Control method, device, apparatus, medium and program product of vehicle

Abstract

The application discloses a kind of control method, device, equipment, medium and program product of vehicle, it is related to automobile technical field, the method comprises the following steps: the environment information and vehicle operation information of the target road of first vehicle travel are collected, environment information is used to indicate the road condition of target road and the case that biological subject exists on target road;In the case that biological subject exists on target road, the collision probability that first vehicle and biological subject occur collision event is predicted based on environment information and vehicle operation information;In response to the collision probability belongs to first probability interval, control first vehicle deceleration travel;In response to the collision probability belongs to second probability interval, control first vehicle stop travel, wherein the value of first probability interval is less than the value of second probability interval.Can predict the probability of colliding with pedestrian during vehicle travel, timely control vehicle deceleration or brake, reduce the probability of collision accident.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of automobiles, and in particular, to a vehicle control method, device, equipment, medium and program product. BACKGROUND

[0002] In order to ensure the safety of the driver driving the vehicle, most vehicles on the market are equipped with an automatic emergency braking system.

[0003] The automatic emergency braking system controls the vehicle to brake in an emergency when the distance between the vehicle and a target in the driving direction is close, so as to avoid the vehicle colliding with the target and reduce rear-end accidents caused by the driver's inattention.

[0004] However, in complex vehicle use scenarios, the automatic emergency braking system also has some limitations. For example, in rainy and snowy weather, due to the presence of water or ice on the ground, the vehicle may lose control when braking. SUMMARY

[0005] Embodiments of the present application provide a vehicle control method, device, equipment, medium and program product, which can predict the probability of a vehicle colliding with a pedestrian during driving, control the vehicle to slow down or brake in time, and reduce the probability of a collision accident. The technical solution is as follows:

[0006] In one aspect, a vehicle control method is provided, the method comprising:

[0007] Collecting environmental information of a target road on which a first vehicle is driving and vehicle operation information, the environmental information being used to indicate the road conditions of the target road and the presence of a biological subject on the target road; the vehicle operation information including vehicle speed information and a driving direction of the first vehicle;

[0008] In the presence of a biological subject on the target road, based on the environmental information and the vehicle operation information, a collision probability of a collision event between the first vehicle and the biological subject is predicted;

[0009] In response to the collision probability belonging to a first probability interval, the first vehicle is controlled to slow down;

[0010] In response to the collision probability belonging to a second probability interval, the first vehicle is controlled to stop driving, wherein the value of the first probability interval is less than the value of the second probability interval.

[0011] In another aspect, a vehicle control device is provided, the device comprising:

[0012] The collection module is configured to collect environmental information and vehicle operation information of a target road on which the first vehicle travels, the environmental information being used to indicate a road condition of the target road and a presence of a biological subject on the target road, and the vehicle operation information including vehicle speed information and a travel direction of the first vehicle.

[0013] The prediction module is configured to predict a collision probability of a collision event between the first vehicle and the biological subject based on the environmental information and the vehicle operation information in the presence of the biological subject on the target road.

[0014] The control module is configured to control the first vehicle to travel at a reduced speed in response to the collision probability belonging to a first probability interval.

[0015] The control module is further configured to control the first vehicle to stop traveling in response to the collision probability belonging to a second probability interval, wherein a value of the first probability interval is less than a value of the second probability interval.

[0016] In another aspect, a computer device is provided, which includes a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement the control method of the vehicle according to any one of the above embodiments of the present application.

[0017] In another aspect, a computer readable storage medium is provided, which stores at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by a processor to implement the control method of the vehicle according to any one of the above embodiments of the present application.

[0018] In another aspect, a computer program product or a computer program is provided, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the control method of the vehicle according to any one of the above embodiments.

[0019] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0020] By predicting the probability of a collision event between the vehicle and the pedestrian during the driving of the vehicle, the vehicle is decelerated or emergency braked according to the predicted probability of the collision event, so as to avoid the collision between the vehicle and the pedestrian and effectively reduce rear-end accidents caused by the distraction of the driver. When there is a pedestrian in the forward direction of the vehicle, the probability of collision is low, and the vehicle is still decelerated. Compared with the related art in which the vehicle is braked only when the distance between the vehicle and the pedestrian is short, the probability of a collision accident caused by the skid of the vehicle in emergency braking under extreme weather conditions can be reduced, and the safety of the driver is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a schematic diagram of a control system of a vehicle provided by an exemplary embodiment of the present application;

[0023] Figure 2 is a flowchart of a control method of a vehicle provided by an exemplary embodiment of the present application;

[0024] Figure 3 is a structural block diagram of a control device of a vehicle provided by an exemplary embodiment of the present application;

[0025] Figure 4 is a structural block diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0027] The exemplary embodiments will be described in detail below, and the examples are shown in the drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0028] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or," as used herein, refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0029] It should be noted that the information and data involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0030] It should be understood that although the terms first, second, etc. can be used in this application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, a first parameter can also be referred to as a second parameter, and similarly, a second parameter can also be referred to as a first parameter, without departing from the scope of the present application. Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining".

[0031] In order to ensure the safety of the driver when driving the vehicle, most vehicles on the market are equipped with an automatic emergency braking system. The automatic emergency braking system controls the vehicle to brake in an emergency when the distance between the vehicle and the target in the direction of travel is close, so as to avoid the vehicle colliding with the target and reduce rear-end accidents caused by the driver's inattention. The target includes but is not limited to vehicles, moving pedestrians, animals, etc., that is, everything that can be considered as a target when colliding with a vehicle that has a certain speed will cause economic losses or safety accidents.

[0032] However, in complex vehicle use scenarios, the automatic emergency braking system also has some limitations. For example, in rainy and snowy weather conditions, there is water or ice on the ground, and the friction between the wet and slippery road surface and the vehicle tires will decrease significantly. Since friction is the main source of resistance when the vehicle brakes, when the friction decreases, the braking effect of the vehicle will also be weakened to varying degrees, and there may be a situation of vehicle loss of control caused by vehicle skidding when braking.

[0033] Since the automatic emergency braking system is usually triggered when the distance between the vehicle and the target is close, when the braking effect is poor, the moving track of the vehicle cannot be predicted when it skids, and it is difficult to ensure the safety of both parties between the vehicle and the target. Therefore, how to improve the safety of the vehicle during driving and solve the problem of poor braking effect of the vehicle in extreme weather conditions is crucial.

[0034] The application provides a control method of a vehicle, information collection is performed on the environment of the vehicle running on a road, the probability of collision between the vehicle and a target is predicted in combination with the running state of the vehicle, the vehicle is directly braked when the probability is high, and the vehicle is controlled to decelerate when the collision probability is low, so that the safe distance between the vehicle and the target is maintained, thereby reducing the occurrence of accidents. Compared with the manner of relying on the straight-line distance between the vehicle and the target to brake the vehicle in the related art, the vehicle can be controlled to brake or decelerate while maintaining the safe distance, so that the collision between the vehicle and the target in the out-of-control state of the vehicle is avoided. Moreover, the problem of rear-end accidents and the like caused by poor braking effect of the vehicle in extreme weather can be solved.

[0035] The related terms involved in the application are explained.

[0036] Vehicle lateral acceleration: refers to the acceleration in the direction perpendicular to the direction of vehicle travel, which is mainly caused by the centrifugal force generated when the vehicle turns. This acceleration reflects the tendency of the vehicle to be "flung" off the driving path. In the safety system of the vehicle, a lateral acceleration sensor is used to measure this acceleration. When the vehicle turns, the vehicle will generate lateral acceleration due to the centrifugal force. When the system detects that the vehicle may slide or deviate from the road, the vehicle can be kept stable by correcting the steering operation of the driver to prevent accidents such as sliding or deviating from the road.

[0037] Vehicle longitudinal acceleration: refers to the acceleration in the same direction as the direction of vehicle travel, i.e., the rate of change of speed of the vehicle in its forward direction. When the vehicle accelerates, the longitudinal acceleration is positive, indicating that the speed is increasing; when the vehicle decelerates or brakes, the longitudinal acceleration is negative, indicating that the speed is decreasing. Generally, during the driving process of the vehicle, the acceleration used to describe the increase in speed is the longitudinal acceleration of the vehicle.

[0038] Vehicle emergency braking: refers to the rapid and correct use of the brake by the driver when the vehicle encounters an emergency situation during driving, so as to stop the vehicle in the shortest distance. The emergency braking system is usually mounted on the front of the vehicle, and the radar, camera and sensor are used to sense the front obstacles. When the front obstacles appear and the driver does not brake, the vehicle will automatically take emergency braking measures to reduce the collision accident. For the vehicle equipped with an automatic emergency braking system, when the vehicle is in emergency braking, the vehicle will control the position of the accelerator pedal to be lifted and control the position of the brake pedal to be at the bottom, which is equivalent to the driver quickly lifting the accelerator pedal and immediately stepping on the brake pedal with force, while stepping on the clutch pedal, so as to quickly stop the vehicle.

[0039] Secondly, the control system of the vehicle involved in the embodiment of the application is described, and the schematic diagram is shown in Figure 1The implementation environment involves a first vehicle 110, a server 120, and a plurality of sensors 111, the first vehicle 110 and the server 120 are connected through a communication network 130, and the plurality of sensors 111 are installed on the vehicle body of the first vehicle 110.

[0040] Among the plurality of sensors 111, there are sensors for collecting different information, such as sensors for collecting environmental information of the target road where the first vehicle 110 is located, and sensors for collecting vehicle operation information of the first vehicle 110. The information collected by these sensors is used to predict the collision probability between the first vehicle 110 and the pedestrians existing on the target road.

[0041] After the plurality of sensors 111 collect a variety of information, the plurality of information is sent to the server 120 through the communication network connection 130. The server 120 has a pre-trained machine learning network, and inputs the plurality of information into the machine learning network to output the collision probability between the first vehicle 110 and the pedestrians. The server 120 returns the collision probability to the first vehicle 110.

[0042] The vehicle body controller / vehicle-mounted terminal of the first vehicle 110 determines how to control the first vehicle 110 according to the interval range of the collision probability. When the collision probability belongs to the first probability interval, the first vehicle 110 is controlled to slow down; when the collision probability belongs to the second probability interval, the first vehicle 110 is controlled to stop, wherein the value of the first probability interval is less than the value of the second probability interval.

[0043] In summary, by predicting the probability of a collision event between a vehicle and a pedestrian during vehicle travel, the vehicle is slowed down or braked according to the predicted probability of the collision event, avoiding the vehicle colliding with the pedestrian and effectively reducing rear-end accidents caused by driver distraction. When there is a pedestrian in the forward direction of the vehicle, the collision probability is low, and the vehicle is still slowed down. Compared with the related art, which brakes only when the distance between the vehicle and the pedestrian is close, the probability of a collision accident caused by the vehicle skidding during emergency braking in extreme weather is reduced, ensuring the safety of the driver.

[0044] It is worth noting that the above-mentioned server can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. Basic cloud computing services such as platform.

[0045] The cloud technology refers to a kind of hosting technology that series resources such as hardware, software and network are unified in wide area network or local area network to realize the calculation, storage, processing and sharing of data.The cloud technology is the general term of network technology, information technology, integration technology, management platform technology and application technology based on cloud computing business model application, can form resource pool, and is used on demand, flexible and convenient.Cloud computing technology will become an important support.The background service of technical network system needs a large amount of computing and storage resources, such as video website, picture website and more portal website.With the high development and application of Internet industry, every item may have its own identification mark in the future, and needs to be transmitted to the background system for logical processing.Different levels of data will be processed separately, and various industry data need strong system backup support, which can only be realized by cloud computing.

[0046] In some embodiments, the above-mentioned server can also be implemented as a node in a blockchain system.

[0047] In combination with the above-mentioned introduction of terms and application scenarios, the control method of the vehicle provided in the present application is described, which can be executed by the server or the first vehicle, or jointly executed by the server and the first vehicle.In the embodiments of the present application, the control method of the vehicle is taken as an example to be executed by the first vehicle, as shown in Figure 2 Figure 2 is a flow chart of the control method of the vehicle provided in an exemplary embodiment of the present application.The method comprises the following steps.

[0048] In step 210, the environmental information of the target road on which the first vehicle travels and the vehicle operation information are collected.

[0049] The environmental information is used to indicate the road condition of the target road and the existence of biological subjects on the target road, and the vehicle operation information includes the speed information and the driving direction of the first vehicle.

[0050] Optionally, a vehicle perception sensor is installed on the first vehicle, which is used to identify the road condition of the target road to obtain the environmental information.

[0051] For example, the image of the target road is collected by the vehicle perception sensor, and the traffic participants of the road are identified, wherein the traffic participants include lane lines, other vehicles except the first vehicle, biological subjects, traffic signal lights, and the road environment is modeled with the first vehicle as a reference point.

[0052] The types of biological subjects include but are not limited to: (1) pedestrians, such as pedestrians walking on the target road and pedestrians driving vehicles; (2) animals, such as pets and stray animals.

[0053] ​Optionally, the vehicle running information of the first vehicle is used to describe the vehicle self-condition of the first vehicle when driving on the target road, including but not limited to: the current vehicle speed of the first vehicle, the lateral acceleration of the first vehicle, the longitudinal acceleration of the first vehicle, the accelerator pedal position (used to indicate whether the first vehicle is in an acceleration state, if in the acceleration state, the degree of speed increase is determined according to the opening degree of the accelerator pedal, etc.), the brake pedal position (used to indicate whether the first vehicle is controlled by the driver to decelerate, emergency brake, etc.), etc.

[0054] Wherein, according to the vehicle type of the first vehicle, the accelerator pedal can be an electric door pedal (the first vehicle is an electric vehicle) and a throttle pedal (the first vehicle is a fuel vehicle).

[0055] It is worth noting that the types of collected environmental information and vehicle running information are different, and a plurality of different sensors can be installed on the first vehicle to collect different types of information, for example, the lateral acceleration of the first vehicle can be measured by a lateral acceleration sensor.

[0056] Step 220, in the case that there is a biological subject on the target road, based on the environmental information and the vehicle running information, the collision probability of the collision event between the first vehicle and the biological subject is predicted.

[0057] For example, after collecting the environmental information, the environmental information is identified based on an image recognition algorithm to determine whether there is a biological subject on the target road. Taking the collected environmental information as an image for example.

[0058] The environmental information and the vehicle running information are input into a pre-trained machine learning network to determine the predicted running mode of the first vehicle in the future time period, and the collision probability is determined based on the predicted running mode and the environmental information.

[0059] Wherein, the starting time of the future time period is the current time, and the predicted running mode is used to indicate the driving condition of the first vehicle in the future time period.

[0060] For example, the future time period refers to a time period of 5 seconds from the current time.

[0061] The current time is 10:00:00, and the future time period refers to the time period between 10:00:00 and 10:00:05.

[0062] The predicted running mode refers to a vehicle running mode of the first vehicle at a future time, and the vehicle running mode includes but is not limited to the following modes: (1) uniform speed driving mode, the first vehicle maintains the current speed and the current driving direction; (2) acceleration / deceleration driving mode, the first vehicle increases / decreases the current speed based on the opening degree of the accelerator pedal, and maintains the current driving direction; (3) braking driving mode, the first vehicle controls the vehicle to stop based on the opening degree of the brake pedal; and (4) direction changing driving mode, the steering wheel rotation angle and direction of the first vehicle control the driving direction of the first vehicle.

[0063] Optionally, a probability table is obtained, the probability table includes a plurality of corresponding relationships between a plurality of vehicle running modes and collision probabilities, and the plurality of corresponding relationships include the first corresponding relationship. The first corresponding relationship is selected from the probability table based on the environment information and the predicted running mode, and the collision probability is determined based on the first corresponding relationship.

[0064] For example, the environment information collected when the first vehicle is on the target road has a plurality of possible conditions. Each vehicle running mode corresponds to a unique collision probability based on the environment information as a prerequisite.

[0065] For example, please refer to Table 1 below, which is an example of a probability table.

[0066] Table 1

[0067]

[0068] In Table 1, the numbers (0, 1, 2, 3) in the first column indicate the serial numbers corresponding to the prerequisite conditions determined based on the environment information. The first row in Table 1 is used to indicate a plurality of vehicle running modes of the first vehicle.

[0069] The numbers in the table are indexed as predicted collision probabilities based on the index condition of (prerequisite condition, vehicle running mode).

[0070] (1) The environment information corresponding to the prerequisite condition 0 is as follows: the distance between the first vehicle and the biological subject is greater than the safety distance, and the road on which the first vehicle travels is not slippery;

[0071] (2) The environment information corresponding to the prerequisite condition 1 is as follows: the distance between the first vehicle and the biological subject is less than the safety distance, and the road on which the first vehicle travels is not slippery;

[0072] (3) The environment information corresponding to the prerequisite condition 2 is as follows: the distance between the first vehicle and the biological subject is greater than the safety distance, and the road on which the first vehicle travels is slippery;

[0073] (4) The environmental information corresponding to precondition 3 is as follows: the distance between the first vehicle and the biological subject is less than the safety distance, and the road on which the first vehicle travels is wet and slippery.

[0074] For example, the predicted running mode of the first vehicle is the accelerating running mode, and the environmental information collected by the first vehicle corresponds to precondition 1. Then, the index condition is (1, accelerating running mode), and the first corresponding relationship is determined as: accelerating running mode-0.6, that is, the collision probability between the first vehicle and the biological subject is 0.6.

[0075] For example, the way to determine whether the road on which the first vehicle travels is wet and slippery is as follows.

[0076] 1. First, determine the weather condition of the current region. If the current region is raining / snowing / hailing at the current time, the ground must be wet and slippery. If there is no rain / snow in the current region within a preset time period before the current time, the ground may be wet and slippery and needs to be further determined. If there is rain / snow in the current region within a preset time period before the current time, the ground may be wet and slippery and also needs to be further determined.

[0077] The way to determine the weather condition includes but is not limited to: (1) determining according to the weather forecast information obtained by the vehicle terminal networking; (2) identifying whether there is rain / snow / hail, etc. according to the collected environmental image.

[0078] 2. When the weather condition alone cannot determine whether the ground is wet and slippery, the environmental image collected by the sensor of the first vehicle is used for identification to determine whether the ground color meets the wet and slippery judgment requirement. For example, the ground is light gray in dry state and dark gray in wet state. If the ground color depth is identified to be less than a preset value, it is determined that the ground is dry. If the ground color depth is identified to be greater than the preset value, it is determined that the ground may be wet and slippery and needs to be further determined.

[0079] 3. The ground color in the environmental image is repaired according to the time when the environmental image is collected, and whether the depth of the repaired ground color exceeds a preset value is determined to determine whether the ground is wet.

[0080] For example, when the sunset starts at 18:00 local time and the night starts at 19:00, the ground color does not need to be repaired in the time period from 6:00 to 18:00, and whether the ground is wet and slippery is determined directly based on the environment image; in the time period from 18:00 to 19:00, the ground color is affected by the increasing light with time, and then the ground color in the image is repaired according to the time (for example, the ground color depth of the environment image collected at 18:13 is 249, and the ground color depth after repair is 249-13=236); in the time period from 19:00 to 6:00, there is no sunlight, and the friction between the first vehicle and the ground is determined according to the vehicle sensor to determine whether the ground is wet and slippery.

[0081] In some embodiments, in addition to the ground wetness degree used for the example described above, the premise indexed in the probability control table can also include the slope of the road on which the first vehicle travels (i.e., the road slope), which affects the braking and deceleration effect of the first vehicle, thereby affecting the probability of the collision event between the first vehicle and the target.

[0082] For example, when the first vehicle travels on an uphill road section, compared with traveling on a flat road, the first vehicle is more likely to decelerate and brake, and the probability of collision between the first vehicle and the biological subject is relatively low. When the first vehicle travels on a downhill road section, the speed of the first vehicle is easy to be too fast due to the influence of gravity, and the braking system is under heavy load, and long-time braking on a downhill road is easy to cause the brake drum to overheat, thereby significantly reducing the braking effect, and the probability of collision between the first vehicle and the biological subject is increased.

[0083] When the premise contains the slope of the first vehicle, the road slope information can be obtained in the following ways.

[0084] 1. A device capable of measuring the slope of the road on which the first vehicle is located, such as a gyroscope, is installed on the first vehicle, and the information such as whether the first vehicle is on an uphill / downhill road section and the inclination angle of the road section is determined according to the angle output by the gyroscope;

[0085] 2. The correspondence between the power output of the first vehicle and the current speed is used to determine whether the first vehicle is on an uphill / downhill road section. When the ratio of the output power (work done by the traction force) of the first vehicle to the current speed is higher than the ratio when the first vehicle travels on a flat road, it indicates that the speed does not increase significantly under the same output power, and the resistance is greater than that on a flat road, so the first vehicle is on an uphill road section. When the ratio decreases, it indicates that the speed increases significantly under the same output power, and the resistance is smaller than that on a flat road, so the first vehicle is on a downhill road section.

[0086] In some embodiments, in addition to the manner of predicting the collision probability of the first vehicle and the biological subject based on the pre-set probability table, the collision probability between the first vehicle and the biological subject can also be determined by predicting the moving trajectories of the first vehicle and the biological subject respectively, judging whether the trajectories intersect, and whether the intersection point meets the collision condition when the trajectories intersect.

[0087] Optionally, the first motion trajectory of the biological subject is predicted based on the environment information, and the first running trajectory of the first vehicle is predicted based on the vehicle running information.

[0088] Taking the collected environment image as the environment information, the biological subject is displayed in multiple environment images, and the multiple environment images are input into the pre-trained machine learning model. The machine learning model can predict the first motion trajectory of the biological subject according to the position change of the biological subject in the image.

[0089] Wherein, a three-dimensional coordinate system is established with any designated point on the road where the first vehicle is located as the origin, and the first motion trajectory includes the position coordinates of the biological subject in the three-dimensional coordinate system at multiple future time points. The running state of the first vehicle is determined based on the vehicle running information of the first vehicle, and the vehicle running information is input into the pre-trained machine learning model. The vehicle running information includes the speed, steering wheel position, and opening degree information of the accelerator pedal / brake pedal of the first vehicle. The machine learning model can predict the first running trajectory of the first vehicle according to the vehicle running information, and the first running trajectory includes the position coordinates of the first vehicle in the three-dimensional coordinate system at multiple future time points.

[0090] For example, there is a signal light intersection on the target road where the first vehicle travels, and the environment image is collected by the camera assembly at the top of the first vehicle. The environment image contains the signal light intersection, and a three-dimensional coordinate system is established with the signal light intersection as the origin.

[0091] Wherein, a distance sensor is installed on the first vehicle, and the distance sensor obtains the distance between the first vehicle and the signal light intersection based on radar technology.

[0092] The sensor determines the distance between the first vehicle and the signal light intersection by emitting electromagnetic waves / radio waves, based on the first time taken for the electromagnetic waves / radio waves to reflect back to the sensor, the speed of the electromagnetic waves / radio waves, and the distance traveled by the first vehicle within the first time.

[0093] Based on the position of the signal light intersection in the environment image, the relative position of the first vehicle and the signal light intersection in the actual environment can be determined. For example, the relative position indicates that the first vehicle is located in the southwest direction of the signal light intersection, and the direction angle is 50 degrees.

[0094] The position of the first vehicle is converted into specific coordinates in a three-dimensional coordinate system based on the distance and the direction angle between the first vehicle and the signal light intersection, and the first running track of the first vehicle is determined according to the change of the coordinates.

[0095] The first motion track and the first running track are fitted into a two-dimensional curve in the same coordinate system, and it is determined whether there is an intersection between the first motion track and the first running track, that is, whether there is coincidence between the first motion track and the first running track.

[0096] Exemplarily, the three-dimensional coordinate system includes a horizontal axis, a vertical axis and a vertical axis, and the vertical axis is a coordinate axis perpendicular to the ground. The first vehicle and the biological subject are both moving on the ground, so the coordinate plane perpendicular to the vertical axis in the three-dimensional coordinate system is regarded as a two-dimensional coordinate system, and the first motion track and the first running track are mapped in the two-dimensional coordinate system to obtain two two-dimensional curves.

[0097] If there is no intersection between the two-dimensional curves corresponding to the first motion track and the first running track, there is no coincidence between the first motion track and the first running track, and no collision will occur between the first vehicle and the biological subject.

[0098] If there is an intersection between the two-dimensional curves corresponding to the first motion track and the first running track, there is coincidence between the first motion track and the first running track, and a collision may occur between the first vehicle and the biological subject. At this time, it is necessary to further determine the collision probability between the first vehicle and the biological subject.

[0099] In response to the coincidence between the first motion track and the first running track, the first time when the first vehicle reaches the coincidence position and the second time when the biological subject reaches the coincidence position are determined. In response to the time length difference between the first time and the second time being less than a preset time length threshold, it is determined that the collision probability is greater than a probability threshold.

[0100] Exemplarily, the probability threshold is 0.6, and the preset time length threshold is 2 seconds.

[0101] For example, the first time is 10:00:05, and the second time is 10:00:09. The time length difference between the first time and the second time is 4 seconds, which is greater than the preset time length threshold of 2 seconds, indicating that the first vehicle passes the coincidence position first, and the biological subject passes the coincidence position later, and the tracks of the first vehicle and the biological subject are staggered. Therefore, it is determined that the collision probability is less than the probability threshold, and the first vehicle is controlled to drive at a reduced speed.

[0102] For example, the first time is 10:00:06, and the second time is 10:00:05, the time difference between the first time and the second time is 1 second, which is less than the preset time threshold of 2 seconds, and it can be approximately considered that the first vehicle and the biological subject pass through the coincident position at the same time, and it is determined that the collision probability is greater than the probability threshold, and the first vehicle is controlled to stop driving.

[0103] In step 230, in response to the collision probability belonging to the first probability interval, the first vehicle is controlled to drive at a reduced speed.

[0104] For example, the first probability interval refers to the collision probability being less than or equal to a preset probability threshold.

[0105] For example, the preset probability threshold is 0.5, and the value range of the first probability interval is (0, 0.5).

[0106] In response to the collision probability being less than or equal to the preset probability threshold, the first distance between the biological subject and the first vehicle is determined based on the environmental information, the target vehicle speed and the target vehicle deceleration of the first vehicle are determined based on the current vehicle speed of the first vehicle and the first distance, and the first vehicle is controlled to drive at the target vehicle speed based on the target vehicle deceleration.

[0107] Optionally, the vehicle operating information includes the current vehicle speed, the vehicle lateral acceleration, the vehicle longitudinal acceleration, the brake pedal position, and the accelerator pedal position, the moving speed of the biological subject is determined based on the environmental information, the target vehicle speed of the first vehicle is determined by inputting the first distance, the moving speed of the biological subject, and the vehicle operating information into a speed limit equation, and the target vehicle deceleration is determined based on the current vehicle speed of the first vehicle, the target vehicle speed, and the first distance.

[0108] For example, the speed limit equation is as follows:

[0109] V=K0*V0+K1*A1+K2*A2+K3*P1+K4*P2+K5*V1+K6*D.

[0110] Wherein, V is the target vehicle speed of the first vehicle, V0 is the current vehicle speed of the first vehicle, A1 is the vehicle lateral acceleration of the first vehicle, A2 is the vehicle longitudinal acceleration of the first vehicle, P1 is a braking parameter determined based on the brake pedal position, P2 is an acceleration parameter determined based on the accelerator pedal position, V1 is the moving speed of the biological subject, D is the first distance, K0, K1, K2, K3, K4, K5, and K6 are preset coefficients, and the preset coefficients are real numbers.

[0111] The current vehicle speed V0 of the first vehicle, the vehicle lateral acceleration A1 of the first vehicle, and the vehicle longitudinal acceleration A2 of the first vehicle can be directly obtained from the vehicle running information of the first vehicle, and the moving speed V1 of the biological subject and the first distance D can be calculated according to the environment image collected by the vehicle sensor.

[0112] In some embodiments, the braking parameter P1 and the acceleration parameter P2 need to be determined according to the running state of the first vehicle and the specific positions of the brake pedal and the accelerator pedal.

[0113] For example, the position of the accelerator pedal in the vehicle running information corresponds to the opening degree of the accelerator pedal, which ranges from 0 to 1. If the opening degree is 0, it means that the accelerator pedal is not stepped on, and the vehicle has no additional acceleration or power, and the first vehicle runs according to the default power output. Therefore, the acceleration parameter P2 can be represented by the opening degree of the accelerator pedal.

[0114] For example, the position of the brake pedal in the vehicle running information corresponds to the opening degree of the brake pedal, which ranges from 0 to 1. If the opening degree is 1, it means that the brake pedal is stepped to the bottom, and the first vehicle is braked to a stop. Therefore, the braking parameter P1 can be represented by the opening degree of the brake pedal. The preset coefficients K0, K1, K2, K3, K4, K5, and K6 can be determined according to the vehicle performance of the first vehicle.

[0115] For example, K0 is the coefficient corresponding to the current speed of the first vehicle, which is determined according to the current speed of the first vehicle and the speed limit value of the current road. If the current speed of the first vehicle is 30 km / h, the speed limit value of the current road is the minimum 20 km / h and the maximum 60 km / h, and the average speed limit is (20+60) / 2=40 km / h, then the first coefficient K0 is determined based on the ratio of the average speed limit to the current speed, i.e. K0=40 / 30=4 / 3.

[0116] In step 240, the first vehicle is controlled to stop running in response to the collision probability belonging to the second probability interval.

[0117] The value of the first probability interval is less than the value of the second probability interval.

[0118] For example, the second probability interval refers to the collision probability being greater than a preset probability threshold.

[0119] For example, the preset probability threshold is 0.5, and the value range of the second probability interval is (0.5, 1).

[0120] In some embodiments, the collision probability between the first vehicle and the biological subject is 0, and the first vehicle travels according to the control of the driver. The collision probability between the first vehicle and the biological subject is predicted in real time. When the vehicle perception sensor of the first vehicle collects information indicating that there is a biological subject on the driving route of the first vehicle, the collision probability between the first vehicle and the biological subject needs to be predicted in real time until the collision probability is 0.

[0121] In summary, the method of the vehicle provided in the application predicts the probability of a collision event between the vehicle and a pedestrian during the driving of the vehicle, and slows down or performs emergency braking on the vehicle according to the predicted probability of the collision event, thereby avoiding the collision between the vehicle and the pedestrian and effectively reducing rear-end accidents caused by the distraction of the driver. When there is a pedestrian in the forward direction of the vehicle, the collision probability is low, and the vehicle is still slowed down. Compared with the related art in which the vehicle is braked only when the distance between the vehicle and the pedestrian is close, the probability of a collision accident caused by the skidding of the vehicle during emergency braking in extreme weather can be reduced, and the safety of the driver can be ensured.

[0122] Figure 3 is a structural block diagram of the control device of the vehicle provided in an exemplary embodiment of the application, as shown in Figure 3 The device includes the following parts.

[0123] The acquisition module 310 is configured to acquire environmental information and vehicle operation information of a target road on which a first vehicle travels. The environmental information is used to indicate the road condition of the target road and the presence of a biological subject on the target road. The vehicle operation information includes vehicle speed information and a driving direction of the first vehicle.

[0124] The prediction module 320 is configured to predict a collision probability of a collision event between the first vehicle and the biological subject based on the environmental information and the vehicle operation information when the biological subject is present on the target road.

[0125] The control module 330 is configured to control the first vehicle to travel at a reduced speed in response to the collision probability belonging to a first probability interval.

[0126] The control module 330 is further configured to control the first vehicle to stop traveling in response to the collision probability belonging to a second probability interval, where the value of the first probability interval is less than the value of the second probability interval.

[0127] In an optional embodiment, the prediction module 320 is further configured to input the environment information and the vehicle running information into a pre-trained machine learning network to determine a predicted running mode of the first vehicle in a future time period, the start time of the future time period being the current time, the predicted running mode being used to indicate a driving condition of the first vehicle in the future time period; and determine the collision probability based on the predicted running mode and the environment information.

[0128] In an optional embodiment, the prediction module 320 is further configured to obtain a probability table, the probability table including a plurality of corresponding relationships between a plurality of vehicle running modes and the collision probability, the plurality of corresponding relationships including a first corresponding relationship; and determine the first corresponding relationship from the probability table based on the environment information and the predicted running mode, and determine the collision probability based on the first corresponding relationship.

[0129] In an optional embodiment, the prediction module 320 is further configured to predict a first motion trajectory of the biological subject based on the environment information, and predict a first running trajectory of the first vehicle based on the vehicle running information; determine a first time at which the first vehicle reaches a coincidence position and a second time at which the biological subject reaches the coincidence position in response to an overlap between the first motion trajectory and the first running trajectory; and determine that the collision probability is greater than the probability threshold in response to a time length difference between the first time and the second time being less than a preset time length threshold.

[0130] In an optional embodiment, the control module 330 is further configured to determine a first distance between the biological subject and the first vehicle based on the environment information in response to the collision probability being less than or equal to a preset probability threshold; determine a target vehicle speed and a target vehicle deceleration of the first vehicle based on a current vehicle speed of the first vehicle and the first distance; and control the first vehicle to decelerate to the target vehicle speed based on the target vehicle deceleration.

[0131] In an optional embodiment, the vehicle running information includes the current vehicle speed, a vehicle lateral acceleration, a vehicle longitudinal acceleration, a brake pedal position, and an accelerator pedal position.

[0132] The control module 330 is further configured to determine a moving speed of the biological subject based on the environment information.

[0133] The first distance, the moving speed of the biological subject, and the vehicle running information are input into a speed limit equation to determine the target vehicle speed of the first vehicle, the speed limit equation being as follows:

[0134] V = K0*V0+ K1*A1+ K2*A2+ K3*P1+ K4*P2+ K5*V1+ K6*D;

[0135] wherein V is the target vehicle speed of the first vehicle, V0 is the current vehicle speed of the first vehicle, A1 is the vehicle lateral acceleration of the first vehicle, A2 is the vehicle longitudinal acceleration of the first vehicle, P1 is a braking parameter determined based on the brake pedal position, P2 is an acceleration parameter determined based on the accelerator pedal position, V1 is the moving speed of the biological subject, D is the first distance, K0, K1, K2, K3, K4, K5, K6 are preset coefficients, the preset coefficients are real numbers; the target vehicle deceleration is determined based on the current vehicle speed, the target vehicle speed and the first distance of the first vehicle.

[0136] In summary, the control device of the vehicle provided in the present application can predict the probability of a collision event between the vehicle and the pedestrian during the driving of the vehicle, decelerate or emergency brake the vehicle according to the predicted probability of the collision event, avoid the collision between the vehicle and the pedestrian, and effectively reduce the rear-end collision accident caused by the distraction of the driver. When there is a pedestrian in the forward direction of the vehicle, the probability of collision is low, and the vehicle is still decelerated. Compared with the related art in which the vehicle is braked only when the distance between the vehicle and the pedestrian is short, the probability of the collision accident caused by the emergency braking of the vehicle in the extreme weather can be reduced, and the safety of the driver is ensured.

[0137] It should be noted that the control device of the vehicle provided in the above embodiments is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the control device of the vehicle and the control method of the vehicle provided in the above embodiments belong to the same concept, and the specific implementation process is described in detail in the method embodiments, which will not be described here.

[0138] Figure 4 A structural block diagram of a computer device 400 provided in an example embodiment of the present application is shown. The computer device 400 can be a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a notebook computer or a desktop computer. The computer device 400 can also be referred to as a user device, a portable terminal, a laptop terminal, a desktop terminal, and other names.

[0139] Generally, the computer device 400 includes a processor 401 and a memory 402.

[0140] The processor 401 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 401 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), a PLA (Programmable Logic Array). The processor 401 can also include a main processor and a coprocessor, the main processor being a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit), and the coprocessor being a low-power processor for processing data in a standby state. In some embodiments, the processor 401 can be integrated with a GPU (Graphics Processing Unit) for rendering and drawing content required to be displayed by a display screen. In some embodiments, the processor 401 can further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

[0141] The memory 402 can include one or more computer-readable storage media that can be non-transitory. The memory 402 can also include a high-speed random access memory, and a nonvolatile memory such as one or more disk storage devices, flash storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 402 is used to store at least one instruction for being executed by the processor 401 to implement the control method of the vehicle provided by the method embodiments in the present application.

[0142] In some embodiments, the computer device 400 further includes other components, which can be understood by those skilled in the art, Figure 4 The structure shown in FIG. 4 is not a limitation on the computer device 400, and can include more or fewer components than shown, or combine certain components, or use different arrangements of components.

[0143] Optionally, the computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a solid state disk (SSD), an optical disk, or the like. The random access memory can include a resistance random access memory (ReRAM) and a dynamic random access memory (DRAM). The above-mentioned application embodiment numbers are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0144] The application further provides a computer device, including a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement the control method of the vehicle according to any one of the above-mentioned embodiments of the application.

[0145] The application further provides a computer readable storage medium, the storage medium storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by a processor to implement the control method of the vehicle according to any one of the above-mentioned embodiments of the application.

[0146] The application further provides a computer program product or a computer program, including computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to make the computer device execute the control method of the vehicle according to any one of the above-mentioned embodiments.

[0147] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by a program instructing related hardware to complete, and the program can be stored in a computer readable storage medium. The storage medium mentioned above can be a read only memory, a magnetic disk or an optical disk, etc.

[0148] The above-mentioned is only the optional embodiment of the application, and does not limit the application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the application should be included in the protection scope of the application.

Claims

1. A control method of a vehicle, characterized by, The method comprises: collecting environment information of a target road on which a first vehicle travels and vehicle operation information, the environment information being used to indicate a road condition of the target road and a case that a biological subject exists on the target road, and the vehicle operation information comprising vehicle speed information and a travel direction of the first vehicle; in the case that the biological subject exists on the target road, inputting the environment information and the vehicle operation information into a pre-trained machine learning network to determine a predicted operation mode of the first vehicle in a future time period, a starting time point of the future time period being a current time point, and the predicted operation mode being used to indicate a travel condition of the first vehicle in the future time period; determining a collision probability of a collision event between the first vehicle and the biological subject based on the predicted operation mode and the environment information; in response to the collision probability belonging to a first probability interval, controlling the first vehicle to travel at a reduced speed; in response to the collision probability belonging to a second probability interval, controlling the first vehicle to stop traveling, wherein a value of the first probability interval is smaller than a value of the second probability interval.

2. The method of claim 1, wherein, The determination of the collision probability based on the predicted operation mode and the environment information comprises: obtaining a probability reference table, the probability reference table comprising a plurality of corresponding relationships between a plurality of vehicle operation modes and the collision probability, and the plurality of corresponding relationships comprising a first corresponding relationship; screening the first corresponding relationship from the probability reference table based on the environment information and the predicted operation mode, and determining the collision probability based on the first corresponding relationship.

3. The method of claim 1, wherein, The method further comprises: predicting a first motion trajectory of the biological subject based on the environment information, and predicting a first operation trajectory of the first vehicle based on the vehicle operation information; in response to an overlap existing between the first motion trajectory and the first operation trajectory, determining a first time point at which the first vehicle arrives at an overlapping position and a second time point at which the biological subject arrives at the overlapping position; in response to a time length difference between the first time point and the second time point being smaller than a preset time length threshold, determining that the collision probability is greater than a probability threshold.

4. The method according to any one of claims 1 to 3, characterized in that, The control of the first vehicle to travel at a reduced speed in response to the collision probability belonging to the first probability interval comprises: in response to the collision probability being smaller than or equal to a preset probability threshold, determining a first distance between the biological subject and the first vehicle based on the environment information; determining a target vehicle speed and a target vehicle deceleration of the first vehicle based on a current vehicle speed of the first vehicle and the first distance; and controlling the first vehicle to travel at the target vehicle speed based on the target vehicle deceleration.

5. The method of claim 4, wherein, The vehicle operation information comprises the current vehicle speed, a vehicle lateral acceleration, a vehicle longitudinal acceleration, a brake pedal position, and an accelerator pedal position. The determination of the target vehicle speed and the target vehicle deceleration of the first vehicle based on the current vehicle speed of the first vehicle and the first distance comprises: determining a moving speed of the biological subject based on the environment information; inputting the first distance, the moving speed of the biological subject and the vehicle running information into a speed limit equation to determine a target speed of the first vehicle, the speed limit equation being as follows: V=K0*V0+K1*A1+K2*A2+K3*P1+K4*P2+K5*V1+K6*D; wherein V is the target speed of the first vehicle, V0 is the current speed of the first vehicle, A1 is the vehicle lateral acceleration of the first vehicle, A2 is the vehicle longitudinal acceleration of the first vehicle, P1 is a braking parameter determined based on the brake pedal position, P2 is an acceleration parameter determined based on the accelerator pedal position, V1 is the moving speed of the biological subject, D is the first distance, K0, K1, K2, K3, K4, K5, K6 are preset coefficients, and the preset coefficients are real numbers; determining a target vehicle deceleration based on the current speed of the first vehicle, the target speed and the first distance.

6. A control device of a vehicle characterized by comprising: The device comprises: a collection module configured to collect environmental information and vehicle running information of a target road on which a first vehicle travels, the environmental information being used to indicate road conditions of the target road and a situation that a biological subject exists on the target road, and the vehicle running information comprising vehicle speed information and a travel direction of the first vehicle; a prediction module configured to input the environmental information and the vehicle running information into a pre-trained machine learning network to determine a predicted running mode of the first vehicle in a future time period under the situation that the biological subject exists on the target road, a starting time of the future time period being a current time, the predicted running mode being used to indicate a travel situation of the first vehicle in the future time period, and determine a collision probability of a collision event between the first vehicle and the biological subject based on the predicted running mode and the environmental information; a control module configured to control the first vehicle to travel at a deceleration in response to the collision probability belonging to a first probability interval; the control module is further configured to control the first vehicle to stop traveling in response to the collision probability belonging to a second probability interval, wherein a value of the first probability interval is less than a value of the second probability interval.

7. A computer device, comprising: The computer device comprises a processor and a memory, and the memory stores at least one program, which is loaded and executed by the processor to implement the control method of the vehicle according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The storage medium stores at least one program, which is loaded and executed by the processor to implement the control method of the vehicle according to any one of claims 1 to 5.

9. A computer program product, characterised in that, The computer program is executed by the processor to implement the control method of the vehicle according to any one of claims 1 to 5.

Images