Method for realizing vehicle obstacle avoidance by crabbing mode, auxiliary driving system and vehicle

Abstract

This application relates to a method for vehicle obstacle avoidance using a crab-like driving mode. The method includes: detecting driving environment information of a vehicle (1) and monitoring obstacle information in the driving environment ahead of the vehicle based on the detected driving environment information; when a first obstacle is detected in the driving environment ahead of the vehicle, determining a planned driving path for the vehicle to avoid the first obstacle in a crab-like driving mode based at least on the driving environment information; controlling the vehicle (1) to drive past the first obstacle in a crab-like driving mode according to the planned driving path, wherein the steering angle of all wheels of the vehicle is equal in the crab-like driving mode; after the vehicle has driven past the first obstacle, adjusting the lateral position of the vehicle in the road in a crab-like driving mode based at least on the driving environment information of the vehicle to avoid other obstacles in the driving environment ahead of the vehicle.

Description

Technical Field

[0001] This application relates to the field of autonomous driving, and in particular to a method for vehicle obstacle avoidance using a crab-like mode, a driver assistance system, a vehicle including the driver assistance system according to this application, and a computer program product. Background Technology

[0002] When driving through narrow roads, vehicles often face the risk of collision with objects in the road environment—such as other vehicles, pedestrians, and motorcyclists—especially the front corners of the vehicle or rearview mirrors, which may scrape against these objects. In such driving scenarios, most existing obstacle avoidance strategies involve actively steering the vehicle. However, this strategy requires the vehicle to quickly straighten its direction after actively steering, ensuring it continues to travel straight along the narrow road. Otherwise, the vehicle may collide with other objects on the narrow road—such as roadside guardrails, building walls, curbs, other pedestrians, or vehicles. This places high demands on the driving skills of the driver or driver assistance system.

[0003] Therefore, there is an urgent need to develop a new obstacle avoidance strategy for objects on narrow roads. Summary of the Invention

[0004] The purpose of this application is to provide a method for vehicle obstacle avoidance using a crab-like driving mode, a driver assistance system, a vehicle including the driver assistance system according to this application, and a computer program product, to at least partially solve the problems in the prior art.

[0005] According to a first aspect of this application, a method for vehicle obstacle avoidance using a crab-like movement mode is provided, the method comprising: - It can detect the vehicle's driving environment information and monitor obstacle information in the driving environment in front of the vehicle based on the detected driving environment information; -If a first obstacle is detected in the driving environment ahead of the vehicle, the planned driving path for the vehicle to avoid the first obstacle in crab mode can be determined at least based on the driving environment information. - The vehicle can be controlled to travel beyond the first obstacle in a crab-like mode along the planned driving path, wherein all wheels of the vehicle have equal steering angles in the crab-like mode; - After the vehicle has passed the first obstacle, it can adjust its lateral position on the road in a crab mode, based at least on the vehicle's driving environment information, in order to avoid other obstacles in the driving environment ahead of the vehicle.

[0006] The core concept of this application includes at least the following: when a vehicle equipped with rear-wheel independent steering is traveling at low speed on a narrow road, the vehicle is controlled to avoid obstacles in the driving environment in front of the vehicle in a crab-like mode, and after passing the obstacle, the lateral position of the vehicle in the road is adjusted in a crab-like mode to avoid the risk of secondary collision with potential obstacles in the driving environment in front of the vehicle, thereby realizing a simple, effective and safe obstacle avoidance strategy for objects on narrow roads.

[0007] According to an optional embodiment of this application, the expected lateral movement distance required for a vehicle to avoid the first obstacle from its current initial lateral position on the road can be calculated based on obstacle information about the first obstacle. If the calculated expected lateral movement distance is less than a lateral distance threshold, a planned driving path for the vehicle to avoid the first obstacle in crab mode can be determined at least based on the driving environment information, wherein the lateral distance threshold is, for example, pre-given or related to the vehicle's driving speed.

[0008] According to another optional embodiment of this application, during the process of controlling the vehicle to drive past the first obstacle in a crab-like mode along the planned driving path, the planned driving path can be adjusted based on the detected driving environment information so that there are no obstacles in the driving area of ​​the vehicle along the planned driving path.

[0009] According to another optional embodiment of this application, after the vehicle has passed the first obstacle, if a second obstacle in the driving environment ahead is determined based on the vehicle's driving environment information, the lateral position of the vehicle in the road can be adjusted in a crab mode at least based on the driving environment information in order to avoid the second obstacle.

[0010] According to another optional embodiment of this application, after the vehicle has passed the first obstacle, if it is determined based on the vehicle's driving environment information that there are no other obstacles in the driving environment ahead, the vehicle can be controlled to drive in a crab-like mode to the initial lateral position, at least based on the vehicle's driving environment information.

[0011] According to another optional embodiment of this application, the obstacle information may include one or more of the following: obstacle type information, size information, location information, and movement speed information, etc. The obstacle size information particularly includes the obstacle width information.

[0012] According to another optional embodiment of this application, the method may further include: - When controlling the vehicle to travel in crab mode according to the planned driving path, the driver may be given prompts about the obstacle avoidance strategy of crab mode in one or more of the following forms: optical, acoustic and tactile forms.

[0013] According to another optional embodiment of this application, the method may further include: - In response to the driver's operation signal regarding the steering device, the vehicle can be controlled to stop driving in crab mode, and the vehicle can be controlled based on the operation signal.

[0014] According to another optional embodiment of this application, the planned driving path for the vehicle to avoid the first obstacle in crab mode and the corresponding control commands for the vehicle can be determined through an end-to-end model, at least based on the driving environment information, so as to control the vehicle to drive past the first obstacle in crab mode according to the planned driving path. During the process of controlling the vehicle to drive past the first obstacle in crab mode according to the planned driving path, the planned driving path and the corresponding control commands for the vehicle can be adjusted through the end-to-end model based on the detected driving environment information, so that there are no obstacles in the driving area of ​​the vehicle along the adjusted planned driving path.

[0015] According to a second aspect of this application, a driving assistance system is provided, which may include the following components: - An environmental sensing unit, which is configured to detect information about the vehicle's driving environment; - A control unit for performing the method according to this application.

[0016] According to another optional embodiment of this application, the environmental sensing unit may include one or more of the following devices: vehicle-mounted camera, millimeter-wave radar, lidar, and ultrasonic radar, etc.

[0017] According to another optional embodiment of this application, the control unit can be integrated into the vehicle-mounted camera, and an end-to-end model is deployed in the control unit. The end-to-end model can determine, at least based on the driving environment information, a planned driving path for the vehicle to avoid the first obstacle and corresponding control commands for the vehicle, thereby controlling the vehicle to travel along the planned driving path in a crab-like mode to pass the first obstacle. During the process of controlling the vehicle to travel along the planned driving path in a crab-like mode to pass the first obstacle, the planned driving path and corresponding control commands for the vehicle can be adjusted based on the detected driving environment information through the end-to-end model, so that there are no obstacles in the driving area along the planned driving path.

[0018] According to a third aspect of this application, a vehicle is provided that may include a driver assistance system according to this application.

[0019] According to a fourth aspect of this application, a computer program product, such as a computer-readable program carrier, is provided, comprising or storing computer program instructions that, when executed by a processor, at least assist in implementing the steps of the method described in this application. Attached Figure Description

[0020] The principles, features, and advantages of this application can be better understood by describing it in more detail below with reference to the accompanying drawings. The drawings show: Figure 1 A flowchart illustrating a method for vehicle obstacle avoidance using a crab-like pattern according to an exemplary embodiment of this application is shown. Figure 2 A schematic diagram of a driving scenario according to an exemplary embodiment of this application is shown; Figure 3 A schematic diagram of a driving scenario according to another exemplary embodiment of this application is shown; Figure 4 A schematic diagram of a driving scenario according to another exemplary embodiment of this application is shown; Figure 5 A flowchart illustrating a method for vehicle obstacle avoidance using a crab-like mode according to another exemplary embodiment of this application is shown. Figure 6 A flowchart illustrating a method for vehicle obstacle avoidance using a crab-like mode according to another exemplary embodiment of this application is shown. Figure 7 A schematic diagram of a vehicle according to an exemplary embodiment of this application is shown. Detailed Implementation

[0021] To make the technical problems to be solved, the technical solutions, and the beneficial technical effects of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and several exemplary embodiments. It should be understood that the specific embodiments described herein are only for explaining this application and are not intended to limit the scope of protection of this application.

[0022] Figure 1 A flowchart illustrating a method for vehicle obstacle avoidance using a crab-like pattern according to an exemplary embodiment of this application is shown. The following exemplary embodiments describe the method according to this application in more detail.

[0023] like Figure 1As shown, the method may include steps S1 to S4. In step S1, driving environment information of vehicle 1 can be detected, and obstacle information in the driving environment ahead of vehicle 1 can be monitored based on the detected driving environment information. In the current embodiment of this application, during the driving of vehicle 1, driving environment information of vehicle 1 can be detected by the environmental perception unit 11 of vehicle 1. The driving environment information may include not only road information such as road surface conditions, lane markings, or curb conditions, but also obstacle information about obstacles in the driving environment ahead of vehicle 1. The environmental perception unit 11 of vehicle 1 includes, for example, one or more of the following devices: vehicle-mounted camera, lidar, millimeter-wave radar, and ultrasonic radar. For example, the obstacle information may include obstacle type information, which may include not only stationary obstacles on the road, such as roadblocks, building piles, parked vehicles, bicycles, electric bicycles, or motorcycles, but also moving obstacles on the road, such as vehicles in motion and / or vulnerable road users, such as pedestrians, cyclists, electric bicycle riders, or motorcycle riders; the obstacle information may also include obstacle size information, particularly the width information of the obstacle; the obstacle information may also include obstacle position information, that is, the relative position information of the obstacle in the driving environment in front of vehicle 1 in the vehicle coordinate system; the obstacle information may also include obstacle speed information, such as the direction of movement and / or relative speed of the obstacle in the driving environment in front of vehicle 1 relative to vehicle 1.

[0024] In step S2, if a first obstacle is detected in the driving environment ahead of vehicle 1, a planned driving path for vehicle 1 to avoid the first obstacle in crab walk mode can be determined at least based on the driving environment information. Figure 2 The diagram illustrates a driving scenario according to an exemplary embodiment of this application. Vehicle 1 is traveling at a low speed on a narrow road. Based on the perception information from the environmental perception unit 11, a first obstacle 21 is detected in the driving environment ahead of vehicle 1. Figure 2 The example shown is a vehicle, but it could also be a vulnerable road user and / or a roadblock, etc.

[0025] Here, the expected lateral movement S required for vehicle 1 to avoid the first obstacle 21 from its current initial lateral position on the road can be calculated based on obstacle information about the first obstacle. pIn the context of this application, "lateral position" refers to the position of vehicle 1 in the road in the lateral direction perpendicular to its longitudinal direction of travel (i.e., the direction in which the front of vehicle 1 is facing forward). This position can be described using the lateral spacing of fixed reference points on the road. For example, in... Figure 2 In the straight road segment shown, the initial lateral position of vehicle 1 is its position in the lateral direction perpendicular to the road edge at the moment it detects the first obstacle in the driving environment ahead. Before this moment, vehicle 1 is always traveling in the longitudinal direction. The expected lateral movement distance S p The calculation needs to consider not only the width of vehicle 1 and the width of the first obstacle 21, but also the safety margin between vehicle 1 and the first obstacle 21. Figure 2 The middle part represents the safe clearance distance S between, for example, the rearview mirror of vehicle 1' at the desired lateral position and the rearview mirror of the first obstacle 21. r The safety allowance distance can be predetermined or adjusted based on driver settings or driving style. The calculated expected lateral movement distance S... p If the lateral distance is less than a certain threshold, the planned driving path for vehicle 1 to avoid the first obstacle in crab mode can be determined at least based on the driving environment information. The lateral distance threshold can be, for example, pre-defined or related to the vehicle 1's speed. A smaller expected lateral movement distance means that vehicle 1 does not need to make long lateral position adjustments, thus crab mode can be used to adjust the lateral position of vehicle 1 on the road.

[0026] In the context of this application, "crab mode" refers to the simultaneous movement of all wheels of a vehicle—including the two front wheels and the two rear wheels—at the same steering angle and speed in either a diagonal (i.e., wheel steering angle less than 90°) or lateral (i.e., wheel steering angle of 90°) direction, enabling the vehicle 1 to move diagonally or laterally on the road surface. For this purpose, the vehicle 1 must be equipped with independent rear-wheel steering, allowing independent control of the rear wheel steering angle. Typically, the crab mode is activated when the vehicle 1 is traveling at low speeds, such as below 40 km / h, and especially below 20 km / h, to achieve short-distance lateral position adjustments on the road.

[0027] Here, the control unit 12 of the driver assistance system 10 can determine the planned driving path of the vehicle 1 in crab mode to avoid the first obstacle, at least based on the driving environment information. Figure 2The planned driving path is schematically indicated by a thick arrow. In crab mode, vehicle 1 moves diagonally along the planned driving path to the desired lateral position (i.e., the lateral position of vehicle 1' after movement), and there are no other obstacles within the driving area of ​​the vehicle along the planned driving path. Control unit 12 may be an on-board control unit constructed separately from environmental perception unit 11, in which the path planning algorithm is deployed.

[0028] Optionally, the control unit 12 can also be integrated into the vehicle-mounted camera. An end-to-end model is deployed in the control unit 12, such as a Vision-Language-Action Model (VLA model). This model can take images / videos and natural language commands as input and directly output action commands executable by actuators or intelligent agents. This reduces the accumulation of errors in the intermediate links between perception, planning, and control, significantly improving the scene adaptability of the control function. Here, the planned driving path for vehicle 1 to avoid the first obstacle in crab mode can be determined by the end-to-end model, at least based on the driving environment information.

[0029] In step S3, vehicle 1 can be controlled to travel past the first obstacle 21 in a crab-like mode according to the planned driving path, wherein all wheels of vehicle 1 have equal steering angles in the crab-like mode. Here, control unit 12 controls all wheels of vehicle 1—including the two front wheels and the two rear wheels—to simultaneously push in an oblique direction with the same steering angle and the same speed, so that vehicle 1 moves along the road, for example, along... Figure 2 The vehicle moves in the diagonal direction indicated by the thick diagonal arrow, thereby controlling the vehicle 1 to travel past the first obstacle 21 in a crab-like mode along the planned driving path. Considering that various obstacles in the driving environment ahead of the vehicle 1—including vehicles and / or vulnerable road users, etc.—may be in motion, i.e., the positions of obstacles may change in real time, during the process of controlling the vehicle 1 to travel past the first obstacle 21 in a crab-like mode along the planned driving path, the driving environment information of the vehicle 1 can be continuously detected, and the planned driving path can be adjusted based on the detected driving environment information, so that there are no obstacles in the driving area of ​​the vehicle 1 along the planned driving path.

[0030] When the control unit 12 is integrated into the vehicle-mounted camera, the corresponding control commands for vehicle 1 can also be determined by the end-to-end model deployed in the control unit 12 and sent to the corresponding actuators of vehicle 1. The actuators can perform corresponding control operations based on the received control commands to control vehicle 1 to travel in a crab-like mode along the planned driving path to pass the first obstacle. During the process of controlling vehicle 1 to travel in a crab-like mode along the planned driving path to pass the first obstacle, the end-to-end model can also adjust the planned driving path and the corresponding control commands for vehicle 1 based on the detected driving environment information, so that there are no obstacles in the driving area of ​​vehicle 1 along the adjusted planned driving path. The actuators can then control vehicle 1 to travel along the adjusted planned driving path based on the received adjusted control commands.

[0031] When vehicle 1 travels in crab mode along the planned path to the desired lateral distance, if vehicle 1 has not yet traveled beyond the first obstacle in the longitudinal distance, the steering angle of all wheels of vehicle 1 can be adjusted to 0°, thereby straightening the vehicle's direction of travel and controlling vehicle 1 to continue traveling straight along the vertical direction indicated by the thick straight arrow.

[0032] During the process of the vehicle passing the first obstacle and after the vehicle 1 has passed the first obstacle, the environmental perception unit 11 of the vehicle 1 can continuously detect the driving environment information of the vehicle 1, and monitor the information of other obstacles in the driving environment ahead of the vehicle 1, other than the first obstacle, based on the detected driving environment information.

[0033] In step S4, after vehicle 1 has passed the first obstacle, its lateral position on the road can be adjusted in a crab-like mode, at least based on the vehicle 1's driving environment information, to avoid other obstacles in the driving environment ahead of vehicle 1. After vehicle 1 has passed the first obstacle, vehicle 1 moves to the desired lateral position set for avoiding the first obstacle. Figure 2 In the exemplary driving scenario, the vehicle 1 is close to the left side of the road, which poses a risk of secondary collision with obstacles on the left side of the road. To avoid the potential risk of secondary collision, the driving environment information of the vehicle 1 can be continuously detected, and the lateral position of the vehicle 1 in the road can be adjusted in a crab mode based at least on the driving environment information of the vehicle 1 to avoid other obstacles in the driving environment in front of the vehicle 1.

[0034] exist Figure 3In a driving scenario diagram illustrating another exemplary embodiment of this application, after vehicle 1 has passed the first obstacle 21, it is determined, based on the driving environment information of vehicle 1, that there are no other obstacles in the driving environment ahead. Based at least on the driving environment information of vehicle 1, vehicle 1 can be controlled to drive in a crab-like mode to the initial lateral position (i.e., the lateral position of the moved vehicle 1'' in the road), that is, to drive to the right front in the direction indicated by the thick diagonal arrow to the front of the first obstacle 21, thereby restoring the initial lateral position of vehicle 1 in the road.

[0035] exist Figure 4 In a driving scenario diagram illustrating another exemplary embodiment of this application, after vehicle 1 has passed the first obstacle, vehicle 1 moves to the left lane of the road at a lateral position marked by the moved vehicle 1'. Based on the driving environment information of vehicle 1', a second obstacle 22 in the driving environment ahead can be determined—in Figure 4 The image exemplarily illustrates a vehicle 22 parked on the left side of the road, which can adjust its lateral position in the road in a crab-like mode, at least based on the driving environment information, to avoid the second obstacle 22, i.e., to travel forward and to the right in the direction indicated by the thick diagonal arrow to the front of the first obstacle 21. Figure 4 The center represents the position of vehicle 1'' after it has been moved. To ensure that the lateral distance between vehicle 1 and the second obstacle 22 is greater than or equal to the safety allowance, the lateral position of vehicle 1'' after it has been moved may be closer to the right than the initial lateral position of vehicle 1 in the road if necessary.

[0036] It should be noted that after the vehicle has passed the second obstacle, if it is determined that there are no other obstacles in the driving environment ahead based on the driving environment information of vehicle 1, the vehicle 1 is controlled to drive in crab mode to the initial lateral position, at least based on the driving environment information of vehicle 1; if a third obstacle is determined in the driving environment ahead based on the driving environment information of vehicle 1, the lateral position of vehicle 1 in the road can be adjusted in crab mode, at least based on the driving environment information, to avoid the third obstacle; and so on.

[0037] According to an embodiment of this application, when a vehicle equipped with rear-wheel independent steering is traveling at low speed on a narrow road, the vehicle is controlled to avoid obstacles in the driving environment in front of the vehicle in a crab-like mode. After passing the obstacle, the vehicle's lateral position in the road is adjusted in a crab-like mode to avoid the risk of secondary collision with potential obstacles in the driving environment in front of the vehicle. This achieves a simple, effective and safe obstacle avoidance strategy for objects on narrow roads.

[0038] Figure 5A flowchart illustrating a method for vehicle obstacle avoidance using a crab-like pattern according to another exemplary embodiment of this application is shown. The following only describes the method in relation to... Figure 1 The differences between the embodiments shown are omitted for brevity, and the same steps will not be described again.

[0039] like Figure 5 As shown, the method may further include step S31. In step S31, when controlling vehicle 1 to drive in crab mode according to the planned driving path, prompt information about the obstacle avoidance strategy of crab mode can be output to the driver. For example, the prompt information about the obstacle avoidance strategy of crab mode can be output to the driver in an optical form, such as through a central control display screen, instrument panel, or head-up display; it can also be output to the driver in an acoustic form, such as through an in-vehicle voice device; or it can be output to the driver in a tactile form, such as through a vibration device arranged in the steering wheel. Here, the prompt information can be output to the driver through one or more of the above prompting methods, so that the driver can timely grasp the switching of the driving mode of vehicle 1 during driving.

[0040] Figure 6 A flowchart illustrating a method for vehicle obstacle avoidance using a crab-like pattern according to another exemplary embodiment of this application is shown. The following only describes the method in relation to... Figure 1 The differences between the embodiments shown are omitted for brevity, and the same steps will not be described again.

[0041] like Figure 6 As shown, the method may further include step S5. In step S5, in response to the driver's operation signal regarding the steering device, the vehicle 1 can be controlled to stop driving in crab mode, and the vehicle 1 can be controlled based on the operation signal. When the driver operates the steering device, such as the steering wheel, the driver takes over the steering control of the vehicle 1, thereby controlling the vehicle 1 to stop driving in crab mode and controlling the driving direction of the vehicle 1 based on the operation signal.

[0042] In addition, it should be noted that the step numbers described herein do not necessarily represent the order of steps, but are merely a reference numeral. The order may be changed depending on the specific circumstances, as long as the technical objective of this application can be achieved.

[0043] Figure 7 A schematic diagram of a vehicle according to an exemplary embodiment of this application is shown.

[0044] like Figure 7 As shown, vehicle 1 is equipped with a driver assistance system 10, which may include the following components: - An environmental sensing unit 11 is configured to detect driving environment information of vehicle 1, wherein the environmental sensing unit includes one or more of the following devices: vehicle camera, millimeter-wave radar, lidar and ultrasonic radar, etc. - Control unit 12, which is used to perform the method according to this application.

[0045] When the environmental perception unit 11 includes an in-vehicle camera, the control unit 12 can be integrated into the in-vehicle camera, and an end-to-end model is deployed in the control unit 12. This end-to-end model may include, for example, a vision-language-action model. Here, at least based on the driving environment information, the end-to-end model can determine the planned driving path for vehicle 1 to avoid the first obstacle and the corresponding control commands for vehicle 1, thereby controlling vehicle 1 to travel past the first obstacle in a crab-like mode along the planned driving path. During the process of controlling vehicle 1 to travel past the first obstacle in a crab-like mode along the planned driving path, the planned driving path and the control commands for vehicle 1 can be adjusted based on the detected driving environment information through the end-to-end model, ensuring that there are no obstacles in the driving area along the planned driving path.

[0046] It should be understood that the terms “first,” “second,” “third,” etc., used in this document are for descriptive purposes only and should not be construed as indicating or implying relative importance, nor should they be construed as implicitly specifying the number of technical features indicated.

[0047] If an embodiment includes an "and / or" association between a first feature and a second feature, it should be interpreted as follows: according to one implementation, the embodiment has not only the first feature but also the second feature; according to another implementation, the embodiment has either only the first feature or only the second feature.

[0048] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of this application, even when only a single embodiment is described with respect to a particular feature. The feature examples provided in this application are intended for illustrative purposes and not for limitation, unless otherwise stated. In practice, multiple features may be combined with each other as needed and where technically feasible. Various substitutions, modifications, and alterations are also conceived without departing from the spirit and scope of this application.

Claims

1. A method for vehicle obstacle avoidance using a crab-like movement pattern, the method comprising: The driving environment information of the vehicle (1) is detected, and the obstacle information in the driving environment in front of the vehicle (1) is monitored based on the detected driving environment information. If a first obstacle (21) is detected in the driving environment ahead of the vehicle (1), the planned driving path for the vehicle (1) to avoid the first obstacle (21) in crab mode is determined based at least on the driving environment information. Control the vehicle (1) to travel past the first obstacle in a crab-like mode according to the planned driving path, wherein in the crab-like mode all wheels of the vehicle (1) have equal steering angles; After the vehicle (1) passes the first obstacle (21), the lateral position of the vehicle (1) in the road is adjusted in crab mode based at least on the driving environment information of the vehicle (1) in order to avoid other obstacles in the driving environment ahead of the vehicle (1).

2. The method according to claim 1, wherein, Based on obstacle information about the first obstacle, calculate the expected lateral movement distance required for vehicle (1) to avoid the first obstacle from its current initial lateral position in the road; If the calculated expected lateral movement distance is less than the lateral distance threshold, the planned driving path for the vehicle (1) to avoid the first obstacle in crab mode is determined at least based on the driving environment information, wherein the lateral distance threshold is, for example, pre-given or related to the driving speed of the vehicle (1).

3. The method according to any one of the preceding claims, wherein, During the process of controlling the vehicle (1) to drive past the first obstacle in crab mode according to the planned driving path, the planned driving path is adjusted based on the detected driving environment information so that there are no obstacles in the driving area of ​​the vehicle (1) along the planned driving path.

4. The method according to any one of the preceding claims, wherein, After the vehicle (1) passes the first obstacle, if a second obstacle (22) is determined in the driving environment ahead based on the driving environment information of the vehicle (1), the lateral position of the vehicle (1) in the road is adjusted in crab mode at least based on the driving environment information in order to avoid the second obstacle.

5. The method according to any one of the preceding claims, wherein, After the vehicle (1) passes the first obstacle, if it is determined that there are no other obstacles in the driving environment ahead based on the driving environment information of the vehicle (1), the vehicle (1) is controlled to drive in crab mode to the initial lateral position based at least on the driving environment information of the vehicle (1).

6. The method according to any one of the preceding claims, wherein, The obstacle information includes one or more of the following: obstacle type information, size information, location information, and movement speed information; The size information of the obstacle specifically includes the width information of the obstacle.

7. The method according to any one of the preceding claims, wherein, The method further includes: When the vehicle (1) is driving in crab mode according to the planned driving path, the driver is given prompts about the obstacle avoidance strategy of crab mode in one or more of the following forms: optical, acoustic and tactile.

8. The method according to any one of the preceding claims, wherein, The method further includes: In response to the driver’s operation signal regarding the steering device, the vehicle (1) is controlled to stop driving in crab mode, and the vehicle (1) is controlled based on the operation signal.

9. The method according to any one of the preceding claims, wherein, Based at least on the driving environment information, an end-to-end model is used to determine the planned driving path of the vehicle (1) in crab mode to avoid the first obstacle, as well as the corresponding control commands for the vehicle (1), to control the vehicle (1) to drive in crab mode along the planned driving path to pass the first obstacle, wherein, During the process of controlling the vehicle (1) to travel past the first obstacle in crab mode according to the planned driving path, the planned driving path and the corresponding control commands of the vehicle (1) are adjusted by the end-to-end model based on the detected driving environment information, so that there are no obstacles in the driving area of ​​the vehicle (1) along the adjusted planned driving path.

10. A driver assistance system (10), the driver assistance system (10) comprising the following components: An environmental sensing unit (11) is configured to detect driving environment information of the vehicle (1); Control unit (12) for performing the method according to any one of claims 1 to 9.

11. The driver assistance system (10) according to claim 10, wherein, The environmental perception unit includes one or more of the following devices: vehicle-mounted camera, millimeter-wave radar, lidar, and ultrasonic radar.

12. The driver assistance system (10) according to claim 11, wherein, The control unit (12) is integrated into the vehicle camera, and an end-to-end model is deployed in the control unit (12). The end-to-end model determines the planned driving path of the vehicle (1) to avoid the first obstacle and the corresponding control command of the vehicle (1) based at least on the driving environment information. The vehicle (1) is controlled to drive past the first obstacle in a crab-like mode according to the planned driving path. During the process of controlling the vehicle (1) to drive past the first obstacle in a crab-like mode according to the planned driving path, the planned driving path and the corresponding control command of the vehicle (1) are adjusted based on the detected driving environment information through the end-to-end model so that there are no obstacles in the driving area of ​​the vehicle (1) along the planned driving path.

13. A vehicle (1) comprising a driver assistance system (10) according to any one of claims 10 to 12.

14. A computer program product, such as a computer-readable program carrier, comprising or storing computer program instructions that, when executed by a processor, at least auxiliaryly implement the steps of the method according to any one of claims 1 to 9.

Images