormal agents within the range of the autonomous vehicle.

[0663] Figure 14 Is a flow chart of a prompt method according to an exemplary embodiment, such as Figure 14 As shown, the method includes:

[0664] 1401. Collect behavior data of an agent in the current range.

[0665] 1402 According to the collected behavior data, identify abnormal agents within the scope.

[0666] 1403. Output the prompt information of the abnormal agent through the output device of the self-driving vehicle, and the output device includes at least one of a display screen, a speaker, or a prompt light.

[0667] The method provided in the embodiments of the present application collects the behavior data of the agent in the current range, identifies the abnormal agent in the range according to the collected behavior data, and outputs the prompt of the abnormal agent through the output device of the autonomous vehicle Information, so that the autonomous vehicle can learn about the existence of the abnormal agent, so as to avoid the abnormal agent, and other agents can also learn about the existence of the abnormal agent, so as to avoid the abnormal agent and better understand the driving operation of the autonomous vehicle , It can perform corresponding operations according to the driving operation of the autonomous vehicle, avoiding conflicts between the operation of other intelligent bodies and the driving operation of the autonomous vehicle as much as possible, reducing the probability of traffic accidents and improving safety. Moreover, autonomous vehicles can eliminate misunderstandings, reduce risks, improve traffic safety, and reduce traffic accidents by actively interacting with other agents.

[0668] In a possible implementation manner, according to the collected behavior data, identifying abnormal agents within the scope includes at least one of the following:

[0669] When the agent is a vehicle and it is determined that the driving route of the vehicle is abnormal according to the behavior data, the vehicle is determined to be an abnormal vehicle;

[0670] When the agent is a vehicle and it is determined based on the behavior data that the vehicle is driving in an area that does not match the vehicle, the vehicle is determined to be an abnormal vehicle;

[0671] When the agent is a pedestrian, and the pedestrian's walking route is determined to conflict with the driving route of any vehicle based on the behavior data, the pedestrian is determined to be an abnormal pedestrian;

[0672] When the agent is a vehicle, and it is determined that the vehicle's travel route conflicts with the travel route of any pedestrian based on the behavior data, the vehicle is determined to be an abnormal vehicle;

[0673] When the agent is a pedestrian, and the pedestrian is determined to perform an abnormal action based on the behavior data, the pedestrian is determined to be an abnormal pedestrian;

[0674] When the agent is an animal, and it is determined that the animal is stuck in the road based on the behavior data, the animal is determined to be an abnormal animal.

[0675] In a possible implementation manner, according to the collected behavior data, the identification of abnormal agents within the scope includes:

[0676] Match behavior data with preset abnormal behavior data;

[0677] When the similarity between the behavior data and the preset abnormal behavior data is greater than the preset threshold, the agent is determined to be an abnormal agent.

[0678] In a possible implementation manner, the output device of the autonomous vehicle is used to output the prompt information of the abnormal agent, including at least one of the following:

[0679] Through the display screen, the first prompt information is displayed, and the first prompt information is used to prompt the location of the abnormal agent;

[0680] Play the second prompt message through the speaker, and the second prompt message is used to prompt the location of the abnormal agent;

[0681] Perform the whistle operation according to the whistle rhythm corresponding to the abnormal agent.

[0682] In a possible implementation manner, displaying the first prompt information on the display screen includes:

[0683] Through the first display screen, the category to which the abnormal agent belongs is displayed;

[0684] Through the second display screen, display the behavior data of the abnormal agent;

[0685] The first display screen is a display screen on the side of the autonomous vehicle that is close to the abnormal agent, and the second display screen is a display screen of the autonomous vehicle on the side that is far from the abnormal agent.

[0686] In one possible implementation, the output device of the autonomous vehicle is used to output the prompt information of the abnormal agent, including:

[0687] When the driving route of the autonomous vehicle conflicts with the route of the abnormal agent, in the process of executing the driving operation of avoiding the abnormal agent, prompt information is output through the output device, and the prompt information is used to prompt the autonomous vehicle to avoid the abnormal agent.

[0688] In a possible implementation manner, the driving operation of avoiding the abnormal agent includes at least one of the following:

[0689] Lane change operation;

[0690] Slow down operation;

[0691] Parking operation.

[0692] In a possible implementation manner, the driving operation of avoiding the abnormal agent includes an operation of changing lanes, and outputting prompt information through an output device, including at least one of the following:

[0693] Through the display screen, display the lane change prompt information;

[0694] Through the loudspeaker, the voice prompt message of lane change is played;

[0695] Turn on the turn signal corresponding to the lane change operation;

[0696] Perform the whistle operation according to the whistle rhythm corresponding to the lane change operation.

[0697] In a possible implementation manner, the driving operation of avoiding the abnormal agent includes a deceleration operation, and outputting prompt information through an output device, including at least one of the following:

[0698] Through the display screen, display deceleration prompt information;

[0699] Play deceleration voice prompt information through the speaker;

[0700] Light up the prompt light corresponding to the deceleration operation;

[0701] Perform the whistle operation according to the whistle rhythm corresponding to the deceleration operation.

[0702] In a possible implementation manner, the driving operation of avoiding the abnormal agent includes a parking operation, and the prompt information is output through the output device, including at least one of the following:

[0703] Through the display screen, display the parking prompt information and parking signs, which are used to prompt the self-driving vehicle to stop;

[0704] Through the speaker, the parking prompt information is played, and the parking prompt information is used to prompt the autonomous vehicle to stop;

[0705] Operate the whistle according to the whistle rhythm corresponding to the parking operation;

[0706] Turn on the warning light corresponding to the parking operation.

[0707] In a possible implementation manner, the method further includes:

[0708] Through the wireless network, send an abnormal agent notification message to the management server connected to the autonomous vehicle.

[0709] Figure 15 Is a flowchart of another prompt method according to an exemplary embodiment, such as Figure 15 As shown, the method includes:

[0710] 1501. The self-driving vehicle collects behavior data of the agent in the current range.

[0711] There are moving vehicles, pedestrians and animals on the road, which can all be called agents. When the vehicle is driving, the driver may not be able to drive along the center line of the road due to the driver's fatigue, distraction, or playing with the mobile phone, or even drive left and right, or non-motorized vehicles and self-driving vehicles may rush on the road. When pedestrians are walking, they may suddenly go out of the car because they have no scruples, or they may be overly optimistic and compete with autonomous vehicles. Animals may stay in the road and affect the driving of autonomous vehicles. These behaviors are abnormal behaviors, and an agent with abnormal behavior is an abnormal agent.

[0712] When the abnormal agent is within the current range of the autonomous vehicle, it may affect the safe driving of the autonomous vehicle. Autonomous driving needs to change lanes, slow down, or perform parking operations to avoid traffic accidents.

[0713] Therefore, in order to identify the abnormal agents in the current range in time and realize safe automatic driving, the autonomous vehicle needs to collect the behavior data of the agents in the current range during the driving process, so as to be based on the collected behavior data Identify anomalous agents in the range.

[0714] Optionally, the self-driving vehicle may be equipped with a collection device, and the behavior data of the agent within the current range can be collected through the collection device.

[0715] Among them, the current range of the autonomous vehicle refers to the range in which the autonomous vehicle can recognize environmental information. It can be determined according to the maximum distance at which the acquisition device of the autonomous vehicle collects environmental information. It can be centered on the autonomous vehicle to collect information. The maximum distance of environmental information is a circular area composed of a radius, or a fan-shaped area composed of an autonomous vehicle as the center, the maximum distance of collecting environmental information as the radius, and the collection angle of the collection device as the vertex angle.

[0716] The collection device may include at least one of a camera, a lidar, a millimeter-wave radar, an infrared sensor, a humidity sensor, or a temperature sensor, and different types of behavior data can be collected through different collection devices. For example, the behavior data may include the driving route of the vehicle, the driving speed of the vehicle, the walking direction of pedestrians, and the location of animals.

[0717] 1502. The autonomous vehicle matches the behavior data with preset abnormal behavior data.

[0718] The self-driving vehicle can set preset abnormal behavior data according to the behavior characteristics of the abnormal agent. When the autonomous vehicle is driving, the behavior data of the agent within the current range is collected, and the behavior data is matched with preset abnormal behavior data to determine whether the agent is an abnormal agent.

[0719] Optionally, considering that the agent includes multiple categories, the autonomous vehicle can set the preset abnormal behavior data corresponding to each category of agent respectively, then the autonomous vehicle recognizes the agent and collects the behavior data of the agent , First determine the category to which the agent belongs according to the behavior data, then obtain preset abnormal behavior data corresponding to the category, and match the behavior data with the preset abnormal behavior data.

[0720] For example, for an abnormal vehicle, the automatic driving vehicle can determine that the preset abnormal behavior data of the abnormal vehicle includes: the driving route swaying from side to side, driving in a prescribed lane not in accordance with road laws, and not driving along the center line of the road. For abnormal pedestrians, the self-driving vehicle can determine the preset abnormal behavior data of the abnormal pedestrians, including: crossing traffic, standing on the road, suddenly jumping out, etc. For abnormal animals, the autonomous vehicle can determine that the preset behavior data of the abnormal animals include: staying on the road or stopping on the side of the road.

[0721] 1503. When the similarity between the behavior data and the preset abnormal behavior data is greater than a preset threshold, the autonomous vehicle determines that the agent is an abnormal agent.

[0722] The autonomous vehicle calculates the similarity between the behavior data and the preset abnormal behavior data and determines whether the similarity is greater than the preset threshold. If the similarity is greater than the preset threshold, it means that the behavior data is relatively similar to the preset abnormal behavior data. Then it can be determined that the currently recognized agent is an abnormal agent. If the similarity is not greater than the preset threshold, indicating that the behavior data is not similar to the preset abnormal behavior data, it can be determined that the currently recognized agent is not an abnormal intelligence body.

[0723] Wherein, when calculating the similarity between the behavior data and the preset abnormal behavior data, the first feature vector corresponding to the behavior data and the second feature vector corresponding to the preset abnormal behavior data can be obtained, and the first feature vector and the second feature vector can be calculated. The similarity between the two feature vectors is used as the similarity between the behavior data and the preset abnormal behavior data. The similarity can be calculated by using the cosine distance or the Euclidean distance, which is not limited in the embodiment of the present application.

[0724] Wherein, the preset threshold value may be set by default by the autonomous vehicle, or may be set according to the requirement for recognition accuracy.

[0725] Optionally, for agents of the same type, the preset abnormal behavior data can also include multiple types. The autonomous vehicle can set multiple types of preset abnormal behavior data for each agent. In the behavior data of the agent, using the above-mentioned method of calculating the similarity, the preset abnormal behavior data whose similarity with the behavior data is greater than the preset threshold can be determined from multiple types of preset abnormal behavior data. It is determined that the agent is an abnormal agent, and it can also be determined which type of abnormal behavior has occurred in the abnormal agent.

[0726] The first point that needs to be explained is that the current range of the autonomous vehicle may include one or more agents, and similar operations can be performed for each agent to identify whether each agent is an abnormal agent.

[0727] The second point that needs to be explained is that the above steps 1502-1503 are optional steps, and the autonomous vehicle may also use other methods to identify abnormal agents.

[0728] For example, in a possible implementation manner, according to the collected behavior data, identifying abnormal agents within the scope may also include at least one of the following:

[0729] (1) When the agent is a vehicle and it is determined that the driving route of the vehicle is abnormal according to the behavior data, the vehicle is determined to be an abnormal vehicle.

[0730] Autonomous vehicles can collect behavioral data of vehicles within the current range. The behavioral data can include the position of the vehicle at multiple times in the current cycle. The driving route of the vehicle can be determined according to the change in the position of the vehicle, and the driving route can be determined Whether it is abnormal, such as whether the driving direction corresponding to the driving route has changed multiple times, whether the driving direction corresponding to the driving route matches the specified driving direction of the lane where the vehicle is located, etc. When it is determined that the driving route of the vehicle is abnormal according to the behavior data, it can be determined that the vehicle is an abnormal vehicle.

[0731] Among them, the self-driving vehicle can collect behavior data in the cycle every other cycle, and a cycle can be 1 second, 1 minute, or 2 minutes.

[0732] (2) When the agent is a vehicle, and it is determined that the vehicle is driving in an area that does not match the vehicle based on the behavior data, the vehicle is determined to be an abnormal vehicle.

[0733] The autonomous driving vehicle can collect the behavior data of the vehicles in the current range. The behavior data can include the location of the vehicle. According to the location of the vehicle, determine the area where the vehicle is currently located, and determine whether the vehicle matches the area, such as a motor vehicle. Should drive in motor vehicle lanes, non-motor vehicles should drive in non-motor vehicle lanes, etc. When it is determined according to the behavior data that the vehicle is driving in an area that does not match the vehicle, it can be determined that the vehicle is an abnormal vehicle.

[0734] (3) When the agent is a pedestrian, and it is determined according to the behavior data that the pedestrian's walking route conflicts with the driving route of any vehicle, the pedestrian is determined to be an abnormal pedestrian.

[0735] Among them, the conflict between the walking route of the pedestrian and the driving route of the vehicle may include: the walking route of the pedestrian crosses the driving route of the vehicle, the pedestrian and the vehicle are in the same position at the same time, or the walking route of the pedestrian coincides with the driving route of the vehicle and the pedestrian is located The front of the vehicle may also include other conditions, which are not limited in the embodiment of the present application.

[0736] Optionally, the self-driving vehicle obtains the current walking route of the pedestrian and the driving route of the vehicle, determines whether the walking route and the driving route conflict, and if there is a conflict, determines that the pedestrian is an abnormal pedestrian.

[0737] Optionally, the self-driving vehicle can also predict the walking route of pedestrians and the driving route of the vehicle in the next cycle. That is, the autonomous vehicle can collect the behavior data of the vehicles in the current range. The behavior data can include the position and driving direction of the vehicle, and then the driving route of the vehicle can be predicted based on the position and driving direction of the vehicle. In addition, pedestrian behavior data can be collected. The behavior data includes the position and walking direction of the pedestrian, and the pedestrian's walking route can be predicted according to the position and walking direction of the pedestrian. It is judged whether there is a conflict between the walking route and the driving route. If there is a conflict, it means that the pedestrian and the vehicle are about to collide, and the pedestrian is determined to be an abnormal pedestrian.

[0738] (4) When the agent is a vehicle, and it is determined according to the behavior data that the driving route of the vehicle conflicts with the walking route of any pedestrian, the vehicle is determined to be an abnormal vehicle.

[0739] This step (4) is similar to the above step (3) and will not be repeated here.

[0740] (5) When the agent is a pedestrian, and it is determined that the pedestrian performs an abnormal action according to the behavior data, the pedestrian is determined to be an abnormal pedestrian.

[0741] The self-driving vehicle can collect the behavior data of the pedestrians in the current range to determine the actions performed by the pedestrians and determine whether the actions are abnormal actions, so as to determine whether the pedestrians are abnormal pedestrians.

[0742] For example, autonomous vehicles pre-determine actions such as crossing the road, hurdling, staying on the road, running on the road, and going out of the vehicle in the middle of the road as abnormal actions, and judge whether the pedestrian's actions belong to the preset abnormal actions. When the pedestrian's motion belongs to any of the preset abnormal motions, the pedestrian is determined to be an abnormal pedestrian.

[0743] Alternatively, the autonomous vehicle pre-determined normal walking on the roadside, staying at the bus station, etc. as normal actions, and judged whether the pedestrian's actions belong to the preset normal actions. When the pedestrian's actions do not belong to all the preset normal actions During the action, determine that the pedestrian is an abnormal pedestrian.

[0744] (6) When the agent is an animal, and it is determined that the animal is stuck in the road based on the behavior data, the animal is determined to be an abnormal animal.

[0745] The self-driving vehicle can collect the behavior data of the animals in the current range. The behavior data includes the position of the animal at multiple times in the current cycle. When it is determined that the animal’s position is on the road and there is no animal at multiple times When there is a change, it means that the animal is stuck in the road, and the action is determined to be an abnormal animal at this time.

[0746] 1504. Output the prompt information of the abnormal agent through the output device of the autonomous vehicle.

[0747] The self-driving vehicle is equipped with an output device, and the output device includes at least one of a display screen, a speaker, a car whistle, or a warning light. Wherein, the number of display screens may be one or more, and the facing directions may include front, rear, left, right, and top, so as to realize the function of displaying information in the multiple directions. And the display screen can include multiple types of display screens such as subtitle screens and video screens. There can be one or more speakers, which can be installed on the roof or side of the car. The car whistle can include a mechanical whistle or an electronic whistle. The warning lights include turn signals, fog lights, and position lights.

[0748] The prompt information of the abnormal agent includes the text with abnormal characters, the screen of the abnormal agent, the position of the abnormal agent, the voice message of the abnormal agent being broadcast, and the whistle prompting the abnormal agent.

[0749] In a possible implementation manner, outputting the prompt information of the abnormal agent through the output device may include at least one of the following:

[0750] (1) See Figure 16 For the display screen, when there is an abnormal agent in the range where the autonomous vehicle is currently located, the first prompt information is displayed through the display screen, and the first prompt information is used to prompt the location of the abnormal agent.

[0751] By configuring the display screen, during the driving of the autonomous vehicle, the display screen of the autonomous vehicle displays the first prompt information. When other agents view the first prompt information of the autonomous vehicle, they can determine the current location of the autonomous vehicle There is an abnormal agent in the range.

[0752] In a possible implementation manner, the first prompt information may include text information or picture information, for example, the text information may be "abnormal pedestrians exist", and the picture information may be any picture that can reflect the location of abnormal pedestrians.

[0753] In one possible implementation, the autonomous vehicle is equipped with multiple display screens, each display screen faces a different direction, and each display screen can display different information. For example, an autonomous vehicle is equipped with 5 display screens, each of which faces forward, rear, left, right, and top, in five directions, so that the autonomous vehicle is forward, rear, left, right, and top. Agents in five directions can view the prompt information of autonomous vehicles.

[0754] In one possible implementation manner, displaying the first prompt information through the display screen includes: displaying the category to which the abnormal agent belongs through the first display screen; displaying the behavior data of the abnormal agent through the second display screen; The display screen is a display screen on the side of the autonomous vehicle close to the abnormal agent, and the second display screen is the display screen on the side of the autonomous vehicle away from the abnormal agent.

[0755] Prompts are displayed on the side of the autonomous vehicle close to the abnormal agent and the side far away from the abnormal agent. The display screen on the side close to the abnormal agent displays the category of the abnormal agent, so that other agents on the side close to the abnormal agent can be used as early as possible. Knowing that there is an abnormal situation, avoid giving way early or slow down, reducing the probability of traffic accidents. The display screen on the side far from the abnormal agent displays the behavior data of the abnormal agent, so that other agents on the side far away from the abnormal agent can better understand the driving behavior of the autonomous vehicle, give way in time, and improve safety.

[0756] (2) See Figure 16 For the speaker, when the autonomous vehicle determines that there is an abnormal agent in the current range, the second prompt information is played through the speaker, and the second prompt information is used to prompt the location of the abnormal agent.

[0757] Wherein, the second prompt information is voice information. By configuring a speaker, the speaker of the self-driving vehicle plays the second prompt information during the driving of the autonomous vehicle, so that other agents can listen to the second prompt information and learn about the abnormality. The location of the agent.

[0758] In one possible implementation, one or more speakers can be set up, the speakers can be placed on the roof of the autonomous vehicle, and the sound diffusion effect will be better. In addition, the speakers can also be placed in the front, rear, left or right of the car. side.

[0759] (3) See Figure 16 For car horns, when there is an abnormal agent in the current range of the autonomous vehicle, the whistle operation can be performed according to the whistle rhythm corresponding to the abnormal agent.

[0760] Among them, the self-driving vehicle is equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or the electronic whistle. Autonomous vehicles can set the number of whistle whistle in each fixed period to determine the whistle rhythm. Different agent types correspond to different whistle whistle rhythms. The period can be one second or one minute, etc.

[0761] When the autonomous vehicle collects the behavior data of the agent in the current range, it can obtain the category of the abnormal agent. The autonomous vehicle can establish the correspondence between different categories and the rhythm of the whistle. When the autonomous vehicle recognizes the abnormal agent , Confirm the category to which the abnormal agent belongs, query the corresponding relationship, obtain the whistle rhythm corresponding to the category, and perform the whistling operation according to the whistle rhythm corresponding to the category, which can alert the abnormal agent and actively remind the abnormal agent Correcting the dangerous behavior also enables other agents to learn about the types of abnormal agents in the current area of ​​the autonomous vehicle, and remind other agents to be careful of the abnormal agents.

[0762] In the embodiment of the present application, the autonomous vehicle may establish a connection with the management server, log in to the management server, and send an abnormal agent notification message to the management server. The management server receives the abnormal agent notification message sent by the self-driving vehicle, publishes the abnormal agent notification message, and the management personnel checks the abnormal agent notification message and processes the abnormal agent in a timely manner.

[0763] Among them, self-driving vehicles can be equipped with car networking wireless devices, and communicate with other devices through car networking wireless devices.

[0764] Among them, the abnormal agent notification message carries the position information and behavior data of the abnormal agent. Through the location information, managers can clearly know the location of the abnormal agent, and through the behavior data, they can understand the abnormal situation of the abnormal agent.

[0765] Wherein, publishing the abnormal agent notification message may include: the management server sends alarm information to the control terminal, the control terminal displays the alarm information, and the manager holding the control terminal views the alarm information, and the alarm information carries the location of the abnormal agent For information and behavior data, managers go to the location of the abnormal agent to process the abnormal agent.

[0766] Optionally, the management server sends alarm information to the nearest control terminal, which can notify the nearest management personnel, so that the abnormal agent can be processed in the fastest time.

[0767] Other agents can include smart devices, such as mobile phones, computers, car networking wireless devices, etc. The smart devices can establish a connection with the management server, log in to the management server, and the autonomous vehicle sends an abnormal agent notification message to the management server. The abnormal agent notification message is forwarded to the smart device logging in to the management server, and the smart device outputs the abnormal agent notification message. The user of the smart device learns the location information and behavior data of the abnormal agent and can go to the abnormal agent The location, processing the abnormal agent. Or, the risk of the road section where the abnormal agent is located can be predicted, so as to make a detour or slow down in advance, which improves traffic safety and reduces traffic accidents.

[0768] 1505. When the driving route of the self-driving vehicle conflicts with the route of the abnormal agent, the self-driving vehicle performs a driving operation to avoid the abnormal agent.

[0769] In order to ensure safe driving and avoid traffic accidents, when the driving route of the autonomous vehicle conflicts with the route of the abnormal agent, it is necessary to perform corresponding driving operations to avoid the abnormal agent.

[0770] The self-driving vehicle can obtain the route of the current abnormal agent and the driving route of the self-driving vehicle, and judge whether the route of the abnormal agent and the driving route of the self-driving vehicle conflict. If a conflict occurs, the self-driving vehicle needs to avoid the abnormal intelligence body.

[0771] The driving operation of the avoidance abnormal agent includes at least one of lane changing operation, deceleration operation, or parking operation.

[0772] For example, when the abnormal agent is a vehicle, if the abnormal agent and the autonomous vehicle are in the same lane and driving in the same direction, and the abnormal agent is located behind the autonomous vehicle, the autonomous vehicle needs to perform lane change operations to avoid the abnormal agent; If the anomalous agent and the autonomous vehicle are in the same lane and driving in the same direction, and the anomaly agent is in front of the autonomous vehicle, the autonomous vehicle needs to perform a deceleration operation to avoid the anomaly agent; when the anomaly agent suddenly breaks into the road When a pedestrian is in front of an autonomous vehicle, the autonomous vehicle needs to perform a parking operation to avoid it.

[0773] 1506. In the process of executing the driving operation of the automatic driving vehicle to avoid the abnormal agent, it outputs prompt information for prompting the automatic driving vehicle to avoid the abnormal agent through the output device.

[0774] In the embodiment of this application, the autonomous driving vehicle outputs prompt information through an output device. The prompt information is used to remind other agents that the autonomous vehicle is currently avoiding the abnormal agent, so that other agents can understand that the autonomous vehicle is avoiding the abnormal agent. behavior.

[0775] The prompt information can carry related information of the abnormal agent. For example, the prompt information displayed on the display screen and the prompt information played through the speaker can carry the category of the abnormal agent, the position of the abnormal agent, and the current execution of the abnormal agent. Abnormal actions, etc., are not limited in the embodiment of the present application.

[0776] When the driving operation is a lane change operation, the output device is used to output prompt information for prompting the autonomous vehicle to avoid the abnormal agent, which may include at least one of the following:

[0777] (1) See Figure 16 For the display screen, when the autonomous vehicle executes the lane change operation, the lane change prompt information is displayed on the display screen. When other agents view the prompt information of the autonomous vehicle, they can determine that the current autonomous vehicle is changing lanes.

[0778] In one possible implementation, the prompt information corresponding to the lane changing operation may include text information or picture information. For example, the text information may be "changing lanes, avoiding abnormal agents", and the picture information may be any information that can reflect automatic driving. Picture of the operation performed by the vehicle.

[0779] (2) See Figure 16 , For the speaker, when the autonomous vehicle performs the lane change operation, the speaker will play the prompt information of the lane change to avoid abnormal agent. The lane change prompt information is voice information. Other agents can listen to the prompt information and learn about automatic driving The vehicle is currently changing lanes.

[0780] (3) See Figure 16 For the warning lights, when the autonomous vehicle is performing the lane changing operation, turn on the turn signal corresponding to the lane changing driving operation, so that other intelligent agents can know that the autonomous vehicle is changing lanes.

[0781] (4) See Figure 16 For car horns, during the process of lane change operations performed by the autonomous vehicle, the horn operation can be performed in accordance with the whistle rhythm corresponding to the lane change operations.

[0782] Among them, the self-driving vehicle is equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or the electronic whistle. The self-driving vehicle can set the number of whistle honking in each fixed period to determine the whistle rhythm. The period can be one second or one minute, etc.

[0783] The autonomous vehicle can establish the corresponding relationship between the lane change operation and the whistle rhythm. When the autonomous vehicle performs the lane change operation, the corresponding relationship is inquired to obtain the whistle rhythm corresponding to the lane change operation. Operate the corresponding whistle rhythm to perform the whistle operation, so that other agents can understand that the autonomous vehicle is currently changing lanes.

[0784] Self-driving vehicles can automatically perform the whistle operation, or a whistle button is provided on the steering wheel, and the driver will also perform the whistle operation when pressed.

[0785] When the driving operation is a deceleration operation, the output device is used to output prompt information for prompting the autonomous vehicle to avoid the abnormal agent, which may include at least one of the following:

[0786] (1) See Figure 16 , For the display screen, when the autopilot vehicle performs a deceleration operation, the deceleration prompt information is displayed on the display screen. The deceleration prompt information is used to prompt the autopilot vehicle to slow down. When other agents view the deceleration prompt information of the autopilot vehicle, It can be determined that the current autonomous vehicle is decelerating.

[0787] In one possible implementation, the deceleration prompt information may include text information or picture information. For example, the text information may be "slowing down, avoid abnormal agents", and the picture information may be any picture that can reflect the deceleration operation performed by the autonomous vehicle .

[0788] (2) See Figure 16 , For the speaker, when the self-driving vehicle performs a deceleration operation, the deceleration prompt information is played through the speaker. The deceleration prompt information is a voice message, which is used to prompt the self-driving vehicle to slow down, so that other agents can listen to the deceleration prompt information. The autonomous vehicle is currently decelerating.

[0789] (3) See Figure 16 For the prompt light, during the deceleration operation of the self-driving vehicle, the prompt light corresponding to the deceleration operation currently performed is turned on, so that other agents can know that the self-driving vehicle is decelerating.

[0790] (4) See Figure 16 For car horns, during the deceleration operation of the self-driving vehicle, the whistle operation can be performed according to the whistle rhythm corresponding to the deceleration operation.

[0791] Among them, the self-driving vehicle is equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or the electronic whistle. The self-driving vehicle can set the number of whistle honking in each fixed period to determine the whistle rhythm. The period can be one second or one minute, etc.

[0792] Automatically driving vehicles can establish the corresponding relationship between the deceleration operation and the whistle rhythm. When the automatic driving vehicle performs the deceleration operation, query the corresponding relationship to obtain the whistle rhythm corresponding to the deceleration operation, and follow the whistle rhythm corresponding to the deceleration operation. The whistle rhythm performs the whistle operation, so that other agents can understand that the autonomous vehicle is currently decelerating.

[0793] Self-driving vehicles can automatically perform the whistle operation, or a whistle button is provided on the steering wheel, and the driver will also perform the whistle operation when pressed.

[0794] When the driving operation is a parking operation, the output device is used to output prompt information for prompting the autonomous vehicle to avoid the abnormal agent, which may include at least one of the following:

[0795] (1) See Figure 16 , Regarding the display screen, the parking prompt information and parking sign are displayed through the display screen, and the parking prompt information and parking sign are used to prompt the self-driving vehicle to stop.

[0796] During the parking driving operation of the self-driving vehicle, the parking prompt information and the parking sign are displayed on the display screen, and the parking prompt information and the parking sign are used to prompt the self-driving vehicle to stop.

[0797] By configuring the display screen, when the self-driving vehicle is parked, the display screen of the self-driving vehicle displays the parking prompt information and parking sign. When other agents view the parking prompt information and parking sign of the self-driving vehicle, the current self-driving vehicle can be determined parking.

[0798] In a possible implementation manner, the parking prompt message may be "Please note when parking", and the parking sign may be any sign that can reflect the parking of the autonomous vehicle.

[0799] (2) See Figure 16 , Regarding the speaker, during the parking driving operation of the autonomous vehicle, the parking prompt information is played through the speaker, and the parking prompt information is used to prompt the autonomous vehicle to stop.

[0800] By configuring the speaker, during the driving of the autonomous vehicle, the speaker of the autonomous vehicle will play voice prompts, so that other agents can listen to it and learn about the current parking of the autonomous vehicle.

[0801] (3) See Figure 16 , For the reminder light, when the autonomous vehicle is performing the parking driving operation, the reminder light corresponding to the parking operation is lit, so that other agents can make it clear that the autonomous vehicle is parking.

[0802] (4) See Figure 16 For car horns, during the process of parking and driving operations performed by the autonomous vehicle, the whistle operation can be performed in accordance with the whistle rhythm corresponding to the parking operation.

[0803] Among them, the self-driving vehicle is equipped with a mechanical whistle or an electronic whistle, and the whistle can be operated through the mechanical whistle or the electronic whistle. The self-driving vehicle can set the number of whistle honking in each fixed period to determine the whistle rhythm. The period can be one second or one minute, etc.

[0804] Automatically driving vehicles can establish the corresponding relationship between parking operation and whistle rhythm. When the automatic driving vehicle performs parking driving operations, query the corresponding relationship to obtain the whistle rhythm corresponding to the parking operation, and follow the corresponding parking operation The whistle rhythm is performed to perform the whistle operation, so that other agents can learn that the autonomous vehicle is currently parking.

[0805] Self-driving vehicles can automatically perform the whistle operation, or a whistle button is provided on the steering wheel, and the driver will also perform the whistle operation when pressed.

[0806] Such as Figure 16 As shown, first determine whether there is an abnormal agent in the current range of the autonomous vehicle. If so, determine whether the driving route of the autonomous vehicle and the abnormal agent conflict, so as to determine which driving operation the autonomous vehicle performs. The vehicle’s display screen, speakers, reminder lights, and car whistle remind abnormal agents and driving operations performed by autonomous vehicles.

[0807] In the case of a route conflict, the position of the abnormal agent is displayed on the display screen, the position of the abnormal agent is played through the speaker, the whistle operation is performed according to the whistle rhythm corresponding to the abnormal agent, and the abnormality is sent to the management server connected to the autonomous vehicle Agent notification message. In the case of route conflicts, autonomous vehicles need to change lanes, slow down to avoid or stop to avoid, and will use similar methods to prompt.

[0808] The method provided in the embodiments of the present application collects the behavior data of the agent in the current range, identifies the abnormal agent in the range according to the collected behavior data, and outputs the prompt of the abnormal agent through the output device of the autonomous vehicle Information, so that the autonomous vehicle can learn about the existence of the abnormal agent, so as to avoid the abnormal agent, and other agents can also learn about the existence of the abnormal agent, so as to avoid the abnormal agent and better understand the driving operation of the autonomous vehicle , It can perform corresponding operations according to the driving operation of the autonomous vehicle, avoiding conflicts between the operation of other intelligent bodies and the driving operation of the autonomous vehicle as much as possible, reducing the probability of traffic accidents and improving safety. Moreover, autonomous vehicles can eliminate misunderstandings, reduce risks, improve traffic safety, and reduce traffic accidents by actively interacting with other agents.

[0809] In addition, by matching the collected behavior data with the preset abnormal behavior data, the abnormal agent can be identified, which improves the recognition accuracy.

[0810] In addition, the display screen, speakers, and car whistle are used to provide prompts, and the prompt channels are diversified, which can increase the probability of other agents receiving prompt information, and avoid traffic accidents caused by failure of a certain output device. , Improve the safety of autonomous driving.

[0811] In addition, prompt messages are displayed on the side of the autonomous vehicle close to the abnormal agent and the side far away from the abnormal agent. The display screen on the side close to the abnormal agent displays the category of the abnormal agent, so that the Other agents learn about the abnormal situation early, and avoid giving way or slowing down as soon as possible, reducing the probability of traffic accidents. The display screen on the side far from the abnormal agent displays the behavior data of the abnormal agent, so that other agents on the side far away from the abnormal agent can better understand the driving behavior of the autonomous vehicle, give way in time, and improve safety.

[0812] In addition, the output device outputs the prompt information corresponding to the driving operation performed by the autonomous vehicle, so that other agents understand the driving operation of the autonomous vehicle better, and can perform corresponding operations according to the driving operation of the autonomous vehicle, avoiding as much as possible The conflict between the operation of other agents and the driving operation of the autonomous vehicle can reduce the probability of traffic accidents and improve safety.

[0813] In addition, when it is determined that there is an abnormal agent in the current range of the autonomous vehicle, the abnormal agent notification message can be sent to the management server connected to the autonomous vehicle through the wireless network, and the management server can be promptly assisted by the abnormal agent. Processing is performed to prevent the abnormal agent from continuing to affect the driving of other vehicles. The notification message of the abnormal agent can also be sent to other agents through the management server, so that other agents can know the road section of the abnormal agent in advance, avoid driving, and avoid possible occurrences. Risks improve the safety of autonomous vehicles.

[0814] Figure 17 Is a block diagram of a prompting device according to an exemplary embodiment, such as Figure 17 As shown, the device includes:

[0815] The behavior data collection module 1701 is used to collect behavior data of the agent in the current range;

[0816] The identification module 1702 is used to identify abnormal agents in the range according to the collected behavior data;

[0817] The prompt information output module 1703 is configured to output prompt information of the abnormal agent through the output device of the autonomous vehicle. The output device includes at least one of a display screen, a speaker, or a prompt light.

[0818] In one possible implementation, such as Figure 18 As shown, the identification module 1702 includes at least one of the following:

[0819] The first determining unit 1710 is configured to determine that the vehicle is an abnormal vehicle when the agent is a vehicle and the driving route of the vehicle is determined to be abnormal according to the behavior data;

[0820] The second determining unit 1711 is used for determining that the vehicle is an abnormal vehicle when the agent is a vehicle and it is determined according to the behavior data that the vehicle is driving in an area that does not match the vehicle;

[0821] The third determining unit 1712 is configured to determine that the pedestrian is an abnormal pedestrian when the agent is a pedestrian and the pedestrian's walking route is determined to conflict with the driving route of any vehicle according to the behavior data;

[0822] The fourth determining unit 1713 is configured to determine that the vehicle is an abnormal vehicle when the agent is a vehicle and it is determined according to the behavior data that the travel route of the vehicle conflicts with the travel route of any pedestrian;

[0823] The fifth determining unit 1714 is configured to determine that the pedestrian is an abnormal pedestrian when the agent is a pedestrian and it is determined that the pedestrian performs an abnormal action according to the behavior data;

[0824] The sixth determining unit 1715 is used for determining that the animal is an abnormal animal when the agent is an animal and it is determined that the animal is stuck in the road according to the behavior data.

[0825] In one possible implementation, such as Figure 18 As shown, the identification module 1702 includes:

[0826] The matching unit 1716 is configured to match the behavior data with preset abnormal behavior data;

[0827] The seventh determining unit 1717 is configured to determine that the agent is an abnormal agent when the similarity between the behavior data and the preset abnormal behavior data is greater than the preset threshold.

[0828] In one possible implementation, such as Figure 18 As shown, the prompt information output module 1703 includes at least one of the following:

[0829] The first display unit 1720 is configured to display first prompt information on a display screen, and the first prompt information is used to prompt the location of the abnormal agent;

[0830] The first playing unit 1721 is configured to play second prompt information through the speaker, and the second prompt information is used to prompt the location of the abnormal agent;

[0831] The first whistle unit 1722 is configured to perform whistle operation according to the whistle rhythm corresponding to the abnormal agent.

[0832] In one possible implementation, such as Figure 18 As shown, the first display unit 1720 is also used for:

[0833] Through the first display screen, the category to which the abnormal agent belongs is displayed;

[0834] Through the second display screen, display the behavior data of the abnormal agent;

[0835] The first display screen is a display screen on the side of the autonomous vehicle that is close to the abnormal agent, and the second display screen is a display screen of the autonomous vehicle on the side that is far from the abnormal agent.

[0836] In one possible implementation, such as Figure 18 As shown, the prompt information output module 1703 includes:

[0837] The avoidance prompt unit 1723 is used to output prompt information through the output device when the driving route of the autonomous vehicle conflicts with the route of the abnormal agent, and the prompt information is used to prompt automatic driving during the process of executing the driving operation of the avoidance abnormal agent. Vehicle avoids anomalous agents.

[0838] In one possible implementation, such as Figure 18 As shown, the driving operation of avoiding the abnormal agent includes at least one of the following:

[0839] Lane change operation;

[0840] Slow down operation;

[0841] Parking operation.

[0842] In one possible implementation, such as Figure 18 As shown, the driving operation of the avoiding abnormal agent includes lane changing operations, and the avoiding prompt unit 1723 is further configured to perform at least one of the following:

[0843] Through the display screen, display the lane change prompt information;

[0844] Through the loudspeaker, the voice prompt message of lane change is played;

[0845] Turn on the turn signal corresponding to the lane change operation;

[0846] Perform the whistle operation according to the whistle rhythm corresponding to the lane change operation.

[0847] In one possible implementation, such as Figure 18 As shown, the driving operation of the avoidance abnormal agent includes a deceleration operation, and the avoidance prompt unit 1723 is further configured to perform at least one of the following:

[0848] Through the display screen, display deceleration prompt information;

[0849] Play deceleration voice prompt information through the speaker;

[0850] Light up the prompt light corresponding to the deceleration operation;

[0851] Perform the whistle operation according to the whistle rhythm corresponding to the deceleration operation.

[0852] In one possible implementation, such as Figure 18 As shown, the driving operation of the avoiding abnormal agent includes a parking operation, and the avoiding prompt unit 1723 is further configured to perform at least one of the following:

[0853] Through the display screen, display the parking prompt information and parking signs, which are used to prompt the self-driving vehicle to stop;

[0854] Through the speaker, the parking prompt information is played, and the parking prompt information is used to prompt the autonomous vehicle to stop;

[0855] Operate the whistle according to the whistle rhythm corresponding to the parking operation;

[0856] Turn on the warning light corresponding to the parking operation.

[0857] In one possible implementation, such as Figure 18 As shown, the device also includes:

[0858] The sending module 1704 is configured to send an abnormal agent notification message to the management server connected to the autonomous driving vehicle through a wireless network.

[0859] Figure 19 It is a schematic diagram showing the structure of an automatic driving vehicle according to an exemplary embodiment. Generally, the autonomous vehicle 1900 includes a processor 1901 and a memory 1902.

[0860] The processor 1901 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 1901 can adopt at least one hardware form among DSP (Digital Signal Processing, Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array, Programmable Logic Array). achieve. The processor 1901 may also include a main processor and a coprocessor. The main processor is a processor used to process data in the awake state, also known as a CPU (Central Processing Unit, central processing unit); It is a low-power processor for processing data in the standby state. In some embodiments, the processor 1901 may be integrated with a GPU (Graphics Processing Unit, image processing interactive device), and the GPU is used to render and draw content that needs to be displayed on the display screen. In some embodiments, the processor 1901 may further include an AI (Artificial Intelligence, artificial intelligence) processor, which is used to process calculation operations related to machine learning.

[0861] The memory 1902 may include one or more computer-readable storage media, which may be non-transitory. The memory 1902 may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1902 is used to store at least one instruction, and the at least one instruction is used by the processor 1901 to implement the lane information provided by the method embodiment of the present application. Obtaining method.

[0862] In some embodiments, the autonomous vehicle 1900 may optionally further include: a peripheral device interface 1903 and at least one peripheral device. The processor 1901, the memory 1902, and the peripheral device interface 1903 may be connected by a bus or a signal line. Each peripheral device can be connected to the peripheral device interface 1903 through a bus, a signal line, or a circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 1904, a touch display screen 1905, a camera 1906, an audio circuit 1907, a positioning component 1908, and a power supply 1909.

[0863] The peripheral device interface 1903 can be used to connect at least one peripheral device related to I/O (Input/Output) to the processor 1901 and the memory 1902. In some embodiments, the processor 1901, the memory 1902, and the peripheral device interface 1903 are integrated on the same chip or circuit board; in some other embodiments, any one of the processor 1901, the memory 1902, and the peripheral device interface 1903 or The two can be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0864] The radio frequency circuit 1904 is used to receive and transmit RF (Radio Frequency, radio frequency) signals, also called electromagnetic signals. The radio frequency circuit 1904 communicates with a communication network and other communication devices through electromagnetic signals. The radio frequency circuit 1904 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 1904 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and so on. The radio frequency circuit 1904 can communicate with other autonomous vehicles through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: metropolitan area network, various generations of mobile communication networks (2G, 3G, 4G and 8G), wireless local area network and/or WiFi (Wireless Fidelity, wireless fidelity) network. In some embodiments, the radio frequency circuit 1904 may also include a circuit related to NFC (Near Field Communication), which is not limited in this application.

[0865] The display screen 1905 is used to display a UI (User Interface, user interface). The UI can include graphics, text, icons, videos, and any combination thereof. When the display screen 1905 is a touch display screen, the display screen 1905 also has the ability to collect touch signals on or above the surface of the display screen 1905. The touch signal may be input to the processor 1901 as a control signal for processing. At this time, the display screen 1905 may also be used to provide virtual buttons and/or virtual keyboards, also called soft buttons and/or soft keyboards. In some embodiments, there may be one display screen 1905, which is provided with the front panel of the autonomous vehicle 1900; in other embodiments, there may be at least two display screens 1905, which are respectively provided on different surfaces or on different surfaces of the autonomous vehicle 1900. Folding design; in other embodiments, the display screen 1905 may be a flexible display screen, which is set on the curved surface or the folding surface of the autonomous vehicle 1900. Furthermore, the display screen 1905 can also be set as a non-rectangular irregular pattern, that is, a special-shaped screen. The display screen 1905 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0866] The camera assembly 1906 is used to capture images or videos. Optionally, the camera assembly 1906 includes a front camera and a rear camera. Generally, the front camera is arranged on the front panel of the autonomous vehicle 1900, and the rear camera is arranged on the back of the autonomous vehicle 1900. In some embodiments, there are at least two rear cameras, each of which is a main camera, a depth-of-field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth-of-field camera to realize the background blur function, the main camera Integrate with the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1906 may also include a flash. The flash can be a single-color flash or a dual-color flash. Dual color temperature flash refers to a combination of warm light flash and cold light flash, which can be used for light compensation under different color temperatures.

[0867] The audio circuit 1907 may include a microphone and a speaker. The microphone is used to collect sound waves of the user and the environment, and convert the sound waves into electrical signals and input them to the processor 1901 for processing, or input to the radio frequency circuit 1904 to implement voice communication. For the purpose of stereo collection or noise reduction, there may be multiple microphones, which are respectively arranged in different parts of the autonomous vehicle 1900. The microphone can also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert the electrical signal from the processor 1901 or the radio frequency circuit 1904 into sound waves. The speaker can be a traditional thin-film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, not only can the electrical signal be converted into human audible sound waves, but also the electrical signal can be converted into human inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1907 may also include a headphone jack.

[0868] The positioning component 1908 is used to locate the current geographic location of the autonomous vehicle 1900 to implement navigation or LBS (Location Based Service). The positioning component 1908 may be a positioning component based on the GPS (Global Positioning System, Global Positioning System) of the United States, the Beidou system of China, the Grenas system of Russia, or the Galileo system of the European Union.

[0869] The power supply 1909 is used to supply power to various components in the autonomous vehicle 1900. The power source 1909 may be alternating current, direct current, disposable batteries, or rechargeable batteries. When the power source 1909 includes a rechargeable battery, the rechargeable battery may support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0870] In some embodiments, the autonomous vehicle 1900 further includes one or more sensors 1910. The one or more sensors 1910 include, but are not limited to: an acceleration sensor 1911, a gyroscope sensor 1912, a pressure sensor 1913, a fingerprint sensor 1914, an optical sensor 1915, and a proximity sensor 1916.

[0871] The acceleration sensor 1911 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the autonomous vehicle 1900. For example, the acceleration sensor 1911 can be used to detect the components of the gravitational acceleration on three coordinate axes. The processor 1901 may control the touch screen 1905 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 1911. The acceleration sensor 1911 may also be used for the collection of game or user motion data.

[0872] The gyroscope sensor 1912 can detect the body direction and rotation angle of the autonomous vehicle 1900, and the gyroscope sensor 1912 can cooperate with the acceleration sensor 1911 to collect the user's 3D actions on the autonomous vehicle 1900. Based on the data collected by the gyroscope sensor 1912, the processor 1901 can implement the following functions: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0873] The pressure sensor 1913 may be arranged on the side frame of the autonomous vehicle 1900 and/or the lower layer of the touch screen 1905. When the pressure sensor 1913 is arranged on the side frame of the autonomous vehicle 1900, the user's holding signal of the autonomous vehicle 1900 can be detected, and the processor 1901 performs left and right hand recognition or quick operation according to the holding signal collected by the pressure sensor 1913. When the pressure sensor 1913 is arranged on the lower layer of the touch display screen 1905, the processor 1901 can control the operability controls on the UI interface according to the user's pressure operation on the touch display screen 1905. The operability control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0874] The fingerprint sensor 1914 is used to collect the user's fingerprint. The processor 1901 can identify the user's identity based on the fingerprint collected by the fingerprint sensor 1414, or the fingerprint sensor 1914 can identify the user's identity based on the collected fingerprint. When it is recognized that the user's identity is a trusted identity, the processor 1901 authorizes the user to have related sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings. The fingerprint sensor 1914 may be provided on the front, back or side of the autonomous vehicle 1900. When a physical button or manufacturer logo is provided on the autonomous vehicle 1900, the fingerprint sensor 1914 can be integrated with the physical button or manufacturer logo.

[0875] The optical sensor 1915 is used to collect the ambient light intensity. In an embodiment, the processor 1901 may control the display brightness of the touch screen 1905 according to the ambient light intensity collected by the optical sensor 1915. Specifically, when the ambient light intensity is high, the display brightness of the touch screen 1905 is increased; when the ambient light intensity is low, the display brightness of the touch screen 1905 is decreased. In another embodiment, the processor 1901 may also dynamically adjust the shooting parameters of the camera assembly 1906 according to the ambient light intensity collected by the optical sensor 1915.

[0876] The proximity sensor 1916, also called a distance sensor, is usually installed on the front panel of the autonomous vehicle 1900. The proximity sensor 1916 is used to collect the distance between the user and the front of the autonomous vehicle 1900. In one embodiment, when the proximity sensor 1916 detects that the distance between the user and the front of the autonomous vehicle 1900 gradually decreases, the processor 1901 controls the touch screen 1905 to switch from the on-screen state to the off-screen state; when the proximity sensor When 1916 detects that the distance between the user and the front of the autonomous vehicle 1900 is gradually increasing, the processor 1901 controls the touch screen 1905 to switch from the rest screen state to the bright screen state.

[0877] Those skilled in the art can understand, Figure 19 The structure shown in does not constitute a limitation on the autonomous vehicle 1900, and may include more or fewer components than shown, or combine some components, or adopt different component arrangements.

[0878] An embodiment of the present application also provides an autonomous driving vehicle. The autonomous driving vehicle includes an output device, a processor, and a memory. The output device includes at least one of a display screen, a speaker, a car whistle, or a warning light, and the memory stores at least one of: One piece of program code, at least one piece of program code is loaded and executed by the processor, so as to implement the operations performed in the method of the foregoing embodiment.

[0879] The embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores at least one piece of program code, and at least one piece of program code is loaded and executed by a processor to implement what is executed in the method of the above-mentioned embodiment operating.

[0880] An embodiment of the present application also provides a computer program, in which at least one piece of program code is stored, and the at least one piece of program code is loaded and executed by a processor to implement operations performed in the method of the above-mentioned embodiment.

[0881] The above description is only for the convenience of those skilled in the art to understand the technical solutions of the application, and is not intended to limit the application. Any modification, equivalent replacement, improvement, etc., made within the spirit and principle of this application shall be included in the protection scope of this application.