Obstacle avoidance control methods, controllers, systems, and vehicles

Abstract

This application discloses a vehicle obstacle avoidance control method, controller, system, and vehicle, including: controlling different sections of the vehicle's corners to avoid obstacles at their respective corresponding obstacle avoidance distances, wherein the obstacle avoidance distance of each section is determined by the probability of each section colliding with an obstacle along the vehicle's travel path. This application enables more flexible obstacle avoidance detection of potential collisions at the vehicle corners during obstacle avoidance, ensuring the vehicle's intelligent driving performance and improving the user experience to a certain extent.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, specifically to a vehicle obstacle avoidance control method, controller, system, and vehicle. Background Technology

[0002] Fixed-wheel rotation refers to controlling a vehicle by keeping a specific wheel stationary and using that wheel as the center of rotation to control the vehicle's movement. This allows for adjustments to the vehicle's position and posture, and is particularly effective in narrow and confined spaces.

[0003] However, currently, during the fixed wheel rotation process, an octagonal model of the vehicle is usually constructed, that is, an obstacle avoidance distance of equal length is used to control the vehicle's obstacle avoidance. In practical applications, the different obstacle avoidance requirements at different angles during the fixed wheel rotation process are not considered, which to some extent affects the user's driving experience. Summary of the Invention

[0004] This application provides a vehicle obstacle avoidance control method, controller, system, and vehicle, which aims to divide the vehicle's angles into different zones to allow for setting slightly different obstacle avoidance distances based on actual obstacle avoidance needs, thereby enabling obstacle avoidance control of the vehicle and at least partially solving the aforementioned problems.

[0005] Firstly, this application provides a vehicle obstacle avoidance control method, comprising: The vehicle's different corner sections are controlled to avoid obstacles at their respective corresponding obstacle avoidance distances, wherein the obstacle avoidance distance of each section is determined by the probability of each section colliding with an obstacle along the vehicle's travel path.

[0006] In one embodiment of this application, for each corner of the vehicle, the partition of the corner includes at least a first partition near the front or rear of the vehicle, and a second partition near the side of the vehicle.

[0007] In one embodiment of this application, the method further includes: Based on the relative displacement relationship between each zone and the obstacle, obstacle avoidance distances are configured for different zones of each of the vehicle corners. The relative displacement relationship is determined by the target fixed wheel and the direction of rotation of the vehicle.

[0008] In one embodiment of this application, configuring obstacle avoidance distances for different zones of each vehicle corner based on the relative displacement relationship between each zone and the obstacle includes: When the relative displacement between the target section at the corner of the vehicle and the obstacle is close, the first obstacle avoidance distance is taken as the obstacle avoidance distance of the target section. When the relative displacement between the target section at the corner of the vehicle and the obstacle is far away, the second obstacle avoidance distance is taken as the obstacle avoidance distance of the target section. Wherein, the first obstacle avoidance distance is greater than the second obstacle avoidance distance.

[0009] In one embodiment of this application, after configuring obstacle avoidance distances for different zones of each of the vehicle corners, the method further includes: Based on the vehicle's recognition distance error for different obstacles, the obstacle avoidance distance of each of the vehicle's corners is adjusted according to the different partition configurations.

[0010] In one embodiment of this application, the target wheel is determined from the wheels of the vehicle controlled by an independent motor.

[0011] In one embodiment of this application, controlling the vehicle to avoid obstacles includes: When the distance between an obstacle and a corner of the vehicle is detected to be no more than the obstacle avoidance distance corresponding to that corner, the vehicle is controlled to brake.

[0012] In one embodiment of this application, the method further includes: In parking scenarios where the vehicle is either parallel parking in or parallel parking out, the different sections of the vehicle's corners are controlled to avoid obstacles at their respective corresponding obstacle avoidance distances.

[0013] In one embodiment of this application, in the parking scenario of side parking in or side parking out, the obstacle includes at least one of the following: the curb of the parking scenario, the parking in front of or behind the vehicle, fixed obstacles in the environment where the vehicle is located, and moving obstacles.

[0014] In one embodiment of this application, the method further includes: The obstacle avoidance distance is determined based on the vehicle's performance parameters.

[0015] In one embodiment of this application, the method further includes: Display a virtual model of the vehicle to determine the target wheel and direction of rotation for the fixed wheel rotation in response to interactive operations performed on the virtual model.

[0016] In one embodiment of this application, the interactive operation includes a first interactive operation and a second interactive operation. The response to the interactive operation acting on the virtual model, determining the target fixed wheel for the rotation of the fixed wheel and the rotation direction, includes: In response to a first interactive operation applied to the virtual model, the wheel selected by the first interactive operation is used as the target fixed wheel for the fixed wheel rotation. In response to a second interactive operation applied to the virtual model, the direction indicated by the second interactive operation is taken as the rotation direction.

[0017] Secondly, this application also provides a controller that performs obstacle avoidance control on a vehicle by executing the obstacle avoidance control method described in any of the preceding claims.

[0018] Thirdly, this application also provides a vehicle obstacle avoidance control system, including a controller as described above, wherein the controller performs obstacle avoidance control of the vehicle by executing the vehicle obstacle avoidance control method as described in any of the preceding claims.

[0019] Fourthly, this application also provides a vehicle, including the controller as described above, or including the obstacle avoidance control system of the vehicle as described above, or implementing obstacle avoidance control of the vehicle by the obstacle avoidance control method of the vehicle as described in any of the above claims.

[0020] The vehicle obstacle avoidance control method provided in this application, in the scenario of fixed wheel rotation, divides different corners of the vehicle into different zones, and allows different obstacle avoidance distances to be configured for different zones based on the actual obstacle avoidance distance required by each zone. This enables more flexible obstacle avoidance detection of possible collisions at the corners of the vehicle during obstacle avoidance, thereby improving the user experience to a certain extent. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A schematic diagram illustrating the effect of an octagonal vehicle obstacle avoidance model provided by a related technology in an embodiment of this application; Figure 2 A flowchart illustrating the steps of a vehicle obstacle avoidance control method provided in an embodiment of this application; Figure 3a A schematic diagram illustrating the partitioning effect of a certain corner of a vehicle as provided in an embodiment of this application; Figure 3b A schematic diagram illustrating the effect of using a large obstacle avoidance model simultaneously in two sections at the corner of a vehicle, as provided in an embodiment of this application; Figure 3c A schematic diagram illustrating the effect of using a large obstacle avoidance model and a small obstacle avoidance model at two sections at the corner of a vehicle, respectively, as provided in an embodiment of this application; Figure 3dA schematic diagram illustrating the effect of using a small obstacle avoidance model and a large obstacle avoidance model at two sections at the corner of a vehicle, respectively, as provided in an embodiment of this application; Figure 3e This application provides a schematic diagram illustrating the effect of simultaneously using a small obstacle avoidance model in two sections at the corner of a vehicle, as provided in an embodiment of the present application. Figure 4a A schematic diagram illustrating the effect of an obstacle avoidance model used for dividing the corners of a vehicle with the front wheels as fixed wheels, as provided in an embodiment of this application. Figure 4b A schematic diagram illustrating the effect of an obstacle avoidance model used for dividing the corners of a vehicle with the rear wheels as fixed wheels, as provided in an embodiment of this application. Figure 5a This application provides a schematic diagram illustrating the effect of a vehicle exiting a parallel parking scenario, as shown in an embodiment of the present application. Figure 5b This application provides a schematic diagram illustrating the effect of a vehicle parking in a side parking scenario. Figure 6 A schematic diagram illustrating the complete process of fixed wheel rotation in a vehicle, provided as an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] The use of "applies to" or "configured to" in this application implies open and inclusive language, which does not exclude the applicability to or configuration to devices performing additional tasks or steps. Additionally, the use of "based on" implies openness and inclusivity, because processes, steps, calculations, or other actions "based on" one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0025] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0026] To clearly understand the vehicle obstacle avoidance control method, controller, system, and vehicle provided in this application embodiment, the relevant application background of the obstacle avoidance control method provided in this application will be explained below. Specifically, the vehicle obstacle avoidance control method provided in this application is mainly applied to scenarios where the vehicle's wheels rotate at a fixed position. This means that, if the vehicle's wheels are equipped with independently controlled motors, these wheels can be specifically controlled to remain stationary, and the other wheels of the vehicle can be controlled to move along an arc path using this wheel as the center of rotation, thereby adjusting the vehicle's posture. Because the above-mentioned vehicle control method has a relatively small impact on the overall position of the vehicle body, it is particularly suitable for vehicle control in narrow and confined spaces, such as turning in narrow alleyways or parking / exiting from the side of narrow parking spaces.

[0027] Currently, obstacle avoidance during the fixed-wheel rotation process—that is, detecting whether the vehicle will collide with obstacles while traveling along an arc path—is typically achieved using an octagonal obstacle avoidance model. For a more detailed explanation, please refer to [link to relevant documentation]. Figure 1 , Figure 1 This is a schematic diagram illustrating the effect of an octagonal vehicle obstacle avoidance model provided in a related technology, as illustrated in an embodiment of this application. Wherein, as... Figure 1As shown, in the octagonal vehicle obstacle avoidance model, the inner part is a vehicle model constructed based on the vehicle's length, width, and chamfer parameters to describe the vehicle's external contour, while the outer part is an obstacle avoidance model extended based on a specific obstacle avoidance distance for obstacle avoidance control. When the vehicle detects an external obstacle crossing the boundary of the obstacle avoidance model based on its positioning and perception system—in other words, when the distance to the corresponding position of the vehicle is less than the specific obstacle avoidance distance—the vehicle will be controlled to stop to prevent further movement and a collision with the obstacle. Correspondingly, this application does not limit the subsequent vehicle control strategy; for example, it could be to restart the fixed-wheel rotation after the user switches to manual transmission to adjust the vehicle's posture, or to continue the fixed-wheel rotation after detecting obstacle movement.

[0028] However, in the above scheme, the octagonal obstacle avoidance model does not take into account different fixed wheel rotation methods, such as fixed wheel rotation with different fixed wheels or with different rotation directions (clockwise or counterclockwise). The risk of collision at different corner positions (i.e. the obstacle avoidance requirement) is not exactly the same. In particular, for the same corner, the risk of collision in different areas is not necessarily the same. As a result, when using the above obstacle avoidance model for obstacle avoidance, the obstacle avoidance control effect is not ideal. For example, if a smaller obstacle avoidance distance is used, collisions are very likely to occur at some corners of the vehicle or some areas inside them that have a greater need for obstacle avoidance, such as the corners that are usually at the front of the vehicle's direction of travel. On the other hand, if a larger obstacle avoidance distance is used to meet safety redundancy, collisions will occur at some corners of the vehicle or some areas inside them that have a smaller need for obstacle avoidance, such as the corners that are usually at the rear of the vehicle's direction of travel. When an obstacle is detected to be close, even if the vehicle continues to control the rotation of the fixed wheels during actual operation, the vehicle will stop when the position change of the corner is small and there will be no collision with the obstacle. This will affect the effect of the vehicle's fixed wheel rotation.

[0029] To address the aforementioned technical problems, this application proposes a vehicle obstacle avoidance control method specifically for vehicle rotation (steering) scenarios, particularly fixed-wheel rotation. By introducing slightly different obstacle avoidance distances for different corner zones of the vehicle in the vehicle obstacle avoidance model, collision detection at each corner can be performed more flexibly during obstacle avoidance control, thereby significantly improving the obstacle avoidance control effect. Specifically, for ease of understanding, the following will describe the method in conjunction with specific embodiments.

[0030] For details, please refer to Figure 2 , Figure 2 This is a flowchart illustrating the steps of a vehicle obstacle avoidance control method provided in an embodiment of this application. Specifically, it includes step S210: S210, control different sections of the vehicle's corners to avoid obstacles at their respective corresponding obstacle avoidance distances, wherein the obstacle avoidance distance of each section is determined by the probability of each section colliding with an obstacle along the vehicle's travel path.

[0031] Specifically, in one embodiment of this application, the obstacle avoidance control method is typically used for vehicle rotation (in a steering scenario). For ease of understanding, subsequent embodiments of this application will primarily use a fixed-wheel rotation scenario as an example. Fixed-wheel rotation of a vehicle generally refers to controlling the vehicle to keep one specific wheel stationary while controlling the other wheels to move along an arc path with the vehicle as the center of rotation. This application does not limit fixed-wheel rotation; any vehicle movement method that conforms to the above-described movement logic is considered within the scope of protection claimed in this application.

[0032] In particular, in one embodiment of this application, considering that the overall vehicle body position changes very little during the process of adjusting the vehicle's posture by rotating the fixed wheels, it is usually applied in some narrow and confined spaces, such as turning in narrow alleys as mentioned above, or side parking / exiting in narrow parking spaces. Of course, the above scenario description is only for understanding the technical solution of this application and should not be regarded as a limitation of the technical solution of this application. It is also feasible to use the fixed wheel rotation method provided by this application in other scenarios. This application does not limit this. However, in order to clearly understand the complete implementation process and logic of the vehicle obstacle avoidance control method provided by this application, the subsequent embodiments of this application will mainly use the specific application scenario of side parking / exit as an example for explanation. Those skilled in the art can undoubtedly determine the implementation process of the vehicle obstacle avoidance control method in other application scenarios by combining the description of the solution provided by the above application scenarios. Therefore, the embodiments of this application do not limit the relevant descriptions of other application scenarios.

[0033] Furthermore, in one embodiment of this application, the rotation of the vehicle's fixed wheel typically involves two stages: a preparation stage and a control stage. In the preparation stage, a specific target fixed wheel for rotation, serving as the center of rotation, and its corresponding rotation direction, are usually specified through a method such as user setting or program setting. Specifically, to maintain consistency, the rotation direction is usually described using clockwise and counterclockwise directions, which do not change with reference objects (such as different fixed wheels). Therefore, subsequent related embodiments of this application primarily use clockwise and counterclockwise directions as examples. Of course, using other descriptive methods with equivalent effects to clockwise and counterclockwise does not affect the essence of the solution in this application and should therefore generally be considered within the scope of protection claimed in this application.

[0034] Building upon the aforementioned foundation, during the preparation phase of the fixed wheel rotation, after setting the target fixed wheel and rotation direction for the fixed wheel rotation, in some embodiments of this application, based on this information, and according to the potential probability of the vehicle colliding with an object during actual operation, different obstacle avoidance distances are typically set for the corners of each vehicle, especially for different areas of some corners. That is, the obstacle avoidance distance of each section is determined by the probability of each section colliding with an obstacle under the vehicle's travel path, thereby constructing a new vehicle obstacle avoidance model that is different from the octagonal vehicle obstacle avoidance model, which is then input into the vehicle's central control system for reference. At this point, in the subsequent control phase of the vehicle's fixed-wheel rotation, that is, controlling the vehicle to rotate its fixed wheels, i.e., using the given target fixed wheel as the center of rotation and traveling along an arc path, obstacle avoidance control is performed based on the slightly different obstacle avoidance distances configured for different corners and different zones of the vehicle, as indicated by the vehicle obstacle avoidance model. For example, when it is detected that the distance from an obstacle to a certain zone of a certain corner is less than its corresponding obstacle avoidance distance, indicating that if the fixed-wheel rotation continues, the zone of that corner will have a high probability of colliding with the obstacle, the vehicle will be controlled to brake, such as decelerating until it comes to a stop, thereby avoiding a collision. Of course, this application does not restrict the subsequent processing flow, such as allowing the user to manually control the vehicle to adjust its posture and restart the fixed-wheel rotation, or continuing to travel along the initial fixed-wheel rotation flow after the obstacle leaves or is removed. That is to say, in one embodiment of this application, controlling the vehicle to avoid obstacles includes: When the distance between an obstacle and a corner of the vehicle is detected to be no more than the obstacle avoidance distance corresponding to that corner, the vehicle is controlled to brake.

[0035] Specifically, to facilitate understanding of the obstacle avoidance control method provided in the embodiments of this application, the preparation stage and control stage of the vehicle's fixed wheel rotation will be described in detail below with reference to specific embodiments.

[0036] Specifically, in one embodiment of this application, the corners of the vehicle are divided into different zones, and these zones are configured with different obstacle avoidance distances. Specifically, compared to an octagonal vehicle obstacle avoidance model, the obstacle avoidance distances configured for each corner of the vehicle and / or its internal regions are not entirely the same. Specifically, this inconsistency in obstacle avoidance distances includes two possibilities: either at least one corner has multiple regions within it configured with different obstacle avoidance distances, or, for each corner, different internal regions may be configured with the same obstacle avoidance distance, but for all corners, no two obstacle avoidance distances are configured identically. Of course, the solution provided in this application focuses on more refined obstacle avoidance control based on the different needs of the vehicle corners. Therefore, in subsequent embodiments of this application, the first scenario—that is, at least one corner has multiple regions within it configured with different obstacle avoidance distances—will be used as an example for explanation.

[0037] Specifically, for a vehicle corner whose internal area is configured with not entirely identical obstacle avoidance distances, the number of partitions within that corner may vary. This application does not impose any limitation on this in principle. It is understood that the more partitions a corner has, and considering the extreme case where different obstacle avoidance distances are configured for each point on the corner, the obstacle avoidance distance configured for different positions on that corner should theoretically correspond to the displacement distance of the curve traced by that position during the actual rotation of the fixed wheels. This allows for the determination of a line describing the ideal obstacle avoidance distance for that corner. Of course, it is understood that the more partitions a corner has, the higher the computational requirements become, which translates to higher costs in vehicle control applications where real-time performance is crucial. Therefore, based on practical application needs, subsequent embodiments of this application will primarily use the division of a vehicle corner into two main partitions and the setting of different obstacle avoidance distances for each partition as an example, to achieve a certain degree of refined obstacle avoidance control of the vehicle while minimizing computational costs. Of course, with the development of vehicle technology, based on the concept of the solution provided in this application, it is also appropriate to select other more suitable zones to set the obstacle avoidance distance, which should also be considered within the scope of protection claimed in this application.

[0038] Specifically, in one embodiment of this application, for each corner of the vehicle, based on actual needs, the corner is at least divided into a first section near the front or rear of the vehicle, and a second section near the side of the vehicle. The division of the first and second sections is not fixed; in principle, any form that conforms to the above division rules is feasible. For ease of understanding, a typical division method will be used as an example in subsequent embodiments of this application.

[0039] In particular, considering that this application mainly achieves obstacle avoidance control of the vehicle by having at least one corner of the vehicle and multiple areas within it configured with not exactly the same obstacle avoidance distance, that is, in one embodiment of this application, the obstacle avoidance distances configured for the first and second zones with at least one corner of the vehicle are different.

[0040] Specifically, to facilitate understanding of the above content, the following explanation will use a diagram illustrating the zoning effect at a certain corner of a vehicle as an example. Please refer to [link / reference]. Figure 3a , Figure 3a A schematic diagram illustrating the partitioning effect of a certain corner of a vehicle, provided in an embodiment of this application, is described in detail below.

[0041] For details, please refer to Figure 3a In this embodiment, the right front corner of the vehicle will be used as an example for explanation. For this vehicle, the rear wheel axle can be used as the longitudinal axis, i.e., the y-axis in the figure, the center of the rear wheel axle as the origin O, and the direction perpendicular to the longitudinal axis indicating the vehicle's forward direction as the transverse axis, i.e., the x-axis in the figure. This coordinate system is usually a vehicle coordinate system based on dynamics. On this basis, the vehicle width w, vehicle length L, and parameters L1 and L2 describing the chamfer (or rounded corner) at the vehicle corner are usually related to the vehicle model and can usually be extracted from relevant parameters describing the vehicle's external contour. They are mainly used to simulate the vehicle's external contour information. On this basis, the right front corner, i.e., segment B(E)C in the figure, can be further divided into two different sections according to its position, i.e., segment BE and segment CE in the figure. Usually, E is the midpoint of BC. Building upon the foregoing, and further considering the aforementioned descriptions, segment BE is closer to the front of the vehicle, meaning it can be considered the first partition as mentioned above. Segment CE, on the other hand, is closer to the side of the vehicle body, therefore it can be considered the second partition as mentioned above. Based on similar descriptions, those skilled in the art can undoubtedly determine the partitioning at other vehicle corners, and this application does not impose any limitations on this.

[0042] Based on the aforementioned foundation, Figure 3aTaking the right front corner as an example, since different obstacle avoidance distances need to be set for different zones, for example, taking the obstacle avoidance distances W1 and W2 shown in the figure, where the length of W1 is greater than that of W2, at this time, according to different obstacle avoidance distances, that is, W1 and W2, the corresponding points in the B(E)C segment of the vehicle corner can be extended outward to obtain several related points. For example, extending point B outward by the W2 obstacle avoidance distance, we can get point G, and extending it outward by the W1 obstacle avoidance distance, we can get point A. Similarly, extending point E outward by the W2 obstacle avoidance distance, we can get point H, and extending it outward by the W1 obstacle avoidance distance, we can get point F. Extending point C outward by the W2 obstacle avoidance distance, we can get point I, and extending it outward by the W1 obstacle avoidance distance, we can get point D. Therefore, in the lines shown in the figure, AD is parallel to GI and parallel to BC. The distance between AD and BC is W1, and the distance between GI and BC is W2. F and H are the midpoints of AD and GI, respectively. The geometric relationship between the above line segments and points can be used to further assist in constructing the coordinate position of each point in the vehicle coordinate system shown in the figure, so as to be used for subsequent collision detection.

[0043] At this point, taking the right front corner as an example, different obstacle avoidance distances are set for different partitions. For example, if the first partition BE is set to an obstacle avoidance distance of W1 and the second partition CE is set to an obstacle avoidance distance of W2, then the area enclosed by ABEF and CEHI is the detection area used to build the vehicle obstacle avoidance model in this scenario. Similarly, if the first partition BE is set to an obstacle avoidance distance of W2 and the second partition CE is set to an obstacle avoidance distance of W1, then the area enclosed by BEHG and CEFD is the detection area used to build the vehicle obstacle avoidance model in this scenario. Of course, based on the above description, different obstacle avoidance distances can also be configured in this way for other vehicle corners. This application embodiment will not repeat the description. Of course, the above mainly uses different obstacle avoidance distances for different zones in the front right corner as an example. Based on actual needs, the zones in the front right corner can also be set with the same obstacle avoidance distance (the zones in other corners of the vehicle can be set with different obstacle avoidance distances). For example, when the first zone BE and the second zone CE are both set with an obstacle avoidance distance of W1, the area enclosed by ABCD (including areas ABEF and CDFE) is the detection area used to build the vehicle obstacle avoidance model in this scenario. Similarly, when the first zone BE and the second zone CE are both set with an obstacle avoidance distance of W2, the area enclosed by GBCI (including areas BEHG and CEHI) is the detection area used to build the vehicle obstacle avoidance model in this scenario.

[0044] Of course, it should be noted that the above explanation uses the example of dividing the vehicle corner BC into two zones, namely BE and CE. In this case, two different obstacle avoidance distances W1 and W2 can be configured. However, based on actual needs, the vehicle corner BC can be divided into more zones, for example, by dividing it into three segments through its trisection points, and more obstacle avoidance distances can be configured, such as three obstacle avoidance distances. Figure 3aThe geometric relationships between the points and line segments shown can be readily determined by those skilled in the art, by extending each point outward by different obstacle avoidance distances in the case of more partitions, so as to perform subsequent obstacle avoidance detection. This application will not repeat the description in this embodiment.

[0045] Of course, for further simplification, in subsequent embodiments of this application, a large obstacle avoidance model and a small obstacle avoidance model will be used to indicate different obstacle avoidance distances. Specifically, the obstacle avoidance distance of the large obstacle avoidance model is usually greater than that of the small obstacle avoidance model. For example, corresponding to the aforementioned larger obstacle avoidance distance W1, its corresponding region ABCD (regions ABEF, CDFE) can be regarded as the large obstacle avoidance model. For the aforementioned smaller obstacle avoidance distance W2, its corresponding region GBCI (regions BEHG, CEHI) can be regarded as the small obstacle avoidance model. In this case, if only one obstacle avoidance strategy can be adopted for each partition, then each vehicle corner can form the following four combinations:

[0046] At this time, please refer to Figures 3b-3e The diagrams show the effect of the obstacle avoidance model formed at the corresponding corners of the vehicle under different combinations.

[0047] For details, please refer to Figure 3b , Figure 3b The diagram shows the effect of using a large obstacle avoidance model in two zones at the corresponding corners of the vehicle. It can be seen that both zones at the right front corner of the vehicle use a large obstacle avoidance distance. Typically, this corner is at the front of the vehicle along the direction of travel. For example, the diagram shows one possible direction of travel for this corner. In this case, when an obstacle is detected at a large distance from the corner, the vehicle will be controlled to stop to avoid a collision with the obstacle.

[0048] Please see Figure 3c , Figure 3c The diagram illustrates the effects of using the large obstacle avoidance model and the small obstacle avoidance model for the two sections at the corresponding vehicle corners. It can be seen that for the right front corner of the vehicle, the section near the front of the vehicle uses the large obstacle avoidance model, while the section near the side of the vehicle uses the small obstacle avoidance model. Typically, the section near the front of the vehicle is at the front end along the direction of travel, while the section near the side of the vehicle is at the rear end along the direction of travel. For example, the diagram shows one possible direction of travel for this vehicle corner.

[0049] Please see Figure 3d , Figure 3dThe diagram illustrates the effects of using the small obstacle avoidance model and the large obstacle avoidance model for the two sections at the corresponding vehicle corners. It can be seen that for the right front corner of the vehicle, the section near the front of the vehicle uses the small obstacle avoidance model, while the section near the side of the vehicle uses the large obstacle avoidance model. Typically, the section near the front of the vehicle is at the rear end along the direction of travel, while the section near the side of the vehicle is at the front end along the direction of travel. For example, the diagram shows one possible direction of travel for this vehicle corner.

[0050] Please see Figure 3e , Figure 3e This diagram illustrates the effect of using a small obstacle avoidance model simultaneously in two zones at the corresponding corners of the vehicle. In the two zones at the right front corner of the vehicle, a small obstacle avoidance distance is used. Typically, this corner is located at the rear end along the vehicle's direction of travel. For example, the diagram shows one possible direction of travel for this corner. In this case, the corner will only stop when an obstacle is detected at a very small distance to it, in order to avoid a collision with the obstacle.

[0051] It is understood that the above-mentioned solutions have provided detailed illustrations of the effects of configuring the same or different obstacle avoidance distances for each corner of the vehicle. In fact, the configuration of the obstacle avoidance distance for each corner of the vehicle is usually determined by the target wheel for the fixed wheel rotation and the overall rotation direction. The obstacle avoidance distance configured for each specific corner is determined by the relative displacement information of each corner relative to the surrounding obstacles under the given target wheel and rotation direction (such as clockwise or counterclockwise). That is to say, in one embodiment of this application, the method further includes: Based on the relative displacement relationship between each zone and the obstacle, obstacle avoidance distances are configured for different zones of each of the vehicle corners. The relative displacement relationship is determined by the target fixed wheel and the direction of rotation of the vehicle.

[0052] Taking a fixed-wheel rotation scenario as an example, this application will not specifically describe the implementation scheme for the target fixed wheel and rotation direction given the vehicle during the preparation stage of fixed-wheel rotation. It is typically set by the user or program in a specific application scenario, and will be described in detail in subsequent embodiments. Once the target fixed wheel and rotation direction for the vehicle's fixed-wheel rotation are given, considering the movement trajectories of each vehicle corner and its internal zones, the relative displacement information between each zone and potential obstacles within that zone can be analyzed and determined, thereby configuring the obstacle avoidance distance for different zones within the vehicle corner. It is important to note that the obstacles here are not actual obstacles, but rather obstacles that may exist in the vicinity of the zone. That is, assuming obstacles exist, how should the obstacle avoidance distance of the zone be set to effectively control the vehicle's obstacle avoidance? Specifically, for ease of understanding, based on the relative displacement relationship between each zone and the obstacle determined by the target fixed wheel and the rotation direction, the obstacle avoidance distance is configured for different zones of each vehicle corner, including: When the relative displacement between the target section at the corner of the vehicle and the obstacle is close, the first obstacle avoidance distance is taken as the obstacle avoidance distance of the target section. When the relative displacement between the target section at the corner of the vehicle and the obstacle is far away, the second obstacle avoidance distance is taken as the obstacle avoidance distance of the target section. Wherein, the first obstacle avoidance distance is greater than the second obstacle avoidance distance.

[0053] In this context, a relative displacement relationship of "approaching" means that the relative distance between two objects decreases, or the direction of the relative displacement vector reduces the distance between them. For example, this could be a target area at the corner of a vehicle moving towards an obstacle. Conversely, a relative displacement relationship of "moving away" means that the relative distance between two objects increases, or the direction of the relative displacement vector increases the distance between them. For example, this could be a target area at the corner of a vehicle moving away from an obstacle.

[0054] In other words, in the embodiments of this application, when the target wheel and rotation direction are given, the travel path of each corner and its internal partition can be uniquely determined. Based on the displacement relationship between each partition and potential obstacles near that partition, if they are close (e.g., there may be obstacles in front of the travel path of that partition), then to avoid collisions, a larger obstacle avoidance distance needs to be set for that partition, that is, a first obstacle avoidance distance, such as the obstacle avoidance distance W1 mentioned above. Similarly, if the displacement relationship between the partition and potential obstacles near that partition is far (e.g., there may be obstacles behind the travel path of that partition), that is, when the probability of collision between the obstacle and the partition is low, then a smaller obstacle avoidance distance needs to be set for that partition, that is, a second obstacle avoidance distance, such as the obstacle avoidance distance W2 mentioned above, so as to perform more refined obstacle avoidance control.

[0055] For a clearer understanding of the above, please refer to [link / reference]. Figure 4a and Figure 4b , Figure 4a and Figure 4b The diagrams show the obstacle avoidance effects of the vehicle's various corners and internal zones under different fixed wheel and rotation directions, as detailed below.

[0056] For details, please refer to Figure 4a , Figure 4a The diagram illustrates the effect of the obstacle avoidance model used for each corner of the vehicle when the front wheels (including the left and right front wheels) are used as fixed wheels and rotated in counterclockwise and clockwise directions respectively. The details are as follows.

[0057] In the fixed-wheel rotation method, where the left front wheel rotates counterclockwise, both sections of the left front wheel are set to a large obstacle avoidance model. For the two sections of the right front wheel, the first section closer to the front of the vehicle is set to a large obstacle avoidance model, while the second section closer to the side of the vehicle is set to a small obstacle avoidance model. Correspondingly, the two sections of the left rear wheel are set to a small obstacle avoidance model, and the two sections of the right rear wheel are set to a large obstacle avoidance model.

[0058] In the fixed-wheel rotation method, where the left front wheel rotates clockwise, both sections of the left front wheel and the right front wheel are set to small obstacle avoidance models. Correspondingly, the two sections of the left rear wheel are set to large obstacle avoidance models, and for the two sections of the right rear wheel, the first section near the rear of the vehicle is set to a large obstacle avoidance model, while the second section near the side of the vehicle is set to a small obstacle avoidance model.

[0059] In the fixed-wheel rotation method, where the right front wheel rotates counterclockwise, both sections of the left front wheel and the right front wheel are set to small obstacle avoidance models. Correspondingly, for the two sections of the left rear wheel, the first section near the rear of the vehicle is set to a large obstacle avoidance model, and the second section near the side of the vehicle is set to a small obstacle avoidance model. For the two sections of the right rear wheel, both are uniformly set to large obstacle avoidance models.

[0060] In the fixed-wheel rotation method where the right front wheel rotates clockwise, both sections of the left and right front wheels are set to the large obstacle avoidance model. Correspondingly, the two sections of the left rear wheel are set to the large obstacle avoidance model, and for the two sections of the right rear wheel, the first section near the rear of the vehicle is set to the large obstacle avoidance model, while the second section near the side of the vehicle is set to the small obstacle avoidance model.

[0061] For details, please refer to Figure 4b , Figure 4b The diagram illustrates the effect of the obstacle avoidance model used for each corner of the vehicle when the rear wheels (including the left and right rear wheels) are used as fixed wheels and rotate in counterclockwise and clockwise directions, respectively. Details are as follows. It should be noted that using the rear wheels as fixed wheels typically requires a four-motor vehicle, where each wheel is controlled by an independent motor. For three-motor vehicles where the front wheels are controlled by two independent motors and the rear wheels by the same motor, the effect of fixed wheel rotation using the rear wheels cannot usually be achieved because the rear wheels cannot be controlled independently. However, the above description is for illustrative purposes only and does not affect the implementation of this application. Any feasible fixed wheel rotation method can be controlled using the obstacle avoidance control method for vehicles provided in this application.

[0062] In the fixed-wheel rotation method, where the left rear wheel rotates counterclockwise, both sections of the left front wheel are set to a large obstacle avoidance model. For the two sections of the right front wheel, the first section closer to the front of the vehicle is set to a large obstacle avoidance model, while the second section closer to the side of the vehicle is set to a small obstacle avoidance model. Correspondingly, the two sections of the left rear wheel and the two sections of the right rear wheel are set to small obstacle avoidance models.

[0063] In the fixed-wheel rotation method where the left rear wheel rotates clockwise, the two sections of the left front wheel are configured as follows: the first section closer to the front of the vehicle is set to a large obstacle avoidance model, while the second section closer to the side of the vehicle is set to a small obstacle avoidance model. Both sections of the right front wheel are set to a large obstacle avoidance model. Correspondingly, the two sections of the left rear wheel and the two sections of the right rear wheel are set to a large obstacle avoidance model.

[0064] In the fixed-wheel rotation method where the right rear wheel rotates counterclockwise, both sections of the left front wheel are set to a large obstacle avoidance model. For the two sections of the right front wheel, the first section closer to the front of the vehicle is set to a large obstacle avoidance model, while the second section closer to the side of the vehicle is set to a small obstacle avoidance model. Correspondingly, both sections of the left and right rear wheels are set to large obstacle avoidance models.

[0065] In the fixed-wheel rotation method where the right front wheel rotates clockwise, the two sections of the left front wheel are configured as follows: the first section closer to the front of the vehicle is set to a large obstacle avoidance model, while the second section closer to the side of the vehicle is set to a small obstacle avoidance model. Both sections of the right front wheel are set to a large obstacle avoidance model. Correspondingly, the two sections of the left rear wheel and the two sections of the right rear wheel are set to small obstacle avoidance models.

[0066] It should be noted that, as can be seen, when different wheels are used as fixed wheels and rotate in different directions, the obstacle avoidance distance used for each corner partition is not exactly the same. That is, the final vehicle obstacle avoidance model is completely different from the octagonal vehicle obstacle avoidance model. Moreover, when this vehicle obstacle avoidance model is actually used for obstacle avoidance control of fixed wheel rotation in various specific application scenarios, it can achieve a more refined control effect. Specifically, this will be further explained in subsequent embodiments using parallel parking or parking scenarios as examples.

[0067] Of course, the above-mentioned solution is only for realizing the concept of configuring obstacle avoidance distance for different zones. In actual application scenarios, it is entirely feasible to reasonably modify the obstacle avoidance distance based on the obstacle information in the specific application scenario, in addition to the aforementioned concept. This application does not limit this, but any concept that uses the above-mentioned method as the basic idea for configuring obstacle avoidance distance for different zones should be within the scope of protection claimed by this application. For example, in one embodiment of this application, after configuring obstacle avoidance distance for different zones based on the relative displacement information of each vehicle angle, the method further includes: Based on the vehicle's recognition distance error for different obstacles, the obstacle avoidance distance of each of the vehicle's corners is corrected according to the different partition configurations.

[0068] It should be noted that the obstacles perceived here typically refer to obstacle information collected by the vehicle through sensing devices, such as image acquisition devices and ultrasonic acquisition devices, used to characterize obstacles in the real scene, rather than the obstacles assumed in the aforementioned technical solutions. In particular, for different types of obstacles, such as moving targets or fixed targets, the vehicle's sensing devices have varying errors in recognizing these obstacles at different distances. Therefore, in one embodiment of this application, correction based on the actual obstacle avoidance scenario can be achieved by allocating a large obstacle avoidance model to a certain partition according to the aforementioned concept, and then correcting the obstacle avoidance distance to a certain extent based on the types of obstacles perceived in the vicinity of that partition. Of course, the solution provided above also needs to be based on the aforementioned concept of configuring obstacle avoidance distances for partitions, and can be selectively implemented based on the actual scenario requirements. On this basis, other similar correction methods based on the actual scenario requirements should all be within the scope of protection claimed in this application. For example, in other possible implementations, factors such as road friction, braking distance, vehicle rotation speed, and signal transmission time can be comprehensively considered to more accurately and controllably complete the obstacle avoidance control of the vehicle.

[0069] Furthermore, regarding the slightly different obstacle avoidance distances set for different vehicle corners and their zones in this application, such as including but not limited to the aforementioned first obstacle avoidance distance, such as W1, or the second obstacle avoidance distance W2, this application does not limit the specific values. These values ​​are usually obtained through experimental testing and are typically determined based on vehicle performance parameters. In other words, in one embodiment of this application, the method further includes: The obstacle avoidance distance is determined based on the vehicle's performance parameters.

[0070] The vehicle performance parameters mentioned here mainly include the vehicle's perception performance parameters and braking performance parameters. For example, perception performance parameters usually include perception accuracy. Higher perception accuracy allows for a smaller obstacle avoidance distance, while lower perception accuracy usually requires a larger obstacle avoidance distance to allow for sufficient buffer space. Similarly, for braking performance parameters such as braking reaction time or braking reaction distance, a longer braking reaction time or distance often requires a larger obstacle avoidance distance to allow for sufficient buffer space, while a shorter braking reaction time or distance allows for a relatively lower obstacle avoidance distance. The general principle is that once an obstacle is perceived to have passed the vehicle's obstacle avoidance model (i.e., the distance between the obstacle and the vehicle's corner is less than the corresponding obstacle avoidance distance), the vehicle should be controlled to stop. This allows the vehicle to stop before a collision occurs. Based on this, more suitable obstacle avoidance distances can be set according to other requirements, such as different obstacle avoidance distances W1 and W2. This application does not impose further restrictions on these options.

[0071] Specifically, to facilitate understanding of the above content, subsequent embodiments of this application will primarily focus on controlling the vehicle to enter a fixed-wheel rotation mode in a parking scenario where the vehicle is parallel parking in or parallel parking out, thereby executing the obstacle avoidance control method provided in this application. Of course, the obstacle avoidance method provided in this application can also be applied to any other scenario requiring fixed-wheel rotation, including but not limited to rotational movement at garage corners; this application embodiment does not impose any limitations on this. Specifically, in one embodiment of this application, the method further includes: When the vehicle is in a parking scenario of parallel parking or parallel parking exit, in response to the fixed wheel rotation start command, the vehicle is controlled to enter the fixed wheel rotation mode.

[0072] Specifically, in parking scenarios involving parallel parking or parallel parking exit, typically, once the user controls a specific wheel of the vehicle to a given position, the vehicle can be parked or exited using a fixed-wheel rotation control method, with that wheel acting as a fixed wheel. The fixed-wheel rotation activation command can be triggered by the user or automatically by a program setting, thus controlling the vehicle to enter the fixed-wheel rotation mode. This involves two stages: determining the fixed wheel and rotation direction to accurately construct the vehicle obstacle avoidance model, and controlling the vehicle to avoid obstacles based on the obstacle avoidance distance indicated by the obstacle avoidance model during the fixed-wheel rotation process. For example, if the distance between the detected obstacle and the vehicle's corner does not exceed the obstacle avoidance distance corresponding to the corner, the vehicle is brought to a stop.

[0073] Specifically, in parallel parking scenarios, obstacles mainly include curbs and vehicles in front of and behind the vehicle. For example, when parking with the front wheels fixed, collisions between the side of the vehicle and the curb, or between the rear of the vehicle and the vehicle behind, need to be considered. When parking with the rear wheels fixed, collisions between the side of the vehicle and the curb, or between the front of the vehicle and the vehicle in front, need to be considered. When parking out, obstacles within the parking space also need to be considered, such as various fixed or moving obstacles, like traffic cones, bushes, or pedestrians. Furthermore, in other scenarios involving rotating wheels, obstacles can be determined based on the actual scene. For example, when rotating and moving at a garage corner, obstacles might include pillars within the garage, as well as walls.

[0074] Specifically, to facilitate understanding of the above content, Figure 5a This is a schematic diagram illustrating the effect of a vehicle exiting a parallel parking scenario, as provided in an embodiment of this application.

[0075] Please see Figure 5aThe illustration primarily uses a diagram showing the effect of parking with the left front wheel rotating clockwise as an example. For the two sections of the right front wheel, by selecting small obstacle avoidance models for both sections, premature detection of a potential collision with the curb (which actually won't happen) can effectively prevent the vehicle from affecting rotation, thus ensuring a smooth parking maneuver.

[0076] Furthermore, Figure 5b This is a schematic diagram illustrating the effect of a vehicle parking in a side parking scenario, as provided in an embodiment of this application.

[0077] Please see Figure 5b This example illustrates the effect of parking the vehicle by rotating the right front wheel counterclockwise. For the two sections of the right front wheel, selecting small obstacle avoidance models for both sections effectively prevents premature detection of a potential collision with the curb (which actually won't happen), thus ensuring the vehicle can park smoothly. The three corner collision points are marked. Collision point 1 is the point close to the curb. For vehicles with chassis lower than the curb, the vehicle should not touch the curb during rotation, while also ensuring that it can stop even when close enough to the curb. In this scenario, the two sections at the upper right corner of the vehicle are small obstacle avoidance models. Collision point 2 is the collision point between the right rear corner of the vehicle and the left front corner of the following vehicle. To avoid collision, the two braking sections at the right rear corner of the vehicle are set to large obstacle avoidance models. Collision point 3 is the collision point between the section near the side of the left rear corner of the following vehicle and the person. In this scenario, this section moves away from the person, so a small collision area is set to minimize the risk of stopping due to the person's presence, but ensure timely stopping when the person is close enough. The adjacent partition to the partition where collision point 3 is located is set to the large obstacle avoidance model because the car is rotating counterclockwise with the right front wheel fixed at this time. If there is an obstacle in front of this partition at this time, this partition is close to the obstacle, so this partition is set to the large obstacle avoidance model.

[0078] Of course, the above mainly uses some parallel parking scenarios as examples for explanation. For other scenarios, including but not limited to rotating into or out of parallel parking scenarios using other fixed wheels and rotation methods, the relevant vehicle obstacle avoidance models mentioned above can be used. That is, different partitions are set for the corresponding vehicle corners, such as two obstacle avoidance records of large and small sizes, which can effectively improve the actual fixed wheel rotation experience.

[0079] It should be noted that the obstacle avoidance method for vehicles described above typically operates during the rotation of the vehicle's fixed wheels. Before this rotation, it is usually necessary to determine the fixed wheels and their rotation direction. There are various ways to determine the fixed wheels and rotation direction, and this application does not limit this. For example, it can be user confirmation or automatic program confirmation. For instance, during parallel parking, when a front or rear wheel is detected to have reached a designated position, and automatic parking or parking can be achieved simply by rotating the fixed wheels, the fixed wheel rotation mode is triggered. Specifically, taking manual user confirmation as an example, a virtual model of the vehicle can be displayed on the in-vehicle terminal, such as a vehicle infotainment system or other display terminal. This allows for the response to interactive operations on the virtual model, determining the target fixed wheel and its rotation direction for the fixed wheel rotation.

[0080] Specifically, in one embodiment, the interactive operation may include two types of operations, specifically a first interactive operation and a second interactive operation. In this case, the response applied to the interactive operation of the virtual model determines the target fixed wheel for the rotation of the fixed wheel and the direction of rotation, including: In response to a first interactive operation applied to the virtual model, the wheel selected by the first interactive operation is used as the target fixed wheel for the fixed wheel rotation. In response to a second interactive operation applied to the virtual model, the direction indicated by the second interactive operation is taken as the rotation direction.

[0081] Specifically, the interactive operations here can include various types of operations, such as touch operations on the vehicle's infotainment system, voice operations, gesture operations, etc. Taking touch operations as an example, the first interactive operation can be a click operation, that is, the user clicks on a wheel in the virtual model displayed on the vehicle's infotainment system, thereby using the wheel selected by the click operation as the target wheel. Based on this, the second interactive operation can be a swipe operation. For example, by detecting the swipe operation applied to the virtual model, the direction indicated by the swipe operation, such as clockwise or counterclockwise, can be used as the rotation direction. Of course, the above-described embodiment is only an example of touch operation. For voice interaction operations, the vehicle can use a microphone or other sound acquisition device to collect and detect keywords in the user's voice. For example, if the user says "park the car clockwise with the left front wheel as the target wheel," the vehicle can automatically recognize "left front wheel" and "clockwise" as the selected target wheel and rotation direction, and execute the subsequent target wheel rotation process.

[0082] For details, please refer to [link / reference]. Figure 6 , Figure 6 This application provides a schematic diagram illustrating the complete process of a vehicle's fixed wheel rotation, specifically including the following steps: On the S610, users can tap the fixed wheel rotation function on the screen to select the fixed wheel and the rotation direction.

[0083] In the S620, the chassis transmits information such as fixed wheels, rotation direction, rotation speed, position, and activation status to the domain controller's control algorithm.

[0084] In the S630, the control algorithm generates an obstacle avoidance model based on the received chassis information.

[0085] S640, the car begins to rotate. The algorithm combines the input of perceived obstacles and position information, and uses the obstacle avoidance model to perform reasonable obstacle avoidance.

[0086] After the S650 completes rotation, the chassis notification algorithm enters a silent state.

[0087] The vehicle obstacle avoidance control method provided in this application, in the scenario of fixed wheel rotation, divides different corners of the vehicle into different zones, and allows different obstacle avoidance distances to be configured for different zones based on the actual obstacle avoidance distance required by each zone. This enables more flexible obstacle avoidance detection of possible collisions at the corners of the vehicle during obstacle avoidance, thereby improving the user experience to a certain extent.

[0088] In addition to the foregoing, this application also provides a controller, wherein the controller performs obstacle avoidance control of the vehicle by executing the obstacle avoidance control method of the vehicle as described in any of the above embodiments.

[0089] Specifically, the controller can exist in the form of a type of electronic device, for example, see [link to relevant documentation]. Figure 7 , Figure 7 The present application provides a schematic diagram of the structure of an electronic device, which is described in detail below.

[0090] The electronic device may include: A processor is used to execute the obstacle avoidance control method for a vehicle provided in any of the above embodiments. The processor can be various general-purpose or special-purpose processing components with processing and computing capabilities, including but not limited to a central processing unit (CPU), a graphics processing unit (GPU), a dedicated artificial intelligence computing chip, a digital signal processor, etc. A memory, communicatively connected to at least one processor, stores a computer program executable by the at least one processor, enabling the at least one processor to execute a vehicle obstacle avoidance control method as described in any of the above embodiments. The memory may be a read-only memory (ROM) storing the computer program, or a computer program loaded from a storage unit into a random access memory (RAM). The RAM may also store various programs and data required for the operation of a vehicle obstacle avoidance control method.

[0091] I / O interfaces (input units and output units), input units include keyboards, mice, etc., output units include displays, speakers, etc., communication units include network cards, modems, wireless transceivers, processors, and memory.

[0092] The processor controls the overall operation of the electronic device to complete all or part of the steps in the aforementioned vehicle obstacle avoidance control method. The memory stores various types of data to support the operation of the electronic device. This data may include, for example, instructions for any application or method operating on the electronic device, and application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0093] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), or other electronic components to perform the above-described obstacle avoidance control method for vehicles.

[0094] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the obstacle avoidance control method for a vehicle provided in any of the above embodiments.

[0095] This application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it enables the computer program product to implement the obstacle avoidance control method for vehicles provided in any of the above embodiments.

[0096] This application also provides a vehicle obstacle avoidance control system, including a controller as described in any of the above embodiments, wherein the controller performs obstacle avoidance control of the vehicle by executing the vehicle obstacle avoidance control method as described in any of the above embodiments.

[0097] This application also provides a vehicle that includes a controller as described in any of the above embodiments, or includes an obstacle avoidance control system as described in any of the above embodiments, or implements obstacle avoidance control of the vehicle through an obstacle avoidance control method as described in any of the above embodiments.

[0098] In one embodiment, the vehicle can be configured for fully or partially autonomous driving. For example, the vehicle can control itself while in autonomous driving mode, and can determine the current state of the vehicle and its surrounding environment through human intervention, determine the possible behaviors of at least one other vehicle in the surrounding environment, and determine the confidence level corresponding to the probability of that other vehicle performing a possible behavior, and control the vehicle based on the determined information. When the vehicle is in autonomous driving mode, it can be configured to operate without human interaction.

[0099] The vehicle may also include various subsystems, such as a driving system, sensor system control system, one or more peripheral devices, as well as power supply, computer system, and user interface. Optionally, the vehicle may include more or fewer subsystems, and each subsystem may include multiple components, such as multiple ECUs (electronic control units, i.e., vehicle computers) per subsystem.

[0100] In addition, each subsystem and component of the vehicle can be interconnected via wired or wireless means.

[0101] A propulsion system may include components that provide powered motion to the vehicle. In one embodiment, the propulsion system may include an engine, an energy source, a transmission, and wheels / tires. The engine may be an internal combustion engine, an electric motor, an air-compressed engine, or a combination of other types of engines, such as a hybrid engine consisting of a gasoline engine and an electric motor, or a hybrid engine consisting of an internal combustion engine and an air-compressed engine. The engine converts energy into mechanical energy.

[0102] Examples of energy sources include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity. Energy sources can also power other systems in the vehicle.

[0103] A transmission system can transmit mechanical power from an engine to the wheels. The transmission system may include a gearbox, a differential, and a drive shaft. In one embodiment, the transmission system may also include other components, such as a clutch. The drive shaft may include one or more axles that can be coupled to one or more wheels.

[0104] A sensor system may include several sensors that sense information about the vehicle's surrounding environment. For example, a sensor system may include a positioning system (which could be GPS, BeiDou, or another positioning system), an inertial measurement unit (IMU), radar, a laser rangefinder, and cameras. The sensor system may also include sensors from the vehicle's internal systems being monitored (e.g., an in-vehicle air quality monitor, fuel gauge, oil temperature gauge, etc.). Sensor data from one or more of these sensors can be used to detect objects and their corresponding characteristics (position, shape, orientation, speed, etc.). This detection and identification is a critical function for the safe operation of autonomous vehicles.

[0105] A positioning system can be used to estimate a vehicle's geographical location. An IMU is used to sense changes in the vehicle's position and orientation based on inertial acceleration. In one embodiment, the IMU can be a combination of an accelerometer and a gyroscope.

[0106] Radar can use radio signals to sense objects in the vehicle's surrounding environment. In some embodiments, in addition to sensing objects, radar can also be used to sense the speed and / or direction of travel of objects.

[0107] A laser rangefinder can use lasers to sense objects in the environment in which a vehicle is located. In some embodiments, a laser rangefinder may include one or more laser sources, a laser scanner, one or more processing modules, and other system components.

[0108] The camera can be used to capture multiple images of the vehicle's surroundings. The camera can be a still camera or a video camera.

[0109] A control system controls the operation of a vehicle and its components. Control systems can include various elements, including steering systems, throttles, braking units, computer vision systems, route control systems, and obstacle avoidance systems.

[0110] The steering system is operable to adjust the vehicle's direction of travel. For example, in one embodiment, it can be a steering wheel system.

[0111] The throttle is used to control the engine's operating speed and, consequently, the vehicle's speed.

[0112] The braking unit is used to control the deceleration of the vehicle. The braking unit uses friction to slow down the wheels.

[0113] In other embodiments, the braking unit can convert the kinetic energy of the wheels into electrical current. The braking unit may also take other forms to slow down the wheel rotation speed, thereby controlling the vehicle speed.

[0114] Computer vision systems can be operated to process and analyze images captured by cameras to identify objects and / or features in the environment surrounding a vehicle. These objects and / or features may include traffic signals, road boundaries, and obstacles. Computer vision systems may use object recognition algorithms, structure from motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, computer vision systems may be used to map the environment, track objects, estimate object velocities, and so on.

[0115] A route control system is used to determine the driving route of a vehicle. In some embodiments, the route control system may combine data from GPS and one or more predetermined maps to determine the driving route for the vehicle.

[0116] Obstacle avoidance systems are used to identify, assess, and avoid or otherwise traverse potential obstacles in the environment in which a vehicle is located.

[0117] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0118] The embodiments, implementation methods, and related technical features of this application can be combined and substituted for each other without conflict.

[0119] The above are merely preferred embodiments of this application and are not intended to limit this application in any way. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of this application without departing from the scope of the technical solution of this application shall still fall within the scope of the technical solution of this application.

Claims

1. A method for obstacle avoidance control of a vehicle, characterized in that, include: The vehicle's different corner sections are controlled to avoid obstacles at their respective corresponding obstacle avoidance distances, wherein the obstacle avoidance distance of each section is determined by the probability of each section colliding with an obstacle along the vehicle's travel path.

2. The method according to claim 1, characterized in that, For each corner of the vehicle, the corner partition includes at least a first partition near the front or rear of the vehicle, and a second partition near the side of the vehicle.

3. The method according to claim 1, characterized in that, The method further includes: Based on the relative displacement relationship between each zone and the obstacle, obstacle avoidance distances are configured for different zones of each of the vehicle corners. The relative displacement relationship is determined by the target fixed wheel and the direction of rotation of the vehicle.

4. The method according to claim 3, characterized in that, The configuration of obstacle avoidance distances for different zones at each vehicle corner based on the relative displacement relationship between each zone and the obstacle includes: When the relative displacement between the target section at the corner of the vehicle and the obstacle is close, the first obstacle avoidance distance is taken as the obstacle avoidance distance of the target section. When the relative displacement between the target section at the corner of the vehicle and the obstacle is far away, the second obstacle avoidance distance is taken as the obstacle avoidance distance of the target section. Wherein, the first obstacle avoidance distance is greater than the second obstacle avoidance distance.

5. The method according to claim 3, characterized in that, After configuring obstacle avoidance distances for different zones at each of the vehicle corners, the method further includes: Based on the vehicle's recognition distance error for different obstacles, the obstacle avoidance distance of each of the vehicle's corners is adjusted according to the different partition configurations.

6. The method according to claim 3, characterized in that, The target wheel is determined from the wheels of the vehicle that are controlled by an independent motor.

7. The method according to claim 1, characterized in that, Controlling the vehicle to avoid obstacles includes: When the distance between an obstacle and a corner of the vehicle is detected to be no more than the obstacle avoidance distance corresponding to that corner, the vehicle is controlled to brake.

8. The method according to claim 1, characterized in that, The method further includes: In parking scenarios where the vehicle is either parallel parking in or parallel parking out, the different sections of the vehicle's corners are controlled to avoid obstacles at their respective corresponding obstacle avoidance distances.

9. The method according to claim 8, characterized in that, In the parking scenarios of side parking in or side parking out, obstacles include at least one of the following: curb in the parking scenario, parking in front of or behind the vehicle, fixed obstacles in the environment where the vehicle is located, and moving obstacles.

10. The method according to claim 1, characterized in that, The method further includes: The obstacle avoidance distance is determined based on the vehicle's performance parameters.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: Display a virtual model of the vehicle to determine the target wheel and direction of rotation for the fixed wheel rotation in response to interactive operations performed on the virtual model.

12. The method according to claim 11, characterized in that, The interactive operation includes a first interactive operation and a second interactive operation. The response to the interactive operation acting on the virtual model determines the target fixed wheel for the rotation of the fixed wheel and the direction of rotation, including: In response to a first interactive operation applied to the virtual model, the wheel selected by the first interactive operation is used as the target fixed wheel for the fixed wheel rotation. In response to a second interactive operation applied to the virtual model, the direction indicated by the second interactive operation is taken as the rotation direction.

13. A controller, characterized in that, The controller achieves obstacle avoidance control of the vehicle by executing the obstacle avoidance control method of the vehicle as described in any one of claims 1 to 12.

14. A vehicle obstacle avoidance control system, characterized in that, The system includes the controller as described in claim 13, which implements obstacle avoidance control of the vehicle by executing the obstacle avoidance control method of the vehicle as described in any one of claims 1 to 12.

15. A vehicle, characterized in that, It includes the controller as described in claim 13, or the obstacle avoidance control system of the vehicle as described in claim 14, or the obstacle avoidance control of the vehicle is achieved by the obstacle avoidance control method of the vehicle as described in any one of claims 1 to 12.

Images