Autonomous driving method and apparatus, and vehicle

Abstract

An autonomous driving method and apparatus, and a vehicle. The method comprises: acquiring first motion state information, wherein the first motion state information indicates the speed and moving direction of a vehicle; acquiring second motion state information, wherein the second motion state information indicates a position change of a first object; and when it is determined, on the basis of the first motion state information and the second motion state information, that a first duration is less than a duration threshold, controlling the vehicle to move to a first position at a first deceleration, such that the first object passes through a predicted conflict zone, in which the vehicle and the first object are predicted to collide, prior to the vehicle, wherein the first duration is a difference between a duration required for the vehicle to move to the conflict zone and a predicted duration required for the first object to pass through the conflict zone, and the first position is a position between the current position of the vehicle and a boundary of the conflict zone adjacent to the current position. The technical solution can be applied to the field of intelligent driving of vehicles, and can take into account both driving safety and traffic efficiency when a vehicle yields to vulnerable road users.

Description

Autonomous driving methods, devices and vehicles

[0001] This application claims priority to Chinese Patent Application No. 202411938911.9, filed on December 24, 2024, entitled "Autonomous Driving Method, Apparatus and Vehicle", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of intelligent driving, and more specifically, to an autonomous driving method, device, and vehicle. Background Technology

[0003] Compared to motor vehicles, pedestrians and non-motorized vehicles are more vulnerable road users. In the event of a collision between a pedestrian / non-motorized vehicle and a motor vehicle, the pedestrian / non-motorized vehicle user often suffers more severe injuries. Giving way to vulnerable road users is a necessary measure to ensure the safe crossing of streets by pedestrians and non-motorized vehicles and to create a safe and orderly road traffic environment.

[0004] With the rapid development of the automotive industry, many driver assistance and autonomous driving technologies have emerged, which can reduce driving stress and improve safety and traffic efficiency. However, current autonomous driving technologies make decisions that are either too aggressive or too conservative when yielding to vulnerable road users, resulting in poor vehicle safety or low traffic efficiency. Summary of the Invention

[0005] This application provides an autonomous driving method, device, and vehicle that can balance driving safety and traffic efficiency when the vehicle yields to vulnerable road users.

[0006] In one aspect, an autonomous driving method is provided, which can be executed by a vehicle, for example, by the vehicle's computing platform, or by chips or circuits used in the vehicle.

[0007] The method includes: acquiring first motion state information, which indicates the vehicle's speed and direction of motion; acquiring second motion state information, which indicates the position change of a first object; and when a first duration is determined to be less than a duration threshold based on the first and second motion state information, controlling the vehicle to travel towards a first position with a first deceleration, so that the first object passes through the conflict area before the vehicle; wherein, the conflict area is the area where the vehicle and the first object are predicted to collide, the first duration is the difference between the time required for the vehicle to travel to the conflict area and the predicted time required for the first object to pass through the conflict area, and the first position is the position between the vehicle's current position and the first boundary of the conflict area, the first boundary being the boundary between the conflict area and the nearest neighbor of the current position.

[0008] It should be noted that "controlling the vehicle to move towards the first position with a first deceleration so that the first object passes through the conflict area before the vehicle" can correspond to the following situations: First, the first object passes through the conflict area while the vehicle is moving towards the first position; second, the first object passes through the conflict area when the vehicle stops at the first position; third, if the first object stops moving or moves slowly while the vehicle is moving towards the first position with the first deceleration or stops at the first position, the vehicle can also pass through the conflict area before the first object.

[0009] In the above technical solution, the difference between the time required for the vehicle to travel to the conflict area and the time required for the first object to pass through the conflict area is less than a certain threshold. Furthermore, when the vehicle decides to yield to the first object, it can plan its speed based on the boundary closest to the conflict area and the vehicle's current position. This avoids excessive deceleration during yielding, which could cause discomfort to the vehicle's occupants. It also prevents the vehicle from entering the conflict area and colliding with the first object due to delayed braking. Additionally, it avoids overly conservative driving that would result in slow traffic. Therefore, it can balance driving safety and traffic efficiency during the yielding process.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: during the process of controlling the vehicle to move toward the first position at a first deceleration, when it is determined that the first duration is greater than or equal to a duration threshold, controlling the vehicle to pass through the conflict area at a first speed, wherein the first speed is determined based on the first deceleration.

[0011] In some implementations, controlling the vehicle to travel towards a first position with a first deceleration includes: setting a virtual wall at the first position, indicating that the vehicle cannot cross the first position; determining a first deceleration based on the virtual wall and the vehicle's current speed, such a first deceleration prevents the vehicle from crossing the virtual wall; and then controlling the vehicle to travel towards the first position with the first deceleration. In this case, during the process of controlling the vehicle to travel towards the first position with the first deceleration, if it is determined that a first duration is greater than or equal to a duration threshold, the virtual wall is canceled, and the vehicle is controlled to pass through the conflict area at the first speed. The virtual wall can be a series of parameters used to control the vehicle that are not physically present.

[0012] The first speed is determined based on the first deceleration, which can be understood as: the vehicle decelerates from a certain speed to the first speed through the first deceleration, or the vehicle decelerates from a certain speed to a certain speed through the first deceleration and then accelerates to the first speed.

[0013] In some implementations, while controlling the vehicle to pass through the conflict zone at a first speed, the vehicle's prompting device can be controlled to display information indicating that the vehicle is in a non-yielding state under autonomous driving mode.

[0014] In the above technical solution, when the speed of the first object changes to the point that the vehicle no longer needs to yield to the first object during the process of the vehicle moving to the first position, the yielding process can be terminated. This helps to improve the vehicle's traffic efficiency, reduce the probability of the vehicle being warned or urged by the vehicle behind, and improve the human-likeness and intelligence of the vehicle in the autonomous driving state.

[0015] In conjunction with the first aspect, in some implementations of the first aspect, the first deceleration causes the vehicle to stop at the first position. The method further includes: controlling the vehicle to travel along a first path when the position change of the first object is less than or equal to a displacement threshold within a second time period calculated from the first moment; wherein the first moment is a moment in the process of the vehicle traveling towards the first position, or the first moment is the moment when the vehicle stops at the first position, and the first path is planned according to the position of the first object, and the vehicle can pass through the conflict area before the first object when traveling along the first path.

[0016] In some implementations, if the location of the first object occupies the target lane of the vehicle, then the first path is a path to bypass the first object; if the location of the first object does not occupy the target lane of the vehicle, then the first path can be a straight path.

[0017] In the above technical solution, if the first object is stationary or moving at an extremely slow speed during the driving process of the vehicle, it can be inferred that the first object's intention to pass through the conflict area is not obvious or there is no intention to pass through the conflict area. In this case, the yielding process can be terminated, and the vehicle can be controlled to pass through the conflict area before the first object. This helps to improve the vehicle's traffic efficiency, reduce the probability of the vehicle being warned or urged by the vehicle behind, and improve the human-likeness and intelligence of the vehicle in the autonomous driving state.

[0018] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: controlling the vehicle's prompting device to prompt first information during a second duration, the first information being used to prompt the first object that the vehicle is in a yielding state.

[0019] In the above technical solution, the vehicle is prompted to yield to the first object, making the first object aware of the vehicle's intention to yield and reducing the probability of the first object and the vehicle "stopping at the same time" (e.g., both intending to yield to each other). Furthermore, if the first object's intention to pass through the conflict area is unclear or nonexistent after being prompted to yield, the vehicle is controlled to pass through the conflict area before the first object. In this case, the reliability of the vehicle's decisions can be improved, thereby enhancing the driving experience for the vehicle's users and their trust in the autonomous driving system.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, the first information includes at least one of the following projected in front of the vehicle: a zebra crossing image, an image indicating passage, and text indicating passage.

[0021] In some implementations, "front of the vehicle" can be understood as the direction in which the vehicle is traveling.

[0022] In some implementations, the first information can be an image and / or text projected in front of the first object.

[0023] In the above technical solution, projecting relevant prompts in front of the vehicle helps increase the probability that the first object will receive the relevant prompts, thereby improving the effectiveness of the prompts.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: controlling the vehicle's prompting device to prompt second information from a second moment, the second information indicating that the vehicle is in a non-yielding state under autonomous driving mode; the second moment is the end moment of the second duration.

[0025] In the above technical solution, when a vehicle tries to overtake a first object, it alerts the first object that the vehicle is in a non-yielding state. This reduces the probability of the first object and the vehicle "starting at the same time" (such as both intending to overtake each other), thereby reducing the risk of a collision between the vehicle and the first object and improving the vehicle's driving safety.

[0026] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: deducing a predicted motion path of the first object at different speeds and / or accelerations based on the second motion state information; deducing a planned driving path of the vehicle at different speeds and / or accelerations based on the first motion state information; and controlling the vehicle to move toward the first position with a first deceleration, including: when it is deduced from the predicted motion path and the planned driving path that the first object can pass through the conflict area before the vehicle, and when it is determined from the first motion state information and the second motion state information that the first duration is less than a duration threshold, controlling the vehicle to move toward the first position with a first deceleration.

[0027] In the above technical solution, when it is deduced that the vehicle can yield to the first object, and the difference between the time required for the vehicle to travel to the conflict area and the time required for the first object to pass through the conflict area is less than a certain threshold, controlling the vehicle to travel to the first position with a first deceleration and yield to the first object helps to improve the driving safety of the vehicle.

[0028] In conjunction with the first aspect, in some implementations of the first aspect, controlling the vehicle to travel toward the first position with a first deceleration includes: controlling the vehicle to travel toward the first position with a first deceleration when the vehicle is traveling with a second deceleration and can stop at or before the first position, and the first duration is less than a duration threshold.

[0029] In the above technical solution, the yielding procedure is executed only when it is determined that the vehicle can stop in front of the conflict zone. This helps to improve the comfort of the passengers and can prevent the vehicle from stopping inside the conflict zone, thereby improving the driving safety of the vehicle.

[0030] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: in the previous frame of the current frame, when the vehicle is traveling toward the first position with a third deceleration and is able to stop at or before the first position, in the current frame, the path of the vehicle continuing to travel toward the first position with a second deceleration is deduced, wherein the absolute value of the third deceleration is less than or equal to the absolute value of the second deceleration.

[0031] In the above technical solution, when the vehicle is deduced to stop at or before the first position with the third deceleration in the previous frame, the vehicle's driving path is deduced in the current frame with a smaller deceleration (larger absolute value). This avoids the situation where the planning is unstable due to the lack of virtual walls in the current frame caused by unreasonable deceleration settings, and helps to improve the stability and reliability of the vehicle's autonomous driving system.

[0032] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: during the process of controlling the vehicle to move toward the first position at a first deceleration, a prompting device controlling the vehicle prompts third information, the third information being used to prompt the first object that the vehicle is in a yielding state.

[0033] In the above technical solution, when the vehicle begins to execute the yielding strategy, it prompts the first object that the vehicle is in a yielding state. When the first object intends to pass through the conflict area, it helps the first object to pass through the conflict area more quickly, thereby enabling the vehicle to pass through the conflict area more efficiently. When the first object does not intend to pass through the conflict area, it helps the vehicle to make a faster decision to give way, thereby improving driving efficiency.

[0034] In a second aspect, an autonomous driving device is provided, comprising an acquisition unit and a processing unit, wherein the acquisition unit is configured to: acquire first motion state information, the first motion state information indicating the speed and direction of motion of a vehicle; the acquisition unit is further configured to: acquire second motion state information, the second motion state information indicating the position change of a first object; the processing unit is configured to: when a first duration is determined to be less than a duration threshold based on the first motion state information and the second motion state information, control the vehicle to travel towards a first position with a first deceleration, so that the first object passes through a conflict area before the vehicle; wherein the conflict area is the area where the vehicle and the first object are predicted to collide, the first duration is the difference between the time required for the vehicle to travel to the conflict area and the predicted time required for the first object to pass through the conflict area; the first position is the position between the current position of the vehicle and the first boundary of the conflict area, the first boundary being the boundary between the conflict area and the nearest neighbor of the current position.

[0035] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: when determining that the first duration is greater than or equal to a duration threshold while controlling the vehicle to move toward the first position at a first deceleration, control the vehicle to pass through the conflict zone at a first speed, wherein the first speed is determined based on the first deceleration.

[0036] In conjunction with the second aspect, in some implementations of the second aspect, the first deceleration causes the vehicle to stop at the first position, and the processing unit is further configured to: control the vehicle to travel along the first path when the position change of the first object is less than or equal to a displacement threshold within a second time period calculated from the first moment; wherein the first moment is a moment in the process of the vehicle traveling towards the first position, or the first moment is the moment when the vehicle stops at the first position, and the first path is planned according to the position of the first object, and the vehicle can pass through the conflict area before the first object when traveling along the first path.

[0037] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: control the vehicle's prompting device to display first information within a second duration, the first information being used to indicate to the first object that the vehicle is in a yielding state.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, the first information includes at least one of the following projected in front of the vehicle: a zebra crossing image, an image indicating passage, or text indicating passage.

[0039] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: control the vehicle's prompting device to prompt second information from the second moment, the second information indicating that the vehicle is in a non-yielding state under autonomous driving mode; the second moment is the end moment of the second duration.

[0040] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: deduce the predicted motion path of the first object at different speeds and / or accelerations based on the second motion state information; deduce the planned driving path of the vehicle at different speeds and / or accelerations based on the first motion state information; and when it is deduced, based on the predicted motion path and the planned driving path, that the first object can pass through the conflict area before the vehicle, and when it is determined, based on the first motion state information and the second motion state information, that the first duration is less than a duration threshold, control the vehicle to move towards the first position with a first deceleration.

[0041] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is configured to: control the vehicle to move toward the first position with a first deceleration when the vehicle is able to stop at or before the first position while traveling at a second deceleration and the first duration is less than a duration threshold.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: in the previous frame of the current frame, if the vehicle is traveling toward the first position with a third deceleration and is able to stop at or before the first position, in the current frame, calculate the path for the vehicle to continue traveling toward the first position with a second deceleration, wherein the absolute value of the third deceleration is less than or equal to the absolute value of the second deceleration.

[0043] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: during the process of controlling the vehicle to move toward the first position at a first deceleration, control the vehicle's prompting device to prompt third information, the third information being used to prompt the first object that the vehicle is in a yielding state.

[0044] Thirdly, an autonomous driving device is provided, the device comprising: a processor for executing a computer program stored in the memory, such that the device performs the method in any possible implementation of the first aspect described above.

[0045] In conjunction with the third aspect, in some implementations of the third aspect, the device also includes a memory.

[0046] Fourthly, a computer program product is provided, comprising: computer program code, which, when executed on a computer or processor, causes the computer or processor to perform the method in any possible implementation of the first aspect.

[0047] It should be noted that the above computer program code can be stored in whole or in part on a storage medium, which can be packaged together with the processor or packaged separately from the processor.

[0048] Fifthly, a computer-readable storage medium is provided, the computer-readable medium storing instructions that, when executed by a processor, cause the processor to implement the method in any possible implementation of the first aspect.

[0049] In a sixth aspect, a chip is provided that includes circuitry for performing the method in any of the possible implementations of the first aspect described above.

[0050] In a seventh aspect, a vehicle is provided that includes means as in any possible implementation of the second or third aspect, or the vehicle includes a computer-readable storage medium as in any possible implementation of the fifth aspect, or the vehicle includes a chip as in any possible implementation of the sixth aspect, or the vehicle is loaded with a computer program product as in any possible implementation of the fourth aspect.

[0051] In conjunction with the seventh aspect, in some implementations of the seventh aspect, the vehicle is a vehicle in a broad sense, such as a means of transportation (e.g., commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (e.g., forklifts, trailers, tractors, etc.), engineering vehicles (e.g., excavators, bulldozers, cranes, etc.), agricultural equipment (e.g., lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc. In practical implementation, the vehicle can also be a road vehicle, a water vehicle, an air vehicle, industrial equipment, agricultural equipment, or other intelligent driving equipment such as entertainment equipment.

[0052] For the beneficial effects not described in detail in aspects two through seven, please refer to the description in aspect one, which will not be repeated here. Attached Figure Description

[0053] Figure 1 is a functional block diagram of the vehicle provided in an embodiment of this application;

[0054] Figure 2 is a schematic diagram of the autonomous driving system architecture provided in an embodiment of this application;

[0055] Figure 3 is a schematic flowchart of the autonomous driving method provided in an embodiment of this application;

[0056] Figure 4 is a schematic diagram of the application scenarios involved in the embodiments of this application;

[0057] Figure 5 is another schematic diagram of the application scenario involved in the embodiments of this application;

[0058] Figure 6 is another schematic diagram of the application scenario involved in the embodiments of this application;

[0059] Figure 7 is another schematic diagram of the application scenario involved in the embodiments of this application;

[0060] Figure 8 is a schematic diagram of an information prompting scenario according to an embodiment of this application;

[0061] Figure 9 is another schematic diagram of an information prompting scenario involved in an embodiment of this application;

[0062] Figure 10 is another schematic diagram of a scenario involving information prompting according to an embodiment of this application;

[0063] Figure 11 is another schematic flowchart of the autonomous driving method provided in the embodiments of this application;

[0064] Figure 12 is a schematic block diagram of an autonomous driving device provided in an embodiment of this application;

[0065] Figure 13 is another schematic block diagram of the autonomous driving device provided in the embodiments of this application. Detailed Implementation

[0066] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0067] Figure 1 is a functional block diagram of a vehicle provided in an embodiment of this application. As shown in Figure 1, the vehicle 100 may include a perception system 120, a prompting device 130, and a computing platform 150. The perception system 120 may include several sensors for sensing information about the surrounding environment of the vehicle 100. For example, the perception system 120 may include a positioning system, which may be a Global Positioning System (GPS), a BeiDou system, or other positioning systems. As another example, the perception system 120 may also include one or more of the following: an inertial measurement unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0068] The prompting device 130 may include any of the following: a display device, a sound device, and a lighting device. The display device is mainly divided into two categories: the first is an in-vehicle display screen; the second is a projection display screen, such as a head-up display (HUD). An in-vehicle display screen is a physical display screen and an important component of the in-vehicle infotainment system. Multiple displays can be installed in the cabin, such as digital instrument cluster displays and central control screens. In some possible implementations, one or more of the aforementioned in-vehicle displays can be human-machine interfaces (HMIs), for example, the central control screen can be an HMI. A head-up display, also known as a head-up display system, is mainly used to display driving information such as speed and navigation on a display device (e.g., the windshield) in front of the driver. This reduces the driver's eye-shifting time, avoids pupil changes caused by eye-shifting, and improves driving safety and comfort. HUDs include, for example, combiner-HUD (C-HUD) systems, windshield-HUD (W-HUD) systems, and augmented reality HUD (AR-HUD) systems. Sound-generating devices may include in-vehicle speakers, in-vehicle audio systems, or external speakers, external audio systems. Lighting devices are used to display lights and may include external vehicle lights, such as headlights and pixelated headlights. More specifically, headlights include one or more of low beam headlights, high beam headlights, and turn signals. In some implementations, the lighting device may include one or more. Pixel-type vehicle lights may include, but are not limited to, lighting devices based on digital light processing (DLP) technology, lighting devices based on micro light emitting diode (Micro-LED) technology, or lighting devices based on liquid crystal display (LCD). Pixel-type vehicle lights can be used to project specific patterns onto the ground or buildings around the vehicle to alert other road users to relevant information.

[0069] Some or all of the functions of vehicle 100 can be controlled by computing platform 150. Computing platform 150 may include processors 151 to 15n. A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement related functions. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include a memory for storing instructions. Some or all of the processors 151 to 15n can call the instructions in the memory to implement the corresponding functions.

[0070] The computing platform 150 can control the operation of the intelligent driving system, which may include an advanced driving assistance system (ADAS) and an autonomous driving system (ADS). The intelligent driving system utilizes various sensors on the vehicle (including but not limited to: LiDAR, millimeter-wave radar, cameras, ultrasonic sensors, GPS, and inertial measurement units) to acquire information from the vehicle's surroundings, and analyzes and processes this information to achieve functions such as obstacle perception, target recognition, vehicle localization, path planning, and driver monitoring / alerts, thereby improving the safety, automation, and comfort of driving the vehicle.

[0071] At different levels of autonomous driving (or intelligent driving levels, ranging from L0 to L5, totaling six levels), intelligent driving systems can achieve different levels of automated driving assistance based on artificial intelligence algorithms and information acquired by multiple sensors. These levels of autonomous driving are based on the classification standards of the Society of Automotive Engineers (SAE). Specifically, L0 is no automation; L1 is driver assistance; L2 is partial automation; L3 is conditional automation; L4 is high automation; and L5 is full automation. At levels L1 to L3, the task of monitoring road conditions and reacting is jointly completed by the driver and the system, requiring the driver to take over dynamic driving tasks. Levels L4 and L5 allow the driver to completely transform into a passenger. Currently, the functions that intelligent driving systems can achieve mainly include, but are not limited to: adaptive cruise control, automatic emergency braking, automatic parking, blind spot monitoring, forward cross-traffic alert / braking, rear cross-traffic alert / braking, forward collision warning, lane departure warning, lane keeping assist, rear collision warning, traffic sign recognition, traffic jam assist, and highway assist. It should be understood that the above-mentioned functions can have specific modes at different levels of autonomous driving (L0-L5). The higher the level of autonomous driving, the more intelligent the corresponding mode.

[0072] The roles of the perception system 120, the prompting device 130, and the computing platform 150 in this application are explained in detail below with reference to Figure 2. Figure 2 shows a schematic block diagram of the autonomous driving system architecture provided in an embodiment of this application. The system includes a perception module 210, a control module 220, and a prompting module 230. Wherein:

[0073] The perception module 210 may include one or more camera devices in the perception system 120 shown in Figure 1, or it may also include one or more radars in the perception system 120. The perception module 210 is used to collect information about the vehicle's surrounding environment, the vehicle's real-time motion parameters, etc. The perception module 210 can also process the collected surrounding environment information to build a world model of roads, obstacles, etc. for downstream modules (such as the planning and control module 220).

[0074] The planning and control module 220 may include one or more processors in the computing platform 150 shown in Figure 1. Specifically, the planning and control module 220 may include an interaction decision module 221, a motion planning module 222, and a control module 223. The interaction decision module 221 is used to filter target objects that have an interactive relationship with the vehicle based on changes in the position of the interactive objects. An interactive relationship between the target object and the vehicle can be understood as: the target object may affect the vehicle's driving path, or the vehicle may affect the target object's driving path. The interaction decision module 221 can also set a virtual wall between the vehicle and the target object based on the relative distance between them, and calculate the deceleration of the vehicle as it moves towards the virtual wall. The virtual wall indicates a position that the vehicle cannot cross during its journey. Furthermore, when the interactive relationship between the vehicle and the target object is eliminated, the interaction decision module 221 cancels the virtual wall. The interactive decision module 221 can send the virtual wall setting result to the motion planning module 222. The virtual wall setting result indicates whether a virtual wall has been set, or, if a virtual wall has been set, the setting result can indicate the parameters of the virtual wall, such as the distance between the virtual wall and the vehicle. The motion planning module 222 can plan the path for the vehicle to travel towards the virtual wall based on the virtual wall setting result. The control module 223 controls the vehicle to decelerate or drive normally based on the path planned by the motion planning module 222. Normal driving can be understood as: planning the vehicle's path to the target location while ignoring the influence of the target object on the vehicle, and controlling the vehicle to travel along the path. During normal driving, the vehicle may maintain its current speed, or it may accelerate or decelerate. When the virtual wall setting result indicates the virtual wall's parameters, the motion planning module 222 can plan the vehicle's deceleration based on the vehicle's current speed and the position of the virtual wall. When the vehicle performs this deceleration, it can stop at the virtual wall.

[0075] The prompting module 230 may include one or more of the prompting devices 130 shown in FIG1. ​​The prompting module 230 may prompt the target object with relevant information that the vehicle is yielding when the vehicle yields to the target object; the prompting module 230 may also prompt the target object that the vehicle is in a normal driving state when the vehicle decides not to yield to the target object.

[0076] It should be understood that the above module is only an example, and in actual applications, the above module may be added or deleted according to actual needs.

[0077] The above describes the autonomous driving system architecture provided in the embodiments of this application. The following details the process of implementing the autonomous driving method provided in the embodiments of this application based on the autonomous driving system shown in Figure 2.

[0078] Figure 3 shows a schematic flowchart of an autonomous driving method provided in an embodiment of this application. This method 300 can be applied to the vehicle shown in Figure 1, or it can be executed by the system shown in Figure 2. More specifically, this method 300 can be executed by the control module 220, and it may include some or all of the steps in S301 to S306 below.

[0079] S301, Obtain motion state information, which indicates the position change of at least one interactive object.

[0080] For example, motion state information can be determined based on images and / or point cloud data acquired by the vehicle's perception system. For instance, the positional changes of interactive objects can be determined based on multiple frames of images and / or point cloud data. At least one interactive object may include a stationary object or a moving object.

[0081] For example, interactive objects may include pedestrians, or they may also include non-motorized vehicles such as electric vehicles and bicycles.

[0082] S302, based on motion state information, select target objects that have an interactive relationship with the vehicle from at least one interactive object.

[0083] In some implementations, the motion path of each interactive object in at least one interactive object is predicted based on motion state information. Then, based on the predicted motion paths of the interactive objects, interactive objects that satisfy the following conditions (1) to (3) are determined to have an interactive relationship with the vehicle. These interactive objects are then selected as target objects:

[0084] (1) The predicted motion path of the interactive object and the nearest point between it and the vehicle are within a preset range of the vehicle. For example, the preset range can be a range in which the distance between the object and the vehicle in the horizontal direction is less than or equal to a distance threshold 1, and the distance between the object and the vehicle in the vertical direction is less than or equal to a distance threshold 2.

[0085] The horizontal and vertical axes can be determined relative to the vehicle's direction of travel or the vehicle's coordinate system. For example, the vertical axis can be parallel to the vehicle's direction of travel, and the horizontal axis can be perpendicular to the vehicle's direction of travel. Alternatively, the vertical axis can be parallel to the X-axis of the vehicle's coordinate system, and the horizontal axis can be parallel to the Y-axis of the vehicle's coordinate system. It should be noted that the origin O of the vehicle coordinate system can be located at the projection point of the rear axle center onto the ground. The positive directions of the X and Z axes can be the direction of the vehicle's front end and the direction perpendicular to the vehicle's plane, respectively.

[0086] For example, distance threshold 1 can be a value between 1 meter and 1.5 meters, distance threshold 2 can be a value between 50 meters and 150 meters, or distance threshold 1 and distance threshold 2 can be other values.

[0087] (2) The predicted proportion of the lateral velocity component of the interactive object is greater than the velocity component threshold. For example, the relationship between the proportion of the lateral velocity component and the velocity component threshold of the interactive object can satisfy the following formula (a):

[0088] Where abs() represents taking the absolute value, v oy v represents the lateral component of the current velocity of the interactive object. ox Thre represents the vertical component of the current velocity of the interactive object. vR This represents the velocity component threshold. For example, the velocity component threshold can be a value between 0.3 and 0.4, or it can be other values.

[0089] (3) The difference between the longitudinal collision time (TTC) between the vehicle and the interactive object and the time required for the interactive object to move out of the collision area is less than the time threshold, specifically satisfying the following formulas (b) to (d): (ttc eo -ttl o ) <Thre oNo (b)

[0090] Among them, TTC eo This indicates the collision time between the vehicle and the interacting object in the longitudinal direction; ttl o This represents the time required for the interactive object to move from its current position to leave the conflict zone. The conflict zone is the area where the vehicle's driving path and the interactive object's predicted path overlap. For example, the conflict zone could be region 1, region 2, or region 3, as shown by the shaded area in Figure 4. oNoThis represents a time threshold, which can be a value between 0.5 seconds and 1 second, or other values. eo This represents the longitudinal distance between the vehicle and the interacting object at the current moment. For example, if the vehicle is traveling forward in a straight line, the aforementioned longitudinal distance can be the distance between points A and C, as shown in Figure 4. e Indicates the current speed of the vehicle; dist oy This represents the lateral distance that an interactive object needs to move from its current position to leave the conflict area, such as the distance between points B and D as shown in Figure 4. Alternatively, it can be the distance between points B and D plus a certain distance threshold, where the distance threshold can be 1 to 2 meters, or other values.

[0091] It should be noted that when the interactive object moves longitudinally in a direction away from the vehicle (e.g., the interactive object moves along the predicted path 1 in Figure 4), v ox It is a positive number; when the interactive object moves longitudinally towards the direction closer to the vehicle (such as when the interactive object moves along the predicted path 2 of the interactive object in Figure 4), v ox It is negative; when the direction of motion of the interactive object is perpendicular to the direction of travel of the vehicle (such as when the interactive object moves along the predicted path 3 of the interactive object in Figure 4), v ox It is 0.

[0092] In some other implementations, when the motion states of the vehicle and the interactive object satisfy the aforementioned conditions (1) to (3), and it is determined that the vehicle can yield to the interactive object, the interactive object is identified as the target object. For example, based on the different accelerations of the vehicle and the interactive object, the lateral and longitudinal paths of the vehicle, as well as the lateral and longitudinal paths of the interactive object, are deduced respectively. The lateral path includes the shape of the offset path curve; the longitudinal path includes the relationship between the longitudinal distances at corresponding times. Finally, multiple sets of deduced paths with time information are generated based on the lateral and longitudinal paths.

[0093] For example, the lateral path of a vehicle can be derived using the following formula (e):

[0094] Among them, s e This is the longitudinal position (in meters) of the vehicle at the moment of lateral path calculation, and this position changes with the calculation time. l(s) e ) is the longitudinal position s of the vehicle. e Corresponding lateral offset (unit: m); s eST is the starting position of the vehicle's longitudinal direction (unit: m). This starting position can be understood as the vehicle's position in the direction parallel to the X-axis of the vehicle coordinate system at the moment the path calculation begins; C1 is the offset corresponding to the vehicle's current orientation (unit: m); s e CT is the longitudinal position at the end of the cubic curve connection (unit: m); C2 is the lateral offset at the end of the cubic curve connection (unit: m), where C2 can be the preset minimum or maximum lateral offset of the vehicle during the simulation; s e ST and s e CT can dynamically adjust based on the vehicle's model and level of aggression. For example, when the vehicle is a large vehicle, s e ST and s e When the CT value is large; and / or the vehicle's aggression is high, s e ST and s e The CT value is relatively small. From (s) e ST,C1) to (s e CT,C2) uses cubic curves to connect paths, and the cubic curves are in (s e ST,C1) and (s e The tangent at CT,C2) is parallel to the vehicle's direction of travel. Here, a, b, c, and d are the coefficients of a cubic polynomial, and their specific values ​​can be determined based on the vehicle's model and aggression level.

[0095] During the longitudinal path simulation of the vehicle, the change in longitudinal acceleration of the vehicle over the simulation time may include at least one of the following four segments: (1) Delay segment (t∈[0,delayTime)): longitudinal path simulation is performed based on the current acceleration of the vehicle; (2) Uniform acceleration rate of change segment (t∈[delayTime,jerkChangeTime), hereinafter referred to as uniform Jerk segment): the acceleration rate of change is determined based on the acceleration at the beginning of the uniform Jerk segment and the simulation acceleration, and longitudinal path simulation is performed according to uniform Jerk; (3) Uniform acceleration segment (t∈[jerkChangeTime,speedLimitTime)): path simulation is performed while maintaining the simulation acceleration; (4) Uniform speed segment (t≥speedLimitTime): when the simulation speed reaches the upper or lower bound speed, the path simulation is performed while maintaining the upper or lower bound speed. It should be noted that the above uniform Jerk segment can be a process of linearly increasing acceleration or a process of linearly decreasing acceleration. Among them, the simulation acceleration can be -4m / s². 2 Up to 3m / s 2 One of the values. For example, for the same lateral path, the extrapolated acceleration can be taken as -4, -3, -2, -1, 0, 1, 2, and 3 m / s². 2This yields 8 vertical paths, which are then merged with the horizontal paths to obtain 8 derivation paths.

[0096] Furthermore, the motion path of the interactive object can be deduced using the aforementioned method of deriving the lateral and longitudinal paths of the vehicle. The difference is that the deduced acceleration can be taken as -1, 0, and 1 m / s², respectively. 2 .

[0097] After obtaining the projected paths of the interactive object and the vehicle, the decision can be made based on factors such as safety, comfort, and traffic efficiency during the vehicle's journey towards the conflict area. Specifically, the vehicle should either overtake the interactive object (i.e., the vehicle passes through the conflict area before the interactive object) or yield to the interactive object (i.e., the interactive object passes through the conflict area before the vehicle). For example, if the overall evaluation of safety, comfort, and traffic efficiency is better when the vehicle overtakes the interactive object, then the decision is made to overtake the interactive object; if the overall evaluation of safety, comfort, and traffic efficiency is better when the vehicle yields to the interactive object, then the decision is made to yield to the interactive object. Safety can be characterized by the distance (or time difference) between the closest points on the vehicle's projected path and the interactive object's projected path; a larger distance (or time difference) indicates higher safety. Comfort can be characterized by the maximum acceleration (or maximum deceleration) on the projected paths of the vehicle and / or the interactive object; a larger maximum acceleration (or the absolute value of the maximum deceleration) indicates lower comfort.

[0098] S303, Determine if the target object exists.

[0099] Specifically, if a target object exists, S304 is executed for each target object; otherwise, S306 is executed.

[0100] S304, determine whether the vehicle can stop outside the target area.

[0101] Specifically, if the vehicle can stop outside the target area, S305 is executed; otherwise, a lateral avoidance path can be planned to avoid the target object.

[0102] For example, the ability of a vehicle to stop outside the target area can be understood as the ability of the vehicle to stop between its current location and the target area. The target area can be the aforementioned conflict zone, or it can be any other area including the conflict zone.

[0103] In some implementations, the vehicle can generate a virtual zebra crossing based on the predicted path of the target object. The area where this virtual zebra crossing is set can cover the aforementioned conflict area and / or the area traversed by the predicted path. For example, the area covered by the virtual zebra crossing can be considered as the area where the target is located. Further, based on the position of the virtual zebra crossing, it is determined whether the vehicle can brake to a stop outside the area where the target is located. For example, in... When the vehicle can stop outside the virtual zebra crossing, it is determined that s is the minimum distance between the vehicle's current position and the virtual zebra crossing. Alternatively, s can be the minimum distance between the vehicle's current position and the virtual zebra crossing minus a certain threshold, which can be a value between 0.1 meters and 0.3 meters, or other values. dec Let a be the absolute value of the vehicle's deceleration. For example, a dec It can be 3m / s 2 Up to 5m / s 2 One of the values.

[0104] In some implementations, when it is determined that the vehicle can brake to a stop outside the target area, the vehicle can use -a dec A virtual wall is set at the front position of the vehicle that can stop, and the information of the virtual wall is sent to the vehicle's motion planning module 222 so that the motion planning module 222 can plan the longitudinal path and / or lateral path of the vehicle to travel towards the virtual wall based on the position of the virtual wall.

[0105] In some implementations, when deducing in the first frame whether the vehicle can brake to a stop outside the target area, a dec 3m / s can be taken 2 The first frame can be understood as: after identifying the target object, the first determination of whether the vehicle can stop outside the target's area. dec The virtual wall can be increased frame by frame as the simulation progresses. For example, if a virtual wall was set between the conflict zone and the vehicle in the previous frame, the vehicle's path can be planned based on this virtual wall in the frame preceding the current one. Furthermore, when the simulation in the current frame determines whether the vehicle can stop outside the target area, the simulation can be based on a deceleration that is larger in absolute value than the deceleration in the previous frame. If the vehicle can stop, the virtual wall is still set between the conflict zone and the vehicle; otherwise, the virtual wall is removed.

[0106] S305 plans a driving path based on the area where the target object is located, so that the vehicle decelerates and drives towards the area where the target object is located.

[0107] In some implementations, a virtual wall is placed between the vehicle's current location and the virtual zebra crossing, indicating a location the vehicle cannot cross during its journey. Furthermore, planning the driving path based on the area where the target object is located can include: determining the deceleration required for the vehicle to avoid colliding with the virtual wall based on its position and the vehicle's current speed.

[0108] In some other implementations, when the vehicle is moving in the direction it is heading, the driving path is planned based on the area where the target object is located, including: when the vehicle passes through -a dec A virtual wall is set at the front of the car where it can stop, and then the car is controlled by pressing -a. dec Slow down and move toward the area where the target object is located.

[0109] For example, Figure 5 shows the location of the virtual zebra crossing and an example of the relative position between the virtual zebra crossing and the virtual wall. The thickness of the virtual wall can be a value between 0.01 meters and 0.05 meters, or it can be any other value, or in practice, the thickness of the virtual wall can be ignored. The closest distance between the virtual wall and the virtual zebra crossing can be greater than or equal to a threshold 1, which can be a value between 0.1 meters and 0.3 meters, or it can be any other value.

[0110] It should be noted that in real-time implementation, when a vehicle travels along a path planned based on a virtual wall, it may decelerate towards the area where the target object is located, or it may travel at a constant speed towards the target object, or it may accelerate towards the target object. For example, if it is determined that the vehicle can still yield to the target object while traveling at a constant speed or accelerating towards the area where the target object is located when the vehicle speed is relatively slow, then the vehicle can be controlled to travel at a constant speed or accelerating towards the area where the target object is located.

[0111] In some implementations, S302 is executed synchronously during S305, and if no target object is found, the virtual wall is canceled, and S306 is executed. In one example, the relationship between the target object and the vehicle satisfies (ttc) eo -ttl o )≥Thre oNoIn one example, if the target object can pass through the conflict zone before the vehicle reaches the virtual wall, the virtual wall can be canceled (as shown in Figure 6), and S306 can be executed. In another example, if the target object's displacement within a certain time period (e.g., one of 1 to 3 seconds, or other durations) is less than or equal to a displacement threshold (e.g., 5 to 10 centimeters, or other distances), allowing the vehicle to pass through the conflict zone before the target object, then the virtual wall is canceled, and S306 is executed. In a later example, if the target object is located in the vehicle's lane, after canceling the virtual wall, an obstacle avoidance path can be planned based on the target object's position to bypass it, as shown in Figure 7.

[0112] S306 controls the vehicle to travel at its current speed, or controls the vehicle to increase its speed.

[0113] In some implementations, during the process of planning a driving path based on a virtual wall and controlling the vehicle's movement, or when the vehicle stops at the virtual wall location to wait for a target object to pass, the vehicle's prompting device can be controlled to display relevant information indicating that the vehicle is in a yielding state, so that the target object is aware of the vehicle's intention to yield. For example, Figures 8 and 9 illustrate the vehicle's prompting of relevant information indicating that it is in a yielding state. In one example, as shown in Figure 8, during the process of the vehicle moving towards the target object 801, or during the process of the vehicle stopping to wait for the target object 801 to pass through the conflict area, a prompt message 802 can be projected onto the ground using pixelated headlights. This prompt message 802 includes the text "Yielding, please proceed" indicating passage and a pattern indicating the direction of passage. In another example, as shown in Figure 9, during the process of the vehicle moving towards the target object 801, or during the process of the vehicle stopping to wait for the target object 801 to pass through the conflict area, a prompt message 803 can be projected onto the ground using pixelated headlights. This prompt message 803 includes the text "Please proceed" indicating passage and a zebra crossing pattern.

[0114] In some implementations, after the virtual wall is canceled, the vehicle's warning device can be controlled to indicate that the vehicle is in a non-yielding state, so that the target object is aware of the vehicle's intention. For example, as shown in Figure 10, when the vehicle sets up a virtual wall based on the target object 901 and is driving towards the virtual wall, if it is determined that the displacement of the target object within a certain period of time is less than or equal to a displacement threshold, the virtual wall is canceled, and a warning message 902 is projected onto the ground through pixel-type headlights. This warning message 902 includes the text "Normal driving, please yield" instructing the target object to give way, as well as a warning pattern.

[0115] It is understood that when the vehicle is projecting the prompt information shown in Figure 8 or Figure 9, confirming the cancellation of the virtual wall will switch to projecting the prompt information shown in Figure 10. The prompt information shown in Figures 8, 9, and 10 is merely illustrative; the prompt information may consist of only text or images, or it may include both text and images. Furthermore, when the prompt information includes text, the text may be oriented towards the direction of the target object to improve the readability of the text relative to the target object.

[0116] It should be noted that, in actual implementation, the way a vehicle indicates to a target object whether it is in a yielding or non-yielding state is not limited to the methods shown in Figures 8 to 10. The vehicle can also provide information through other prompting devices. For example, the vehicle can play sound effects or audio information indicating whether it is in a yielding or non-yielding state through an external speaker; or the vehicle can display a prompt message indicating whether it is in a yielding or non-yielding state on a vehicle body display screen; or the vehicle can provide information through other means.

[0117] In some implementations, when a vehicle yields to a target object, a notification device (such as a display device or an audio device) in the vehicle's cabin can also indicate that the vehicle is in a yielding state; when the vehicle ends its yielding state, the notification device in the vehicle's cabin can also indicate that the vehicle has ended its yielding state, so that the driver and passengers of the vehicle are aware of the vehicle's status.

[0118] The autonomous driving method provided in this application embodiment can set up a virtual wall when deciding whether to yield to a target object, and control the vehicle to travel at a speed that allows it to stop before the virtual wall, thus yielding to the target object. This avoids discomfort to the driver and passengers caused by excessive deceleration during yielding, and prevents the vehicle from entering the conflict zone and colliding with the target object due to untimely braking. Furthermore, if the motion state of the target object and the vehicle changes during the vehicle's journey towards the target object, such that the target object can pass through the conflict zone first without the vehicle yielding, the virtual wall can be canceled, and the vehicle can be controlled to pass through the conflict zone. Alternatively, if the target object's intention to pass through the conflict zone is canceled or unclear during the vehicle's journey towards the target object, the virtual wall can be canceled, and the vehicle can be controlled to pass through the conflict zone before the target object, which helps improve traffic efficiency.

[0119] Figure 11 shows another schematic flowchart of the autonomous driving method provided in an embodiment of this application. The method can be executed by the vehicle shown in Figure 1, or by the system shown in Figure 2. The method 1000 includes:

[0120] S1010, Obtain first motion state information, which indicates the vehicle's speed and direction of motion.

[0121] S1020, Obtain second motion state information, which indicates the position change of the first object.

[0122] For example, the second motion state information can be the motion state information in method 300, and the first object can be the target object in method 300. The specific implementation of filtering the target object can be referred to the description in method 300, and will not be repeated here.

[0123] S1030, when it is determined from the first motion state information and the second motion state information that the first duration is less than the duration threshold, the vehicle is controlled to move toward the first position with a first deceleration so that the first object passes through the conflict area before the vehicle.

[0124] The conflict zone is the predicted area where the vehicle and the first object will collide; the first duration is the time required for the vehicle to travel to the conflict zone, which is the difference between the predicted time required for the first object to pass through the conflict zone; the first position is the position between the current position of the vehicle and the first boundary of the conflict zone, which is the boundary between the conflict zone and the nearest neighbor of the current position.

[0125] It is understandable that the first deceleration is negative, and the larger the absolute value of the first deceleration, the faster the vehicle decelerates.

[0126] For example, the first duration can be as described in method 300 (ttc) eo -ttl o The value of ) can be the position of the virtual wall set in method 300, and the first deceleration can be calculated based on the position of the virtual wall and the current speed of the vehicle.

[0127] For example, the duration threshold can be a value between 0.5 seconds and 1 second, or it can be other values.

[0128] In some implementations, the method further includes: when it is determined that a first duration is greater than or equal to a duration threshold while controlling the vehicle to move toward a first position at a first deceleration, controlling the vehicle to pass through the conflict zone at a first speed, wherein the first speed is determined based on the first deceleration.

[0129] For example, when it is determined that the first duration is greater than or equal to the duration threshold, the virtual wall is canceled and the vehicle is controlled to pass through the conflict area at the first speed, that is, the vehicle is no longer controlled to stop at or before the first position.

[0130] In some implementations, the first deceleration causes the vehicle to stop at the first position. The method further includes: controlling the vehicle to travel along a first path when the position change of the first object is less than or equal to a displacement threshold within a second time period starting from the first moment; wherein the first moment is a moment in the process of the vehicle traveling to the first position, or the first moment is the moment when the vehicle stops at the first position, and the first path is planned according to the position of the first object, and the vehicle can pass through the conflict area before the first object when traveling along the first path.

[0131] For example, the second duration can be a duration of 1 to 3 seconds. When the first object is located in the vehicle's original target driving area (such as the lane where the vehicle is currently located), the first path can be a path to bypass the first object, such as the obstacle avoidance driving path shown in Figure 7; when the first object is not located in the target driving area of ​​the lane, the first path can be the path that the vehicle travels in the original target driving area.

[0132] In some implementations, the method further includes: controlling a vehicle's prompting device to display first information during a second duration, the first information being used to indicate to a first object that the vehicle is in a yielding state. The first information includes at least one of the following projected in front of the vehicle: a zebra crossing image, a crossing instruction image, or crossing instruction text, so that the first object clearly understands the vehicle's intention to yield, reducing the probability of the first object and the vehicle stopping together.

[0133] For example, the first information may include the prompt information shown in Figure 8 or Figure 9, or the first information may be other information.

[0134] In some implementations, the method further includes: starting from a second moment, controlling the vehicle's prompting device to display second information, the second information indicating that the vehicle is in a non-yielding state under autonomous driving mode, which can reduce the probability of the first object and the vehicle starting simultaneously. Here, the second moment is the end time of the second duration.

[0135] For example, the second information may include the prompt information shown in FIG10, or the second information may be other information.

[0136] In some implementations, the method further includes: deducing a predicted motion path of the first object at different speeds and / or accelerations based on the second motion state information; deducing a planned driving path of the vehicle at different speeds and / or accelerations based on the first motion state information; and controlling the vehicle to move towards the first position with a first deceleration, including: when it is deduced from the predicted motion path and the planned driving path that the first object can pass through the conflict area before the vehicle, and when it is determined from the first motion state information and the second motion state information that the first duration is less than a duration threshold, controlling the vehicle to move towards the first position with a first deceleration.

[0137] For example, the methods for predicting the motion path of the first object and predicting the planned driving path of the vehicle can refer to the description of predicting the target object and the predicted path of the vehicle in S302, and will not be repeated here.

[0138] In some implementations, controlling the vehicle to move toward the first position with a first deceleration includes: controlling the vehicle to move toward the first position with the first deceleration when the vehicle can stop at or before the first position with a second deceleration and the first duration is less than a duration threshold.

[0139] It should be noted that the second deceleration and the first deceleration can be the same or different.

[0140] In some implementations, if the vehicle is deduced to travel towards the first position with a third deceleration in the previous frame and can stop at or before the first position, the vehicle is deduced to continue traveling towards the first position with a second deceleration in the current frame, where the absolute value of the third deceleration is less than or equal to the absolute value of the second deceleration.

[0141] In some implementations, the method further includes: while controlling the vehicle to move toward the first position at a first deceleration, a prompting device controlling the vehicle prompts a third message, the third message being used to prompt the first object that the vehicle is in a yielding state.

[0142] For example, the third information and the aforementioned first information can be the same information.

[0143] The autonomous driving method provided in this application can plan the vehicle's speed based on the boundary between the conflict area and the vehicle's current position. This avoids discomfort to the vehicle's occupants caused by excessive deceleration during yielding to a first object, and also prevents the vehicle from entering the conflict area and colliding with the first object due to untimely braking. Therefore, it can balance driving safety and traffic efficiency during the yielding process. When the speed of the first object changes to the point where the vehicle no longer needs to yield, or when the first object's intention to pass through the conflict area is unclear or nonexistent, the yielding process ends, and the vehicle resumes normal driving.

[0144] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0145] The methods provided by the embodiments of this application have been described in detail above with reference to Figures 1 to 11. The apparatus provided by the embodiments of this application will now be described in detail with reference to Figures 12 and 13. It should be understood that the descriptions of the apparatus embodiments correspond to the descriptions of the method embodiments; therefore, any content not described in detail can be found in the above method embodiments, and for the sake of brevity, will not be repeated here.

[0146] Figure 12 shows a schematic block diagram of an autonomous driving device 2000 provided in an embodiment of this application. The device 2000 may include units for executing the methods described in the foregoing embodiments. Furthermore, each unit in the device 2000 implements a corresponding process of the above method embodiments. The device 2000 includes an acquisition unit 2010, which can be used to implement corresponding data acquisition or transmission / reception functions. The device 2000 also includes a processing unit 2020, which can be used to implement corresponding processing functions.

[0147] Optionally, the device 2000 further includes a storage unit, which can be used to store instructions and / or data. The processing unit 2020 can read the instructions and / or data in the storage unit so that the device can perform the relevant actions in the aforementioned method embodiments.

[0148] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0149] It should also be understood that the device 2000 described herein is embodied in the form of a functional unit. The terms “module” or “unit” may refer to application-specific ASICs, electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, integrated logic circuits, and / or other suitable components that support the described functions.

[0150] The apparatuses described above have the function of implementing the corresponding steps in the methods described above. These functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above; for example, the acquisition unit 2010 can be replaced by a transceiver, and other units, such as the processing unit, can be replaced by a processor, used to execute the relevant processing operations in each method embodiment.

[0151] Exemplarily, the acquisition unit 2010 and processing unit 2020 can be disposed in the vehicle 100 shown in FIG. 1, or they can also be disposed in the system shown in FIG. 2. More specifically, the acquisition unit 2010 and processing unit 2020 can be disposed in the control module 220. Exemplarily, the operations performed by the acquisition unit 2010 and processing unit 2020 can be performed by a single processor, or they can be performed by different processors. In specific implementation, the one or more processors can be processors disposed in the vehicle 100 shown in FIG. 1; or, the device 2000 can be a chip disposed in the vehicle 100.

[0152] In the specific implementation process, the units in the above device can be fully or partially integrated together, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0153] Figure 13 is another schematic block diagram of the autonomous driving device provided in an embodiment of this application. The device 2100 shown in Figure 13 may include a processor 2110, a transceiver 2120, and a memory 2130. The processor 2110, transceiver 2120, and memory 2130 are connected via internal interconnection paths. The memory 2130 is used to store instructions, and the processor 2110 is used to execute the instructions stored in the memory 2130 to implement the methods in the above embodiments. Optionally, the memory 2130 may be coupled to the processor 2110 via an interface or integrated with the processor 2110.

[0154] It should be noted that the transceiver 2120 mentioned above may include, but is not limited to, transceiver devices such as input / output interfaces, to realize communication between device 2100 and other devices or communication networks.

[0155] Memory 2130 can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes various forms such as: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0156] Transceiver 2120 uses transceiver devices, such as but not limited to transceivers, to enable communication between device 2100 and other devices or communication networks to receive / send data / information for implementing the methods in the above embodiments.

[0157] This application also provides an intelligent driving device, which includes the device 2000 or device 2100 in the above embodiments.

[0158] This application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to implement the methods described in the above embodiments of this application.

[0159] This application also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to implement the methods described in the above embodiments of this application.

[0160] This application also provides a chip, including circuitry, for performing the methods described in the above embodiments of this application.

[0161] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0162] In the description of the embodiments of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. In this application, "at least one" means one or more, and "more" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0163] The use of prefixes such as "first" and "second" in this application embodiment is solely for distinguishing different descriptive objects and does not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is found in the claims or the context of the embodiments, and the use of such prefixes should not constitute unnecessary restrictions.

[0164] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0165] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0166] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0167] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0168] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An autonomous driving method, characterized in that, include: Acquire first motion state information, which indicates the vehicle's speed and direction of motion; Acquire second motion state information, which indicates the position change of the first object; When it is determined from the first motion state information and the second motion state information that the first duration is less than the duration threshold, the vehicle is controlled to move toward the first position with a first deceleration so that the first object passes through the conflict area before the vehicle. Wherein, the conflict zone is the predicted area where the vehicle and the first object will collide, and the first duration is the difference between the time required for the vehicle to travel to the conflict zone and the predicted time required for the first object to pass through the conflict zone. The first position is the position between the current position of the vehicle and the first boundary of the conflict area, where the first boundary is the boundary between the conflict area and the current position.

2. The method according to claim 1, characterized in that, The method further includes: During the process of controlling the vehicle to travel towards the first position at the first deceleration, when it is determined that the first duration is greater than or equal to the duration threshold, the vehicle is controlled to pass through the conflict area at a first speed, the first speed being determined based on the first deceleration.

3. The method according to claim 1 or 2, characterized in that, The first deceleration causes the vehicle to stop at the first position, and the method further includes: During the second time period starting from the first moment, if the position change of the first object is less than or equal to the displacement threshold, the vehicle is controlled to travel along the first path. Wherein, the first moment is a moment in the process of the vehicle traveling to the first position, or the first moment is the moment when the vehicle stops at the first position, the first path is planned according to the position of the first object, and the vehicle can pass through the conflict area before the first object when traveling along the first path.

4. The method according to claim 3, characterized in that, The method further includes: During the second duration, the vehicle's prompting device displays first information, which is used to indicate to the first object that the vehicle is in a yielding state.

5. The method according to claim 4, characterized in that, The first information includes at least one of the following projected in front of the vehicle: a zebra crossing image, an image indicating passage, or text indicating passage.

6. The method according to any one of claims 3 to 5, characterized in that, The method further includes: Starting from the second moment, the prompting device controlling the vehicle will display a second message, which indicates that the vehicle is in a non-yielding state under autonomous driving mode; the second moment is the end time of the second duration.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Based on the second motion state information, the predicted motion path of the first object under different velocities and / or accelerations is deduced; Based on the first motion state information, the planned driving path of the vehicle at different speeds and / or accelerations is deduced; The control of the vehicle to move toward the first position with a first deceleration includes: When the predicted motion path and the planned driving path indicate that the first object can pass through the conflict area before the vehicle, and when the first duration is determined to be less than the duration threshold based on the first motion state information and the second motion state information, the vehicle is controlled to move towards the first position with the first deceleration.

8. The method according to any one of claims 1 to 7, characterized in that, The control of the vehicle to move toward the first position with a first deceleration includes: When the vehicle is able to stop at or before the first position while traveling at the second deceleration and the first duration is less than the duration threshold, the vehicle is controlled to travel towards the first position at the first deceleration.

9. The method according to claim 8, characterized in that, The method further includes: In the previous frame, if the vehicle is deduced to travel towards the first position with a third deceleration and is able to stop at or before the first position, in the current frame, the path of the vehicle continuing to travel towards the first position with a second deceleration is deduced, wherein the absolute value of the third deceleration is less than or equal to the absolute value of the second deceleration.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: During the process of controlling the vehicle to move towards the first position at a first deceleration, the vehicle's prompting device displays third information, which is used to indicate to the first object that the vehicle is in a yielding state.

11. An automatic driving device, characterized in that, include: An acquisition unit is used to acquire first motion state information, wherein the first motion state information indicates the speed and direction of motion of the vehicle; The acquisition unit is further configured to: acquire second motion state information, wherein the second motion state information indicates the position change of the first object; The processing unit is configured to: when it is determined from the first motion state information and the second motion state information that the first duration is less than the duration threshold, control the vehicle to move toward the first position with a first deceleration so that the first object passes through the conflict area before the vehicle; Wherein, the conflict zone is the predicted area where the vehicle and the first object will collide, and the first duration is the difference between the time required for the vehicle to travel to the conflict zone and the predicted time required for the first object to pass through the conflict zone. The first position is the position between the current position of the vehicle and the first boundary of the conflict area, where the first boundary is the boundary between the conflict area and the current position.

12. The apparatus according to claim 11, characterized in that, The processing unit is also used for: During the process of controlling the vehicle to travel towards the first position at the first deceleration, when it is determined that the first duration is greater than or equal to the duration threshold, the vehicle is controlled to pass through the conflict area at a first speed, the first speed being determined based on the first deceleration.

13. The apparatus according to claim 11 or 12, characterized in that, The first deceleration causes the vehicle to stop at the first position, and the processing unit is further configured to: During the second time period starting from the first moment, if the position change of the first object is less than or equal to the displacement threshold, the vehicle is controlled to travel along the first path. Wherein, the first moment is a moment in the process of the vehicle traveling to the first position, or the first moment is the moment when the vehicle stops at the first position, the first path is planned according to the position of the first object, and the vehicle can pass through the conflict area before the first object when traveling along the first path.

14. The apparatus according to claim 13, characterized in that, The processing unit is also used for: During the second duration, the vehicle's prompting device displays first information, which is used to indicate to the first object that the vehicle is in a yielding state.

15. The apparatus according to claim 14, characterized in that, The first information includes at least one of the following projected in front of the vehicle: a zebra crossing image, an image indicating passage, or text indicating passage.

16. The apparatus according to any one of claims 13 to 15, characterized in that, The processing unit is also used for: Starting from the second moment, the prompting device controlling the vehicle will display a second message, which indicates that the vehicle is in a non-yielding state under autonomous driving mode; the second moment is the end time of the second duration.

17. The apparatus according to any one of claims 11 to 16, characterized in that, The processing unit is also used for: Based on the second motion state information, the predicted motion path of the first object under different velocities and / or accelerations is deduced; Based on the first motion state information, the planned driving path of the vehicle at different speeds and / or accelerations is deduced; When the predicted motion path and the planned driving path indicate that the first object can pass through the conflict area before the vehicle, and when the first duration is determined to be less than the duration threshold based on the first motion state information and the second motion state information, the vehicle is controlled to move towards the first position with the first deceleration.

18. The apparatus according to any one of claims 11 to 17, characterized in that, The processing unit is used for: When the vehicle is able to stop at or before the first position while traveling at the second deceleration and the first duration is less than the duration threshold, the vehicle is controlled to travel towards the first position at the first deceleration.

19. The apparatus according to claim 18, characterized in that, The processing unit is also used for: In the previous frame, if the vehicle is deduced to travel towards the first position with a third deceleration and is able to stop at or before the first position, in the current frame, the path of the vehicle continuing to travel towards the first position with a second deceleration is deduced, wherein the absolute value of the third deceleration is less than or equal to the absolute value of the second deceleration.

20. The apparatus according to any one of claims 11 to 19, characterized in that, The processing unit is also used for: During the process of controlling the vehicle to move towards the first position at a first deceleration, the vehicle's prompting device displays third information, which is used to indicate to the first object that the vehicle is in a yielding state.

21. An automatic driving device, characterized in that, include: A processor for executing a computer program stored in memory to cause the apparatus to perform the method as described in any one of claims 1 to 10.

22. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 10.

23. A chip, characterized in that, The chip includes circuitry for performing the method as described in any one of claims 1 to 10.

24. A computer program product, characterized in that, The computer program product includes: computer program code, which, when executed by a processor, implements the method as described in any one of claims 1 to 10.

25. A vehicle, characterized in that, Includes the apparatus as described in any one of claims 11 to 21, or the computer-readable storage medium as described in claim 22, or the chip as described in claim 23, or the vehicle is equipped with the computer program product as described in claim 24.

Images