Vehicle steering obstacle avoidance method and device, vehicle, storage medium and product

Abstract

The invention discloses a vehicle steering obstacle avoidance method and device, a vehicle, a storage medium and a product, and relates to the technical field of automatic driving, and the method comprises the steps: obtaining environment perception data in a driving scene where the vehicle is located, and determining whether there is a risk obstacle in the driving scene based on the environment perception data, the risk obstacle is an obstacle whose collision risk with the vehicle is greater than a preset risk threshold; determining a plurality of obstacle avoidance paths with different curvatures based on the environmental perception data under the condition that a risk obstacle exists in the driving scene; and determining a target path from the obstacle avoidance paths, and controlling the vehicle to perform steering obstacle avoidance along the target path. The vehicle steering obstacle avoidance difficulty can be reduced, so that the driving safety is improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a vehicle steering obstacle avoidance method, device, vehicle, storage medium and product. Background Technology

[0002] With the continuous development of autonomous driving technology, AES (Automatic Emergency Steering) is a core component of vehicle ADAS (Advanced Driver Assistance Systems), which aims to avoid collisions through active steering intervention.

[0003] Currently, after a vehicle senses a collision risk, it typically uses a fixed curvature to determine the obstacle avoidance path. Specifically, when facing a collision risk, the vehicle assesses whether there is sufficient safety space and enough time to steer and avoid the obstacle according to a fixed curvature. If the space and time requirements are met, the vehicle is controlled to travel along the obstacle avoidance path determined by the fixed curvature. In other words, obstacle avoidance based on a fixed curvature places high demands on the driving scenario, making obstacle avoidance more difficult. For example, in narrow roads, with multiple obstacles, or complex road conditions, the obstacle avoidance path based on a fixed curvature may not be suitable for the actual environment, leading to obstacle avoidance failure and thus affecting driving safety.

[0004] Therefore, how to reduce the difficulty of vehicle steering and obstacle avoidance in order to improve driving safety is an urgent problem that needs to be solved. Summary of the Invention

[0005] The main purpose of this application is to provide a vehicle steering obstacle avoidance method, device, vehicle, storage medium and product, which aims to reduce the difficulty of vehicle steering obstacle avoidance and improve driving safety.

[0006] To achieve the above objectives, this application provides a vehicle steering obstacle avoidance method, the vehicle steering obstacle avoidance method comprising:

[0007] The system acquires environmental perception data of the driving scenario in which the vehicle is located, and determines whether there are any risk obstacles in the driving scenario based on the environmental perception data. The risk obstacles are obstacles whose collision risk with the vehicle is greater than a preset risk threshold.

[0008] In the case of the aforementioned risky obstacle in the driving scenario, multiple obstacle avoidance paths with different curvatures are determined based on the environmental perception data.

[0009] A target path is determined from the various obstacle avoidance paths, and the vehicle is controlled to steer and avoid obstacles along the target path.

[0010] In one embodiment, the step of determining whether there are risk obstacles in the driving scenario based on the environmental perception data includes:

[0011] Based on the environmental perception data, determine whether there are potential obstacles in the driving scenario;

[0012] In the driving scenario where there are potential obstacles, the collision risk between the potential obstacle and the vehicle is determined based on the location information and movement trend information of the potential obstacle in the environmental perception data.

[0013] If the collision risk is greater than the preset risk threshold, the potential obstacle is identified as a risk obstacle.

[0014] In one embodiment, the environmental perception data includes road surface geometry information, and the step of determining whether there are potential obstacles in the driving scenario based on the environmental perception data includes:

[0015] Based on the road surface geometry information, the depression area on the vehicle's driving path is determined;

[0016] If the geometric features of the recessed area satisfy a preset instability condition, the recessed area is determined to be a potential obstacle.

[0017] In one embodiment, the environmental perception data further includes road surface friction coefficient, road surface material, and map data. The step of determining multiple obstacle avoidance paths with different curvatures based on the environmental perception data includes:

[0018] A reference friction coefficient is obtained based on the road surface material, wherein the reference friction coefficient refers to the friction coefficient of the vehicle on the dry road surface of the road surface material;

[0019] The target collision time is obtained by correcting the reference collision time based on the road surface friction coefficient and the reference friction coefficient, wherein the reference collision time refers to the time required for the vehicle to collide with the risk obstacle, calculated based on the reference friction coefficient.

[0020] The vehicle's avoidance space is determined based on the map data;

[0021] Based on the target collision time and the avoidable space, multiple obstacle avoidance paths with different curvatures are determined.

[0022] In one embodiment, the step of determining the target path from each of the obstacle avoidance paths includes:

[0023] Monitor whether the driver of the vehicle intends to steer to avoid obstacles;

[0024] If the driver is detected to have a steering intention to avoid obstacles, a target path is determined from each of the obstacle avoidance paths based on the steering intention to avoid obstacles;

[0025] If the driver is found to have no intention to steer to avoid obstacles, the path with the smallest total lateral acceleration among the obstacle avoidance paths is determined as the target path based on the total lateral acceleration corresponding to each obstacle avoidance path. The total lateral acceleration is the algebraic sum of the lateral accelerations generated by the vehicle during the steering and straightening phases of the obstacle avoidance path.

[0026] In one embodiment, the step of determining a target path from each of the obstacle avoidance paths based on the steering obstacle avoidance intention includes:

[0027] Based on the steering obstacle avoidance intention, it is determined whether there is a first path among the obstacle avoidance paths, wherein the first path and the steering direction of the steering obstacle avoidance intention are the same;

[0028] In the case where there are multiple first paths among the obstacle avoidance paths, the path with the smallest total lateral acceleration is determined as the target path based on the total lateral acceleration corresponding to each first path.

[0029] If there is a single first path among all the obstacle avoidance paths, the first path shall be taken as the target path;

[0030] If the first path does not exist among the obstacle avoidance paths, the path with the smallest total lateral acceleration among the obstacle avoidance paths is determined as the target path based on the total lateral acceleration corresponding to each of the obstacle avoidance paths.

[0031] In one embodiment, the step of controlling the vehicle to steer and avoid obstacles along the target path includes:

[0032] The range of steering torque required for the vehicle to travel along the target path is determined based on the target path.

[0033] If the driver is detected to have a steering intention to avoid an obstacle, the steering torque input by the driver is obtained;

[0034] The torque to be compensated is determined based on the steering torque range and the steering torque, wherein the vector sum of the torque to be compensated and the steering torque is within the steering torque range;

[0035] Based on the torque to be compensated, the vehicle is controlled to steer and avoid obstacles along the target path;

[0036] If the driver is found to have no intention to steer to avoid obstacles, the vehicle is controlled to steer along the target path to avoid obstacles based on the steering torque range.

[0037] Furthermore, to achieve the above objectives, this application also provides a vehicle steering obstacle avoidance device, the vehicle steering obstacle avoidance device comprising:

[0038] The perception module is used to acquire environmental perception data in the driving scenario where the vehicle is located, and to determine whether there are risk obstacles in the driving scenario based on the environmental perception data. The risk obstacle is an obstacle whose collision risk with the vehicle is greater than a preset risk threshold.

[0039] The path planning module is used to determine multiple obstacle avoidance paths with different curvatures based on the environmental perception data when the risky obstacle exists in the driving scenario.

[0040] The control module is used to determine a target path from each of the obstacle avoidance paths and control the vehicle to steer and avoid obstacles along the target path.

[0041] In addition, to achieve the above objectives, this application also provides a storage medium, which is a computer-readable storage medium, on which a program for implementing a vehicle steering obstacle avoidance method is stored, and the program for implementing the vehicle steering obstacle avoidance method is executed by a processor to implement the steps of the vehicle steering obstacle avoidance method as described above.

[0042] In addition, to achieve the above objectives, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle steering obstacle avoidance method described above.

[0043] This application provides a vehicle steering obstacle avoidance method. First, the application acquires environmental perception data of the driving scenario in which the vehicle is located. Based on the environmental perception data, it determines whether there are obstacles in the current driving scenario whose collision risk between vehicles is greater than a preset risk threshold, i.e., risk obstacles. If there are risk obstacles in the current driving scenario, multiple obstacle avoidance paths with different curvatures are determined based on the environmental perception data. A target path is determined from each obstacle avoidance path, and the vehicle is controlled to drive along the target path to perform steering obstacle avoidance.

[0044] In summary, this application, upon detecting the presence of hazardous obstacles in the vehicle's driving scenario, determines multiple obstacle avoidance paths with varying curvatures based on environmental perception data, and then selects a target path from these paths to guide steering and obstacle avoidance. Thus, compared to traditional methods using fixed curvature for steering and obstacle avoidance, this application enhances the adaptability of the steering and obstacle avoidance function to different driving scenarios by providing multiple obstacle avoidance paths with varying curvatures, reduces the difficulty of obstacle avoidance, and thereby improves driving safety. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a flowchart illustrating the first embodiment of the vehicle steering obstacle avoidance method of this application;

[0048] Figure 2 This is a schematic diagram of the vehicle obstacle avoidance process involved in an embodiment of the vehicle steering obstacle avoidance method of this application;

[0049] Figure 3 This is a schematic diagram of the vehicle obstacle avoidance system architecture involved in an embodiment of the vehicle steering obstacle avoidance method of this application;

[0050] Figure 4 This is a schematic diagram of the modular structure of the vehicle steering obstacle avoidance device of this application;

[0051] Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the vehicle steering obstacle avoidance method in the embodiments of this application.

[0052] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0053] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0054] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solution of this application is: to acquire environmental perception data of the driving scenario in which the vehicle is located, and to determine whether there are risk obstacles in the driving scenario based on the environmental perception data, wherein the risk obstacle is an obstacle whose collision risk with the vehicle is greater than a preset risk threshold; if the risk obstacle exists in the driving scenario, to determine multiple obstacle avoidance paths with different curvatures based on the environmental perception data; to determine a target path from each of the obstacle avoidance paths, and to control the vehicle to turn and avoid obstacles along the target path.

[0056] Currently, after a vehicle senses a collision risk, it typically uses a fixed curvature to determine the obstacle avoidance path. Specifically, when facing a collision risk, the vehicle assesses whether there is sufficient safety space and enough time to steer and avoid the obstacle according to a fixed curvature. If the space and time requirements are met, the vehicle is controlled to travel along the obstacle avoidance path determined by the fixed curvature. In other words, obstacle avoidance based on a fixed curvature places high demands on the driving scenario, making obstacle avoidance more difficult. For example, in narrow roads, with multiple obstacles, or complex road conditions, the obstacle avoidance path based on a fixed curvature may not be suitable for the actual environment, leading to obstacle avoidance failure and thus affecting driving safety.

[0057] Therefore, how to reduce the difficulty of vehicle steering and obstacle avoidance in order to improve driving safety is an urgent problem that needs to be solved.

[0058] This application, upon detecting the presence of hazardous obstacles in the vehicle's driving scenario, determines multiple obstacle avoidance paths with varying curvatures based on environmental perception data, and then selects a target path from these paths to guide steering and obstacle avoidance. Thus, compared to traditional methods using fixed curvature for steering and obstacle avoidance, this application enhances the adaptability of the steering and obstacle avoidance function to different driving scenarios by providing multiple obstacle avoidance paths with varying curvatures, reducing the difficulty of obstacle avoidance and thereby improving driving safety.

[0059] It should be noted that the executing entity of the vehicle steering obstacle avoidance method in various embodiments of this application can be a vehicle obstacle avoidance system, or a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a vehicle capable of performing the above functions. This embodiment does not specifically limit this. The following uses a vehicle obstacle avoidance system as the executing entity to describe this embodiment and the following embodiments.

[0060] Based on this, this application proposes a vehicle steering obstacle avoidance method according to the first embodiment. Please refer to [link / reference]. Figure 1 The vehicle steering obstacle avoidance method includes steps S10 to S30:

[0061] Step S10: Obtain environmental perception data of the driving scenario in which the vehicle is located, and determine whether there are risk obstacles in the driving scenario based on the environmental perception data, wherein the risk obstacle is an obstacle whose collision risk with the vehicle is greater than a preset risk threshold;

[0062] It should be noted that the driving scenario in which the vehicle is located can be understood as the area that the vehicle's environmental perception function can perceive. The vehicle's environmental perception module includes, but is not limited to, LiDAR, binocular cameras, millimeter-wave radar, ultrasonic sensors, and infrared sensors. The vehicle obstacle avoidance system of this application includes a risk prediction module, used to determine the collision risk between the vehicle and obstacles based on vehicle information, obstacle information, and environmental information. Vehicle information includes, but is not limited to, vehicle position information, vehicle size information, and vehicle driving information (speed, acceleration, and direction of travel). Obstacle information includes, but is not limited to, obstacle position information, obstacle size information, and obstacle movement trend information. Environmental information includes, but is not limited to, road conditions, traffic conditions, and weather conditions. Furthermore, the risk prediction module is trained using a feature vector pre-constructed from vehicle information, obstacle information, and environmental information in a driving scenario as model input data, and the actual collision risk between the vehicle and obstacles as model label data. This application does not limit the model type of the risk prediction module; it can be a deep learning model. A risk threshold is pre-set; this application does not limit the specific size of this risk threshold, and it can be set within the range of risk values ​​according to actual needs.

[0063] The system obtains environmental perception data of the driving scenario in which the vehicle is located from the vehicle's environmental perception module, and determines the collision risk between each obstacle and the vehicle in the current driving scenario based on the environmental perception data. It also identifies obstacles whose collision risk with the vehicle is greater than a preset risk threshold (hereinafter referred to as risk obstacles for distinction).

[0064] Step S20: In the case of the risky obstacle in the driving scenario, determine multiple obstacle avoidance paths with different curvatures based on the environmental perception data;

[0065] When a potential obstacle is detected in the current driving scenario, multiple obstacle avoidance paths with different curvatures are determined based on environmental perception data. These obstacle avoidance paths are planned routes that can safely circumvent the potential obstacle.

[0066] Step S30: Determine the target path from each of the obstacle avoidance paths, and control the vehicle to steer and avoid obstacles along the target path.

[0067] After obtaining multiple obstacle avoidance paths, an obstacle avoidance path (hereinafter referred to as the target path for distinction) is determined from each obstacle avoidance path based on the preset path selection logic, and then the vehicle is controlled to drive along the target path to avoid obstacles.

[0068] In one feasible implementation, the vehicle obstacle avoidance system includes AES and AEB (Auto Emergency Braking). For example... Figure 2The diagram illustrates the vehicle obstacle avoidance process. When the vehicle senses a potential obstacle, the Automatic Emergency Braking (AEB) first determines whether it can stop to avoid the obstacle. If the AEB can stop and avoid the obstacle, the vehicle is handed over to the AEB for braking. If the AEB cannot safely stop and avoid the obstacle, it checks whether the driver has input steering torque and whether the input torque is sufficient to avoid the obstacle. If the driver has input steering torque and it is sufficient, the vehicle responds to the driver's action and performs steering to avoid the obstacle. If the driver has not input steering torque or the input torque is insufficient to avoid the obstacle, the Automatic Steering (AES) is automatically activated. The AES determines the target path and controls the vehicle to steer along the target path to avoid the obstacle.

[0069] This application embodiment determines multiple obstacle avoidance paths with different curvatures based on environmental perception data when a risky obstacle is detected in the driving scenario where the vehicle is located. From these multiple paths, a target path for guiding steering and obstacle avoidance is then selected. Thus, compared to the traditional method of using a fixed curvature for steering and obstacle avoidance, this application embodiment improves the adaptability of the steering and obstacle avoidance function to different driving scenarios by providing multiple obstacle avoidance paths with different curvatures, reduces the difficulty of obstacle avoidance, and thereby improves driving safety.

[0070] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description and will not be repeated hereafter. Based on this, step S10 may include:

[0071] Step S101: Determine whether there are potential obstacles in the driving scenario based on the environmental perception data;

[0072] It should be noted that the aforementioned potential obstacles can be understood as objects that may pose a threat to or interfere with the normal driving of the vehicle in the current driving scenario.

[0073] Based on environmental perception data, the position, size, and motion trend information of each object in the current driving scenario are determined to determine whether there are potential obstacles in the current driving scenario.

[0074] In this embodiment, the environmental perception data includes road surface geometry information, and step S101 may include:

[0075] Step A10: Determine the concave areas on the vehicle's path to be traveled based on the road surface geometry information;

[0076] It should be noted that the environmental perception data includes road surface geometry information, which includes, but is not limited to, information such as lane line position, road width, road surface slope, and road surface smoothness.

[0077] The system determines the depression areas on the vehicle's path based on road surface geometry information from environmental perception data. In one feasible embodiment, vehicle navigation data can be acquired to determine the vehicle's path. In another feasible embodiment, the vehicle obstacle avoidance system may further include a vehicle path prediction module for predicting the vehicle's path based on vehicle and environmental information.

[0078] Step A20: If the geometric features of the recessed area meet the preset instability conditions, the recessed area is determined to be a potential obstacle.

[0079] It should be noted that the pre-set condition for a depression area to cause vehicle instability can be understood as including the range of values ​​for the geometric features of the depression area that could cause vehicle instability. If the geometric features of the road depression area actually monitored are within the pre-set range, the geometric features of the depression area are considered to meet the pre-set instability condition, and the depression area is identified as a potential obstacle.

[0080] Step S102: In the case of potential obstacles in the driving scenario, based on the location information and movement trend information of the potential obstacles in the environmental perception data, determine the collision risk between the potential obstacles and the vehicle.

[0081] It should be noted that environmental perception data also includes the location information and movement trend information of potential obstacles.

[0082] In the presence of potential obstacles in the current driving scenario, the collision risk between the potential obstacle and the vehicle is determined based on the location and motion trend information of the potential obstacle from environmental perception data. Specifically, the collision risk between the potential obstacle and the vehicle is determined based on vehicle information, obstacle information (including location and motion trend information), and environmental information.

[0083] Step S103: If the collision risk is greater than the preset risk threshold, the potential obstacle is determined to be a risk obstacle.

[0084] Determine whether the collision risk between the potential obstacle and the vehicle is greater than a preset risk threshold. If the collision risk is greater than the preset risk threshold, the current potential obstacle is considered a risk obstacle.

[0085] Thus, by sensing the road surface in a vehicle driving scenario, this application embodiment identifies road depressions that affect safe driving as obstacles to prevent the vehicle chassis from colliding with the depressions or causing the vehicle to become unstable. This improves the comprehensiveness of obstacle recognition and enhances driving safety.

[0086] In this embodiment, the environmental perception data further includes road surface friction coefficient, road surface material, and map data. Step S20 may include:

[0087] Step S201: Obtain a reference friction coefficient based on the road surface material, wherein the reference friction coefficient refers to the friction coefficient of the vehicle on the dry road surface of the road surface material;

[0088] It should be noted that the environmental perception data also includes road surface friction coefficient, road surface material, and map data. The map data can be point cloud map data constructed based on the locations of various objects in the current driving environment. The friction coefficients (i.e., baseline friction coefficients) of various road surface materials under dry conditions are pre-determined, and a mapping relationship between road surface materials and baseline friction coefficients is established. The baseline friction coefficient is obtained based on the road surface material from the environmental perception data.

[0089] Step S202: Correct the reference collision time based on the road surface friction coefficient and the reference friction coefficient to obtain the target collision time, wherein the reference collision time refers to the time required for the vehicle to collide with the risk obstacle, calculated based on the reference friction coefficient;

[0090] It should be noted that the TTC (Time to Collision) between the vehicle and the risk obstacle is calculated based on the reference friction coefficient, which is the reference collision time mentioned above.

[0091] The reference collision time is corrected based on the actual detected road surface friction coefficient and the reference friction coefficient to obtain the corrected collision time (hereinafter referred to as the target collision time for distinction).

[0092] In one feasible implementation, the reference friction coefficient corresponding to the current road surface material is expressed as μ. drg The actual detected road friction coefficient is expressed as μ, and the reference collision time is expressed as TTC. base Therefore, the formula for calculating the target collision time can be expressed as:

[0093]

[0094] Among them, TTC adj The target collision time is k, and k is a preset weight (empirical value).

[0095] Step S203: Determine the vehicle's avoidance space based on the map data;

[0096] The safe space for the vehicle to avoid obstacles, i.e. the vehicle's avoidable space, is determined based on the point cloud map data in the current driving scenario.

[0097] Step S204: Determine multiple obstacle avoidance paths with different curvatures based on the target collision time and the avoidable space.

[0098] In one feasible implementation, the vehicle's kinematic characteristics are first used as constraints for path generation. These kinematic characteristics include, but are not limited to, maximum steering angle, minimum turning radius, maximum acceleration, and maximum deceleration. The avoidable space is divided into multiple grid cells, and the start and end points of the obstacle avoidance path are determined. The safe curvature range of the vehicle is determined, and multiple different curvature values ​​are selected within this range. Obstacle avoidance paths are constructed in the gridded avoidable space based on different curvatures, path start points, and path end points. Then, the travel time of each obstacle avoidance path is estimated to determine whether the path end point can be reached within the target collision time. Finally, obstacle avoidance paths that meet the conditions are selected.

[0099] Thus, this embodiment of the application corrects the benchmark collision time corresponding to the dry road surface based on the real-time monitored road friction coefficient to obtain a more accurate target collision time, thereby avoiding the safety issues caused by the collision time calculation deviation due to the slippery road surface.

[0100] In this embodiment, step S30 may include:

[0101] Step S30: Monitor whether the driver of the vehicle intends to steer to avoid obstacles;

[0102] In one feasible implementation, by monitoring the rotation angle and speed of the vehicle's steering wheel, it is determined whether the driver has a steering intention. When the steering wheel angle changes and the rotation speed reaches a preset speed threshold, it indicates that the driver is trying to avoid an obstacle, that is, the driver has a steering intention to avoid the obstacle.

[0103] Step S301: If the driver is detected to have a steering intention to avoid obstacles, a target path is determined from each of the obstacle avoidance paths based on the steering intention to avoid obstacles.

[0104] If the driver is detected to have a steering intention to avoid obstacles, the target path is determined from the obstacle avoidance paths based at least on the driver's steering intention to avoid obstacles.

[0105] In this embodiment, step S301 may include:

[0106] Step B10: Based on the steering obstacle avoidance intention, determine whether there is a first path among the obstacle avoidance paths, wherein the first path and the steering direction of the steering obstacle avoidance intention are the same;

[0107] It should be noted that obstacle avoidance paths typically include turning sections and straightening sections, with the turning sections providing turning direction information.

[0108] Determine the steering intention and the steering direction information of each obstacle avoidance path. Based on the steering direction information, determine the obstacle avoidance path that is consistent with the steering direction of the driver's steering intention (hereinafter referred to as the first path for distinction).

[0109] Step B20: In the case that there are multiple first paths among the obstacle avoidance paths, the path with the smallest total lateral acceleration is determined as the target path based on the total lateral acceleration corresponding to each first path.

[0110] Determine the number of first paths in each obstacle avoidance path. If there are multiple first paths in each obstacle avoidance path, determine the path with the smallest total lateral acceleration from among the first paths as the target path based on the total lateral acceleration corresponding to each first path.

[0111] Step B30: If there is a single first path among all the obstacle avoidance paths, the first path shall be taken as the target path.

[0112] If only one first path exists among all obstacle avoidance paths, then that first path is directly taken as the target path.

[0113] Step B40: If the first path does not exist among the obstacle avoidance paths, the path with the smallest total lateral acceleration among the obstacle avoidance paths is determined as the target path based on the total lateral acceleration corresponding to each obstacle avoidance path.

[0114] If no first path exists among the obstacle avoidance paths, the path with the smallest total lateral acceleration among all obstacle avoidance paths is determined as the target path based on the total lateral acceleration corresponding to each obstacle avoidance path. That is, it can be understood that when there is no path in the same turning direction as the driver's intention to avoid the obstacle, the most comfortable path is selected as the target path based on the logic that the smaller the total lateral acceleration, the higher the passenger comfort.

[0115] Step S302: If it is detected that the driver does not intend to turn to avoid obstacles, the path with the smallest total lateral acceleration among the obstacle avoidance paths is determined as the target path based on the total lateral acceleration corresponding to each obstacle avoidance path. The total lateral acceleration is the algebraic sum of the lateral accelerations generated by the vehicle during the turning phase and the straightening phase of the obstacle avoidance path.

[0116] It should be noted that the total lateral acceleration corresponding to the obstacle avoidance path refers to the algebraic sum of the lateral accelerations generated by the vehicle during the turning and straightening phases of the obstacle avoidance path. It can be understood that the total lateral acceleration is obtained based on the vehicle's kinematic characteristics and the obstacle avoidance path prediction.

[0117] If the driver is not detected to be attempting to steer to avoid obstacles, the total lateral acceleration corresponding to each obstacle avoidance path is determined, and the path with the minimum total lateral acceleration is selected as the target path. It should be understood that the lower the lateral acceleration generated during vehicle movement, the greater the passenger comfort.

[0118] Thus, in this embodiment of the application, when a first path exists among the obstacle avoidance paths that is in the same direction as the intended steering obstacle avoidance, the target path with the highest comfort level is determined from the first path to improve the user experience while enhancing steering obstacle avoidance efficiency. Furthermore, when no first path exists among the obstacle avoidance paths that is in the same direction as the intended steering obstacle avoidance, the path with the highest comfort level among the obstacle avoidance paths is selected as the target path to further improve the user experience.

[0119] In this embodiment, step S30 may include:

[0120] Step S303: Determine the range of steering torque required for the vehicle to travel along the target path based on the target path;

[0121] Determine the curvature of the target path and the current driving state of the vehicle. Based on the vehicle dynamics model and steering system characteristics, establish the mathematical relationship between steering torque, path geometry, and vehicle state. Determine the steering torque required at each point on the target path. Considering driving safety margin and target collision time, determine the steering torque range corresponding to each point on the target path.

[0122] Step S304: If the driver is detected to have a steering intention to avoid obstacles, the steering torque input by the driver is obtained;

[0123] When the driver is detected to have a steering intention to avoid obstacles, the actual steering torque input by the driver is obtained.

[0124] Step S305: Determine the torque to be compensated based on the steering torque range and the steering torque, wherein the vector sum of the torque to be compensated and the steering torque is within the steering torque range;

[0125] The steering torque is compensated based on the actual steering torque input by the driver within the steering torque range to determine the value of the torque to be compensated. Essentially, the vector sum of the torque to be compensated and the steering torque input by the driver should exactly meet the steering torque range requirement.

[0126] Step S306: Based on the torque to be compensated, control the vehicle to steer and avoid obstacles along the target path.

[0127] The driver's input torque is compensated based on the torque to be compensated, so that the vehicle can be controlled to travel along the target path according to the compensated torque, thereby achieving obstacle avoidance.

[0128] In one feasible implementation, such as Figure 3 The diagram shows the architecture of a vehicle obstacle avoidance system. The system includes an environmental perception module, an AES (Automatic Steering Module), and a PSCM (Power Steering Control Module). The AES is communicatively connected to both the environmental perception module and the PSCM. Compared to the traditional method where the AES connects to the PSCM via the vehicle's VCU, this embodiment enables faster steering obstacle avoidance control.

[0129] Step S307: If it is detected that the driver does not intend to steer to avoid obstacles, control the vehicle to steer to avoid obstacles along the target path based on the steering torque range;

[0130] If the driver does not show any intention to steer to avoid the obstacle, the vehicle is controlled to travel along the target path based on the steering torque range in order to avoid the obstacle.

[0131] Thus, in this embodiment of the application, the vehicle's AES performs positive or negative compensation on the steering torque input by the driver, enabling the driver to participate in steering and obstacle avoidance together with the AES, avoiding human-machine decision-making conflicts, and improving the generalization capability of the steering and obstacle avoidance function of this application.

[0132] This application also provides a vehicle steering obstacle avoidance device; please refer to... Figure 4 The vehicle steering obstacle avoidance device includes:

[0133] The perception module 10 is used to acquire environmental perception data in the driving scenario where the vehicle is located, and to determine whether there are risk obstacles in the driving scenario based on the environmental perception data. The risk obstacle is an obstacle whose collision risk with the vehicle is greater than a preset risk threshold.

[0134] Path planning module 20 is used to determine multiple obstacle avoidance paths with different curvatures based on the environmental perception data when the risk obstacle exists in the driving scenario.

[0135] The control module 30 is used to determine a target path from each of the obstacle avoidance paths and control the vehicle to turn and avoid obstacles along the target path.

[0136] Optionally, the sensing module 10 is further configured to:

[0137] Based on the environmental perception data, determine whether there are potential obstacles in the driving scenario;

[0138] In the driving scenario where there are potential obstacles, the collision risk between the potential obstacle and the vehicle is determined based on the location information and movement trend information of the potential obstacle in the environmental perception data.

[0139] If the collision risk is greater than the preset risk threshold, the potential obstacle is identified as a risk obstacle.

[0140] Optionally, the environmental perception data includes road surface geometry information, and the perception module 10 is further used for:

[0141] Based on the road surface geometry information, the depression area on the vehicle's driving path is determined;

[0142] If the geometric features of the recessed area satisfy a preset instability condition, the recessed area is determined to be a potential obstacle.

[0143] Optionally, the environmental perception data also includes road surface friction coefficient, road surface material, and map data, and the path planning module 20 is further used for:

[0144] A reference friction coefficient is obtained based on the road surface material, wherein the reference friction coefficient refers to the friction coefficient of the vehicle on the dry road surface of the road surface material;

[0145] The target collision time is obtained by correcting the reference collision time based on the road surface friction coefficient and the reference friction coefficient, wherein the reference collision time refers to the time required for the vehicle to collide with the risk obstacle, calculated based on the reference friction coefficient.

[0146] The vehicle's avoidance space is determined based on the map data;

[0147] Based on the target collision time and the avoidable space, multiple obstacle avoidance paths with different curvatures are determined.

[0148] Optionally, the control module 30 is further configured to:

[0149] Monitor whether the driver of the vehicle intends to steer to avoid obstacles;

[0150] If the driver is detected to have a steering intention to avoid obstacles, a target path is determined from each of the obstacle avoidance paths based on the steering intention to avoid obstacles;

[0151] If the driver is found to have no intention to steer to avoid obstacles, the path with the smallest total lateral acceleration among the obstacle avoidance paths is determined as the target path based on the total lateral acceleration corresponding to each obstacle avoidance path. The total lateral acceleration is the algebraic sum of the lateral accelerations generated by the vehicle during the steering and straightening phases of the obstacle avoidance path.

[0152] Optionally, the control module 30 is further configured to:

[0153] Based on the steering obstacle avoidance intention, it is determined whether there is a first path among the obstacle avoidance paths, wherein the first path and the steering direction of the steering obstacle avoidance intention are the same;

[0154] In the case where there are multiple first paths among the obstacle avoidance paths, the path with the smallest total lateral acceleration is determined as the target path based on the total lateral acceleration corresponding to each first path.

[0155] If there is a single first path among all the obstacle avoidance paths, the first path shall be taken as the target path;

[0156] If the first path does not exist among the obstacle avoidance paths, the path with the smallest total lateral acceleration among the obstacle avoidance paths is determined as the target path based on the total lateral acceleration corresponding to each of the obstacle avoidance paths.

[0157] Optionally, the control module 30 is further configured to:

[0158] The range of steering torque required for the vehicle to travel along the target path is determined based on the target path.

[0159] If the driver is detected to have a steering intention to avoid an obstacle, the steering torque input by the driver is obtained;

[0160] The torque to be compensated is determined based on the steering torque range and the steering torque, wherein the vector sum of the torque to be compensated and the steering torque is within the steering torque range;

[0161] Based on the torque to be compensated, the vehicle is controlled to steer and avoid obstacles along the target path;

[0162] If the driver is found to have no intention to steer to avoid obstacles, the vehicle is controlled to steer along the target path to avoid obstacles based on the steering torque range.

[0163] The vehicle steering obstacle avoidance device provided in this application, employing the vehicle steering obstacle avoidance method described in the above embodiments, can solve the technical problem of how to reduce the difficulty of vehicle steering obstacle avoidance and thus improve driving safety. Compared with the prior art, the beneficial effects of the vehicle steering obstacle avoidance device provided in this application are the same as those of the vehicle steering obstacle avoidance method described in the above embodiments, and other technical features in the vehicle steering obstacle avoidance device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0164] This application provides a vehicle, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform the vehicle steering obstacle avoidance method of Embodiment 1 described above.

[0165] The following is for reference. Figure 5 It shows a structural schematic diagram of a vehicle suitable for implementing the embodiments of this application. Figure 5 The vehicle shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0166] like Figure 5 As shown, the vehicle may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for vehicle operation. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the vehicle to exchange data via wireless or wired communication with other devices. Although the diagram shows vehicles with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0167] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0168] The vehicle provided in this application, employing the vehicle steering obstacle avoidance method described in the above embodiments, can solve the technical problem of how to reduce the difficulty of vehicle steering obstacle avoidance and thus improve driving safety. Compared with the prior art, the beneficial effects of the vehicle provided in this application are the same as those of the vehicle steering obstacle avoidance method provided in the above embodiments, and other technical features of the vehicle are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0169] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0170] 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 scope of the technology 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.

[0171] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the vehicle steering obstacle avoidance method in the above embodiments.

[0172] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0173] The aforementioned computer-readable storage medium may be included in the vehicle or may exist independently and not installed in the vehicle.

[0174] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a vehicle, cause the vehicle to: acquire environmental perception data of the driving scenario in which the vehicle is located; determine, based on the environmental perception data, whether there are any risky obstacles in the driving scenario, wherein the risky obstacles are obstacles whose collision risk with the vehicle is greater than a preset risk threshold; if the risky obstacles exist in the driving scenario, determine multiple obstacle avoidance paths with different curvatures based on the environmental perception data; determine a target path from each of the obstacle avoidance paths, and control the vehicle to steer and avoid obstacles along the target path.

[0175] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0176] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0177] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0178] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described vehicle steering obstacle avoidance method. This solves the technical problem of how to reduce the difficulty of vehicle steering obstacle avoidance and thus improve driving safety. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the vehicle steering obstacle avoidance method provided in the above embodiments, and will not be repeated here.

[0179] This application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle steering obstacle avoidance method described above.

[0180] The computer program product provided in this application can reduce the difficulty of vehicle steering and obstacle avoidance, thereby improving driving safety. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the vehicle steering and obstacle avoidance method provided in the above embodiments, and will not be repeated here.

[0181] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A vehicle steering obstacle avoidance method, characterized in that, The vehicle steering obstacle avoidance method includes: The system acquires environmental perception data of the driving scenario in which the vehicle is located, and determines whether there are any risk obstacles in the driving scenario based on the environmental perception data. The risk obstacles are obstacles whose collision risk with the vehicle is greater than a preset risk threshold. In the case of the aforementioned risky obstacle in the driving scenario, multiple obstacle avoidance paths with different curvatures are determined based on the environmental perception data. A target path is determined from the various obstacle avoidance paths, and the vehicle is controlled to steer and avoid obstacles along the target path.

2. The vehicle steering obstacle avoidance method as described in claim 1, characterized in that, The step of determining whether there are risk obstacles in the driving scenario based on the environmental perception data includes: Based on the environmental perception data, determine whether there are potential obstacles in the driving scenario; In the driving scenario where there are potential obstacles, the collision risk between the potential obstacle and the vehicle is determined based on the location information and movement trend information of the potential obstacle in the environmental perception data. If the collision risk is greater than the preset risk threshold, the potential obstacle is determined to be a risk obstacle.

3. The vehicle steering obstacle avoidance method as described in claim 2, characterized in that, The environmental perception data includes road surface geometry information, and the step of determining whether there are potential obstacles in the driving scenario based on the environmental perception data includes: Based on the road surface geometry information, the depression area on the vehicle's driving path is determined; If the geometric features of the recessed area satisfy a preset instability condition, the recessed area is determined to be a potential obstacle.

4. The vehicle steering obstacle avoidance method as described in claim 1, characterized in that, The environmental perception data also includes road surface friction coefficient, road surface material, and map data. The step of determining multiple obstacle avoidance paths with different curvatures based on the environmental perception data includes: A reference friction coefficient is obtained based on the road surface material, wherein the reference friction coefficient refers to the friction coefficient of the vehicle on the dry road surface of the road surface material; The target collision time is obtained by correcting the reference collision time based on the road surface friction coefficient and the reference friction coefficient, wherein the reference collision time refers to the time required for the vehicle to collide with the risk obstacle, calculated based on the reference friction coefficient. The vehicle's avoidance space is determined based on the map data; Based on the target collision time and the avoidable space, multiple obstacle avoidance paths with different curvatures are determined.

5. The vehicle steering obstacle avoidance method as described in claim 1, characterized in that, The step of determining the target path from each of the obstacle avoidance paths includes: Monitor whether the driver of the vehicle intends to steer to avoid obstacles; If the driver is detected to have a steering intention to avoid obstacles, a target path is determined from each of the obstacle avoidance paths based on the steering intention to avoid obstacles; If the driver is found to have no intention to steer to avoid obstacles, the path with the smallest total lateral acceleration among the obstacle avoidance paths is determined as the target path based on the total lateral acceleration corresponding to each obstacle avoidance path. The total lateral acceleration is the algebraic sum of the lateral accelerations generated by the vehicle during the steering and straightening phases of the obstacle avoidance path.

6. The vehicle steering obstacle avoidance method as described in claim 5, characterized in that, The step of determining the target path from each of the obstacle avoidance paths based on the steering obstacle avoidance intention includes: Based on the steering obstacle avoidance intention, it is determined whether there is a first path among the obstacle avoidance paths, wherein the first path and the steering direction of the steering obstacle avoidance intention are the same; In the case where there are multiple first paths among the obstacle avoidance paths, the path with the smallest total lateral acceleration is determined as the target path based on the total lateral acceleration corresponding to each first path. If there is a single first path among all the obstacle avoidance paths, the first path shall be taken as the target path; If the first path does not exist among the obstacle avoidance paths, the path with the smallest total lateral acceleration among the obstacle avoidance paths is determined as the target path based on the total lateral acceleration corresponding to each of the obstacle avoidance paths.

7. The vehicle steering obstacle avoidance method as described in claim 6, characterized in that, The step of controlling the vehicle to steer and avoid obstacles along the target path includes: The range of steering torque required for the vehicle to travel along the target path is determined based on the target path. If the driver is detected to have a steering intention to avoid an obstacle, the steering torque input by the driver is obtained; The torque to be compensated is determined based on the steering torque range and the steering torque, wherein the vector sum of the torque to be compensated and the steering torque is within the steering torque range; Based on the torque to be compensated, the vehicle is controlled to steer and avoid obstacles along the target path; If the driver is found to have no intention to steer to avoid obstacles, the vehicle is controlled to steer along the target path to avoid obstacles based on the steering torque range.

8. A vehicle steering obstacle avoidance device, characterized in that, The vehicle steering obstacle avoidance device includes: The perception module is used to acquire environmental perception data in the driving scenario where the vehicle is located, and to determine whether there are risk obstacles in the driving scenario based on the environmental perception data. The risk obstacle is an obstacle whose collision risk with the vehicle is greater than a preset risk threshold. The path planning module is used to determine multiple obstacle avoidance paths with different curvatures based on the environmental perception data when the risky obstacle exists in the driving scenario. The control module is used to determine a target path from each of the obstacle avoidance paths and control the vehicle to steer and avoid obstacles along the target path.

9. A vehicle, characterized in that, The vehicle includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle steering obstacle avoidance method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the vehicle steering obstacle avoidance method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the vehicle steering obstacle avoidance method as described in any one of claims 1 to 7.

Images