Vehicle control method and apparatus, and device, storage medium and vehicle

Abstract

Disclosed are a vehicle control method and apparatus in a stuck scenario, and a device, a storage medium and a vehicle. The method comprises: when it is detected that a vehicle is in a target stuck scenario, determining a target escape point corresponding to the target stuck scenario (S101), wherein the target escape point is located on a road reference line in front of the vehicle in a driving direction of the vehicle; using the target escape point as an end point to execute a path planning operation, so as to generate a planned escape path (S102); when the planned escape path is successfully generated and there is a reversing path in the planned escape path, controlling the vehicle to move according to the planned escape path, so as to guide the vehicle out of the stuck scenario (S103); and when the path planning operation has been executed a preset number of times and no planned escape path is generated, or, when the planned escape path is successfully generated and there is no reversing path in the planned escape path, stopping the execution of the path planning operation, so as to end the control of vehicle escape from the stuck scenario (S104).

Description

Vehicle control methods, devices, equipment, storage media and vehicles Cross-references to related applications

[0001] This application claims priority to Chinese patent application No. 202411257292.7, filed on September 9, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to, but is not limited to, the field of vehicle technology, and in particular to a vehicle control method, device, equipment, storage medium, and vehicle for use in a trapped scenario. Background Technology

[0003] With the rapid development of autonomous driving technology and vehicle technology, autonomous driving functions are becoming increasingly common in vehicles. Currently, in complex road environments, vehicles with autonomous driving functions need to be able to perceive their surroundings in real time, accurately judge road conditions, and plan safe and efficient driving routes. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0005] This application provides a vehicle control method, device, equipment, storage medium, and vehicle for use in a trapped scenario.

[0006] In a first aspect, embodiments of this application provide a method for controlling a vehicle in a trapped scenario, comprising: upon detecting that the vehicle is in a target trapped scenario, determining a target escape point corresponding to the target trapped scenario, wherein the target escape point is located on a road reference line in front of the vehicle in the vehicle's direction of travel; performing a path planning operation with the target escape point as the endpoint to generate an escape planning path; if the escape planning path is successfully generated and a reversal path exists in the escape planning path, controlling the vehicle to move according to the escape planning path to guide the vehicle out of the trapped scenario; if the path planning operation is executed a preset number of times and no escape planning path is generated, or if the escape planning path is successfully generated and the reversal path does not exist in the escape planning path, stopping the execution of the path planning operation to end the control of the vehicle to escape the trapped scenario.

[0007] In some embodiments, before determining the target escape point corresponding to the target entrapment scenario when the vehicle is detected to be in a target entrapment scenario, the method further includes: during the vehicle's operation, in response to the vehicle stopping, performing a vehicle congestion detection operation based on a preset multiple entrapment scenario detection strategy, wherein the multiple entrapment scenario detection strategies correspond to different entrapment scenarios; if the vehicle is detected to be congested when the vehicle congestion detection operation is performed based on the target entrapment scenario detection strategy, determining the entrapment scenario in which the vehicle is located, corresponding to the target entrapment scenario detection strategy, as the target entrapment scenario.

[0008] In some implementations, the multiple entrapment scenario detection strategy includes a first entrapment scenario detection strategy corresponding to a first entrapment scenario, where the vehicle is blocked by a road boundary. The vehicle blockage detection operation based on the preset multiple entrapment scenario detection strategy includes: obtaining a preset fan-shaped detection range corresponding to the vehicle; determining the blockage angle of the vehicle on the road boundary within the preset fan-shaped detection range; and determining whether the vehicle is in the first entrapment scenario based on non-blockage angles within the preset fan-shaped detection range other than the blockage angle. The target entrapment scenario includes the first entrapment scenario.

[0009] In some implementations, determining the congestion angle of the vehicle on the road boundary within the preset sector detection range includes: determining a first intersection point and a second intersection point formed between the preset sector detection range and the road boundary, wherein the first intersection point and the second intersection point are located on the road boundary; and determining the angle within the preset sector detection range between the first intersection point and the second intersection point as the congestion angle of the vehicle on the road boundary.

[0010] In some implementations, determining whether the vehicle is in the first trapped scenario based on the non-blocking angles within the preset sector detection range other than the blocking angle includes: determining the non-blocking arc length corresponding to the non-blocking angle; and determining that the vehicle is in the first trapped scenario if the non-blocking arc length is less than or equal to a preset arc length threshold.

[0011] In some implementations, when the vehicle is in the first trapped scenario, determining the target escape point corresponding to the target trapped scenario when the vehicle is detected to be in the target trapped scenario includes: determining a first mapping point on the road reference line where the foremost point of the vehicle is mapped in the vehicle's direction of travel; and determining the coordinate point on the road reference line that is a first preset distance away from the first mapping point as the target escape point.

[0012] In some implementations, the multiple entrapment scenario detection strategy includes a second entrapment scenario detection strategy corresponding to a second entrapment scenario, where the vehicle is blocked by one or more obstacles. The vehicle blockage detection operation based on the preset multiple entrapment scenario detection strategy includes: performing obstacle detection within the obstacle detection range of the vehicle, where the obstacle detection range is a range within a preset distance in the vehicle's direction of travel; and determining that the vehicle is in the second entrapment scenario if one or more obstacles are detected within the obstacle detection range, wherein the target entrapment scenario includes the second entrapment scenario.

[0013] In some embodiments, when the vehicle is in the second entrapment scenario, determining the target escape point corresponding to the target entrapment scenario upon detecting that the vehicle is in the target entrapment scenario includes: if the second entrapment scenario has only one obstacle, determining the target escape point as a coordinate point on the road reference line that is a second preset distance away from a second mapping point, wherein the second mapping point is a coordinate point on the road reference line mapped from the foremost point of one of the obstacles in the vehicle's direction of travel; or, if the second entrapment scenario has multiple obstacles, determining the target escape point as a coordinate point on the road reference line that is a third preset distance away from a third mapping point, wherein the third mapping point is a coordinate point on the road reference line mapped from the foremost point of the first obstacle among the multiple obstacles in the vehicle's direction of travel; the first obstacle is the obstacle farthest from the vehicle among the multiple obstacles in the direction of travel, and the mapping distance between two adjacent obstacles on the road reference line is less than or equal to the third preset distance.

[0014] In some implementations, the step of performing path planning operations with the target escape point as the endpoint to generate an escape planning path includes: generating a static grid cost map corresponding to the vehicle's driving road, the static grid cost map including multiple grids; performing an initial path search on the static grid cost map with the target escape point as the starting point to obtain the costs from the multiple grids to the target escape point, and recording the costs from the multiple grids to the target escape point to generate a distance cost map; and performing at least one path search based on the static grid cost map and the distance cost map with the target escape point as the endpoint to generate the escape planning path, wherein for each of the multiple nodes in the at least one path search, the heuristic cost of the node is associated with the cost from the grid where the node is located to the target escape point in the distance cost map.

[0015] In some embodiments, after generating a static grid cost map corresponding to the vehicle's travel path, the method further includes: identifying unreachable and reachable grids in the static grid cost map based on congestion information on the travel path, wherein the congestion information is configured to indicate obstacles and road boundaries, the unreachable grid is the grid where the obstacle or the road boundary is located; the reachable grid is the grid other than the unreachable grid; wherein the initial path search and the at least one path search use the reachable grids located on the road in the static grid cost map as a plurality of nodes.

[0016] Secondly, embodiments of this application also provide a vehicle control device in a trapped scenario, comprising: an escape point determination module, configured to determine a target escape point corresponding to the target trapped scenario when the vehicle is detected to be in a target trapped scenario, wherein the target escape point is located on a road reference line in front of the vehicle in the vehicle's driving direction; a path planning module, configured to perform a path planning operation with the target escape point as the endpoint to generate an escape planning path; a motion control module, configured to control the vehicle to move along the escape planning path when the escape planning path is successfully generated and the escape planning path has a reversal path, thereby guiding the vehicle to escape the trapped scenario; and a path planning stop module, configured to stop executing the path planning operation when the path planning operation is executed a preset number of times and the escape planning path is not generated, or when the escape planning path is successfully generated and the escape planning path does not have the reversal path, thereby ending the control of the vehicle to escape the trapped scenario.

[0017] Thirdly, embodiments of this application also provide an electronic device, the electronic device comprising: at least one processor; and at least one memory coupled to the at least one processor and configured to store computer program instructions; the at least one processor is configured to read the computer program instructions from the at least one memory and execute the computer program instructions to implement the vehicle control method in a trapped scenario as described in any embodiment / implementation of the first aspect.

[0018] Fourthly, embodiments of this application also provide a non-transitory computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the vehicle control method in a trapped scenario as described in any embodiment / implementation of the first aspect.

[0019] Fifthly, embodiments of this application also provide a vehicle including the electronic equipment described in the third aspect.

[0020] In a sixth aspect, embodiments of this application also provide a computer program product, including a computer program that is executed by at least one processor to implement the vehicle control method in a trapped scenario as described in any embodiment / implementation of the first aspect.

[0021] After reading and understanding the accompanying diagrams and detailed descriptions, the other aspects can be understood. Attached Figure Description

[0022] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly described below. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0023] Figure 1 is a flowchart illustrating a vehicle control method in a trapped scenario according to an embodiment of this application;

[0024] Figure 2 is a schematic diagram of detecting a first trapped scenario in a vehicle control method under a trapped scenario according to an embodiment of this application;

[0025] Figure 3 is a schematic diagram of detecting a second trapped scenario in a vehicle control method under trapped scenarios according to an embodiment of this application;

[0026] Figure 4 is a schematic diagram of determining the target escape point in the first trapped scenario in the vehicle control method under the trapped scenario according to an embodiment of this application;

[0027] Figure 5 is a schematic diagram of determining the target escape point in the second trapped scenario in the vehicle control method under the trapped scenario according to an embodiment of this application;

[0028] Figure 6 is another schematic diagram of determining the target escape point in the second trapped scenario in the vehicle control method under the trapped scenario according to an embodiment of the present application;

[0029] Figure 7 is a schematic diagram of a static grid cost map in a vehicle control method under a trapped scenario according to an embodiment of this application;

[0030] Figure 8 is a structural schematic diagram of a vehicle control device in a trapped scenario according to an embodiment of this application; and

[0031] Figure 9 is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0032] The features and exemplary embodiments of various aspects of this application will now be described in detail. To make the objectives, solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to explain this application only and are not intended to limit this application. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0033] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0034] In complex road environments, vehicles with autonomous driving capabilities need to be able to perceive their surroundings in real time, accurately assess road conditions, and plan safe and efficient driving routes. However, in situations where vehicles are trapped in special road conditions, such as narrow roads, obstacles, or road construction, they may repeatedly perform path planning operations but fail to plan an effective driving route, resulting in a waste of computing resources in the autonomous driving function.

[0035] In view of this, embodiments of this application provide a vehicle control method, apparatus, device, storage medium, and vehicle in a trapped scenario, which can save computing resources.

[0036] Figure 1 shows a flowchart illustrating a vehicle control method in a trapped scenario according to an embodiment of this application. The vehicle control method in a trapped scenario of this application can be applied to an electronic device, which may be a vehicle-mounted terminal or a terminal device, server, etc., independent of the vehicle. As shown in Figure 1, the vehicle control method in a trapped scenario includes, but is not limited to, the following steps S101 to S104.

[0037] In step S101, when the vehicle is detected to be in a target entrapment scenario, a target escape point corresponding to the target entrapment scenario is determined. The target escape point is located on the road reference line in front of the vehicle in the vehicle's direction of travel.

[0038] In this step, during the autonomous driving process, the vehicle can be continuously monitored to determine whether it is in the target distress scenario. If the vehicle is detected to be in the target distress scenario, the target escape point corresponding to the target distress scenario is determined on the road reference line in front of the vehicle in the direction of vehicle travel.

[0039] The aforementioned reference line can be a virtual line segment located in the middle of the lane in the Frenet coordinate system and used to guide vehicle movement.

[0040] Since vehicles may encounter various entrapment scenarios during autonomous driving, the aforementioned target entrapment scenario can be any one of these scenarios. Specifically, the aforementioned target entrapment scenario can be a first entrapment scenario, in which the vehicle is blocked by a road boundary, which can be an object located at the edge of the road that can obstruct the passage of the vehicle, such as a guardrail; or, the aforementioned target entrapment scenario can also be a second entrapment scenario, in which the vehicle is blocked by an obstacle, which can be an object located within the lane that can obstruct the passage of the vehicle, such as a traffic cone in the lane.

[0041] When detecting whether a vehicle is in a target-related predicament, the distance between the vehicle and the object in front can be determined by radar sensing data. Based on the distance between the vehicle and the object in front, it can be determined whether the vehicle is blocked. If the vehicle is blocked, the object blocking the vehicle can be identified by combining image data, thereby determining the target-related predicament where the vehicle is located.

[0042] In some embodiments, prior to step S101 above, the vehicle control method under the trapped scenario further includes: during vehicle operation, in response to the vehicle stopping, performing a vehicle congestion detection operation based on a preset multiple trapped scenario detection strategy, wherein the multiple trapped scenario detection strategies correspond to different trapped scenarios; if a vehicle congestion is detected when the vehicle congestion detection operation is performed based on the target trapped scenario detection strategy, the trapped scenario in which the vehicle is located, corresponding to the target trapped scenario detection strategy, is determined as the target trapped scenario.

[0043] In this embodiment, when the vehicle stops during autonomous driving, vehicle congestion detection can be performed using various congestion scenario detection strategies. If a vehicle congestion is detected based on the target congestion scenario detection strategy, it can be determined that the vehicle is in the target congestion scenario corresponding to the target congestion scenario detection strategy, thereby making the detection of whether the vehicle is in the target congestion scenario more efficient.

[0044] The aforementioned multiple distress scenario detection strategies can be pre-configured in electronic devices. When the vehicle is in autonomous driving mode, the electronic devices can run these multiple distress scenario detection strategies to detect whether the vehicle is stuck in a traffic jam.

[0045] It should be noted that when the above-mentioned electronic device runs multiple trapped scenario detection strategies, it can run the multiple trapped scenario detection strategies sequentially; or it can run the multiple trapped scenario detection strategies simultaneously. For example, the electronic device can run multiple trapped scenario detection strategies simultaneously through multiple threads, and run different trapped scenario detection strategies through different threads.

[0046] Each of the above-mentioned various distress scenario detection strategies can be understood as a detection algorithm that can detect whether a vehicle is in a distress scenario corresponding to that strategy. The detection algorithm detects the distress scenario of the vehicle according to its preset detection process.

[0047] In some implementations, the above-mentioned multiple distress scenario detection strategies include a first distress scenario detection strategy corresponding to a first distress scenario, where the vehicle is blocked by a road boundary.

[0048] The above-mentioned vehicle congestion detection operation based on multiple preset congestion scenario detection strategies may include: obtaining a preset sector detection range corresponding to the vehicle; determining the congestion angle of the vehicle on the road boundary within the preset sector detection range; and determining whether the vehicle is in a first congestion scenario based on the non-congestion angles within the preset sector detection range, excluding the congestion angle, wherein the target congestion scenario includes the first congestion scenario.

[0049] In this embodiment, the blocking angle of the vehicle on the road boundary within the preset fan-shaped detection range corresponding to the vehicle can be determined. Then, based on the non-blocking angles within the preset fan-shaped detection range other than the blocking angle, the vehicle can be detected as being blocked by the road boundary, that is, whether the vehicle is in the first trapped scenario. This can improve the accuracy of detecting whether the vehicle is in the first trapped scenario blocked by the road boundary.

[0050] The aforementioned preset sector detection range can be a sector detection range pre-defined in the vehicle coordinate system. This preset sector detection range is determined by the detection angle θ and the detection radius r, and these detection angle θ and detection radius r can be preset according to actual conditions. For example, the preset sector detection range can be set to satisfy: θ min ≤θ≤θ max r min ≤r≤r max Where, θ min θ max r minand r max These are preset adjustable parameters.

[0051] The aforementioned determination of the congestion angle of vehicles within the preset sector detection range on the road boundary can be obtained by calculating the congestion angle of vehicles within the preset sector detection range on the road boundary based on the curvature of the road boundary and the intersection point of the outer contour of the preset sector detection range on the road boundary.

[0052] In some implementations, determining the congestion angle of a vehicle at the road boundary within a preset sector detection range includes: determining a first intersection point and a second intersection point formed between the preset sector detection range and the road boundary, wherein the first intersection point and the second intersection point are located on the road boundary; and determining the angle within the preset sector detection range between the first intersection point and the second intersection point as the congestion angle of the vehicle at the road boundary.

[0053] In this embodiment, the aforementioned congestion angle can be determined based on the first and second intersection points formed between the preset sector detection range and the road boundary, thereby making the method of determining the congestion angle easier to implement and further reducing computational resource overhead.

[0054] For example, as shown in Figure 2, when the preset sector detection range is the detection range of detection angle θ and detection radius r, the intersection point 21 and intersection point 22 formed between the preset sector detection range and the road boundary can be determined by radar sensing data, and the angle θ1 between intersection point 21 and intersection point 22 within the preset sector detection range can be further determined as the blocking angle of the vehicle on the road boundary.

[0055] The above method determines whether a vehicle is in the first trapped scenario based on the non-blocking angle within the preset sector detection range, excluding the blocking angle. This can be done if the blocking angle is greater than or equal to the non-blocking angle, or if the non-blocking angle is less than or equal to a preset angle threshold.

[0056] In some implementations, determining whether a vehicle is in a first entrapment scenario is based on the non-blocking angles within a preset sector detection range, excluding the blocking angle. This includes: determining the non-blocking arc length corresponding to the non-blocking angle; and determining that the vehicle is in a first entrapment scenario if the non-blocking arc length is less than or equal to a preset arc length threshold.

[0057] In this embodiment, by determining the unblocked arc length corresponding to the non-blocked angle, and determining that the vehicle is in the first trapped scenario when the unblocked arc length is less than or equal to a preset arc length threshold, it is possible to more accurately determine whether the vehicle is in the first trapped scenario.

[0058] For example, as shown in Figure 2, the electronic device can determine the non-blocking angle as θ2, and the non-blocking arc length corresponding to the non-blocking angle θ2 is l1.

[0059] In some implementations, the above-mentioned multiple entrapment scenario detection strategies include a second entrapment scenario detection strategy corresponding to a second entrapment scenario, where the vehicle is blocked by an obstacle.

[0060] The above-mentioned vehicle congestion detection operation based on multiple preset congestion scenario detection strategies may include: performing obstacle detection within the obstacle detection range of the vehicle, the obstacle detection range being a range within a preset distance in the direction of vehicle travel; and determining that the vehicle is in a second congestion scenario when an obstacle is detected within the obstacle detection range, wherein the target congestion scenario includes the second congestion scenario.

[0061] In this embodiment, the presence of obstacles within the vehicle's obstacle detection range can be detected to determine whether the vehicle is in a second entrapment scenario, thereby accurately determining whether the vehicle is in the aforementioned second entrapment scenario.

[0062] For example, as shown in Figure 3, within the Frenet coordinate system with the vehicle as the origin, the obstacle detection range for the vehicle can be a detection range 31 (i.e., the range within the dashed box) with a distance of S between the vehicle and the obstacle in the longitudinal coordinate and a distance L between the vehicle and the obstacle in the lateral coordinate. If an obstacle 32 is detected within this detection range 31, the vehicle is determined to be in the second entrapment scenario. The values ​​of S and L can be set according to actual needs, such as: S min ≤S≤S max L min ≤L≤L max The above S min S max L min L max This is an adjustable parameter.

[0063] In step S101, the above-mentioned determination of the target escape point corresponding to the target trapped scenario can be achieved by adopting different strategies to determine the target escape point according to different trapped scenarios.

[0064] In some implementations, when the target entrapment scenario includes a first entrapment scenario, step S101 includes: determining a first mapping point on the road reference line where the foremost point of the vehicle is mapped in the vehicle's driving direction; and determining a coordinate point on the road reference line that is a first preset distance away from the first mapping point as the target escape point.

[0065] In this embodiment, when the vehicle is in a first entrapment scenario, a first mapping point on the road reference line can be determined from the vehicle's direction of travel. The coordinate point on the road reference line that is a first preset distance away from the first mapping point (e.g., a coordinate point located in front of the first mapping point in the vehicle's direction of travel) is then identified as the target escape point. This allows for accurate determination of the escape point in the first entrapment scenario, further increasing the likelihood of the vehicle escaping from the first entrapment scenario. In the embodiments / implementations of this application, the mapping point on the road reference line refers to the intersection of the normal line of the road reference line passing through that point and the road reference line itself. Furthermore, the foremost point of the vehicle refers to the boundary point among the vehicle's boundary points whose mapping point is located furthest forward in the vehicle's direction of travel.

[0066] The above-mentioned determination of the first mapping point on the road reference line, which maps the front of the vehicle to the front of the vehicle in the direction of travel, can be achieved by determining the coordinate point on the road reference line where the front of the vehicle is mapped to the front of the vehicle as the first mapping point when the vehicle is moving forward.

[0067] The above-mentioned determination of the target escape point as the coordinate point on the road reference line that is at a first preset distance from the first mapping point can be either the coordinate point on the road reference line that is at a distance equal to the first preset distance from the first mapping point along the road reference line, or the coordinate point on the road reference line that is at a straight-line distance equal to the first preset distance from the first mapping point.

[0068] For example, as shown in Figure 4, when the vehicle is in the first trapped scenario, the electronic device can determine the first mapping point 41 of the front end of the vehicle on the road reference line, and then determine the coordinate point 42 of the road reference line that is a preset distance L1 away from the first mapping point as the target escape point.

[0069] In some implementations, when the vehicle is in a second trapped scenario, step S101 includes: when the second trapped scenario only has a first obstacle, determining the coordinate point on the road reference line that is a second preset distance away from the second mapping point as the target escape point, wherein the second mapping point is the coordinate point on the road reference line where the foremost end of the first obstacle is mapped to the front end of the first obstacle in the vehicle's driving direction.

[0070] In this embodiment, when a vehicle is trapped in a second trapped scenario with only one obstacle (i.e., the first obstacle), the target escape point can be determined based on the second mapping point on the road reference line mapped from the foremost point of the first obstacle, thereby accurately determining the target escape point when the vehicle is trapped in the second trapped scenario with only one obstacle.

[0071] It should be noted that the second preset distance mentioned above may be the same as or different from the first preset distance mentioned above, and is not limited here.

[0072] For example, as shown in Figure 5, in a second trapped scenario where the vehicle is trapped by only one obstacle 51, the electronic device can determine the second mapping point 52 of the foremost point of the obstacle 51 on the road reference line, and then determine the coordinate point 53 on the road reference line that is a preset distance L2 away from the second mapping point 52 as the target escape point.

[0073] In some embodiments, when the vehicle is in a second entrapment scenario, step S101 includes: If the second entrapment scenario has multiple obstacles, a coordinate point on the road reference line that is a third preset distance from a third mapping point is determined as the target escape point. The third mapping point is the coordinate point on the road reference line mapped from the foremost point of the second obstacle in the vehicle's direction of travel. The second obstacle is the obstacle furthest from the vehicle among the multiple obstacles in the direction of travel, and the mapping distance between two adjacent obstacles on the road reference line is less than or equal to the third preset distance. In the embodiments / implementations of this application, the mapping distance between two adjacent obstacles on the road reference line refers to the distance between the two adjacent obstacles and the mapping point on the road reference line. For example, the mapping distance between two adjacent obstacles on the road reference line can be determined by the following steps: Take the foremost (or furthest) mapping point from multiple boundary points of the first obstacle closer to the vehicle to the mapping points on the road reference line as the front mapping point of the first obstacle; take the rearmost (or closest) mapping point from multiple boundary points of the second obstacle furthest from the vehicle to the mapping points on the road reference line as the rear mapping point of the second obstacle; and take the length of the reference line between the front mapping point of the first obstacle and the rear mapping point of the second obstacle as the mapping distance between the two adjacent obstacles on the road reference line.

[0074] In this embodiment, when a vehicle is trapped in a second trapped scenario with multiple obstacles, the target escape point can be determined by mapping the foremost point of the second obstacle furthest from the vehicle along the driving direction to a third mapping point on the road reference line, thereby accurately determining the target escape point when the vehicle is trapped in a second trapped scenario with multiple obstacles.

[0075] It should be noted that the third preset distance mentioned above may be the same as or different from the second preset distance mentioned above, and no limitation is made here.

[0076] For example, as shown in Figure 6, in a second trapped scenario where a vehicle is trapped by three obstacles (i.e., obstacle 61, obstacle 62, and obstacle 63), since the mapping distance between obstacle 61 and obstacle 62 on the road reference line is less than the preset distance L3, while the mapping distance between obstacle 62 and obstacle 63 on the road reference line is greater than the preset distance L3, the electronic device identifies obstacle 62 as the second obstacle. Then, it can determine the third mapping point 64 of the foremost point of obstacle 62 on the road reference line, and finally determine the coordinate point 65 on the road reference line that is a preset distance L3 away from the third mapping point 64 as the target escape point.

[0077] In step S102, a path planning operation is performed with the target escape point as the endpoint to generate an escape planning path.

[0078] In this step, the electronic device can perform path planning operations with the target escape point as the destination using a preset path planning algorithm. In the embodiments according to this application, the path planning algorithm can be any algorithm capable of planning vehicle routes. For example, the path planning algorithm can include at least one of the following: A* algorithm, Dijkstra's algorithm, and breadth-first search algorithm.

[0079] In some implementations, path planning can be performed using an improved A* algorithm. For example, in an embodiment according to this application, step S102 above may include: generating a static grid cost map corresponding to the vehicle's driving road, the static grid cost map including multiple grids; performing an initial path search on the static grid cost map, starting from the target escape point, to obtain the costs from multiple grids to the target escape point, and recording the costs from multiple grids to the target escape point to generate a distance cost map; and performing at least one path search based on the static grid cost map and the distance cost map, ending at the target escape point, to generate an escape planning path, wherein the heuristic cost of each node in the at least one path search is associated with the cost from the grid where that node is located to the target escape point in the distance cost map.

[0080] In this embodiment, in the improved A* algorithm described above, a conventional A* algorithm path search (i.e., the initial path search) can be performed after generating a static grid cost map to generate a distance cost map. In at least one subsequent path search, the heuristic cost of a node in the A* algorithm is associated with the cost from the grid where the node is located to the target escape point in the distance cost map, thereby quickly generating a path that conforms to kinematic constraints and improving path planning efficiency.

[0081] The aforementioned generation of a static grid cost map corresponding to the vehicle's driving path can be based on a preset rectangular boundary range, grid density, and obstacle information.

[0082] In some implementations, after generating the static grid cost map corresponding to the vehicle's driving road, the vehicle control method in the trapped scenario further includes: identifying unreachable and reachable grids in the static grid cost map based on congestion information on the driving road, wherein the congestion information is used to indicate obstacles and road boundaries, unreachable grids are grids where obstacles or road boundaries are located, and reachable grids are grids other than unreachable grids; wherein the initial path search and at least one path search use reachable grids located on the road in the static grid cost map as nodes.

[0083] In this embodiment, unreachable and reachable grids in the static grid cost map can be identified based on obstacles and road boundaries. In path search, only reachable grids located on roads in the static grid cost map are used as nodes, thereby reducing the search range and further reducing the consumption of computational resources for path planning.

[0084] For example, as shown in Figure 7, after generating a static grid cost map, the electronic device can mark the grid containing the obstacle 71 and the road boundary 72 as unreachable grids (gray grids), while in the path search, only the reachable grids within the road closed area 73 are used as nodes.

[0085] In this embodiment, the electronic device can perform a path search based on the static grid cost map, starting from the target escape point, and record the cost from each grid to the target escape point obtained in this path search, thereby generating a distance cost map.

[0086] When the static grid cost map identifies unreachable and reachable grids, the distance cost map is consistent with the unreachable grids in the static grid cost map, but the cost information of the reachable grids is updated to the shortest distance to the target escape point.

[0087] It should be noted that the improved A* algorithm in this application has a processing flow that is basically the same as the traditional A* algorithm. The main difference is that the heuristic cost of a node in the improved A* algorithm is related to the cost from the grid where the node is located to the target escape point in the distance cost map mentioned above. Since the processing flow of the traditional A* algorithm is known in the art, it will not be described in detail here.

[0088] In this embodiment, the cost function in the improved A* algorithm can start with the vehicle pose, use N arcs of fixed arc length as the expansion path, and use path length, turning angle, and steering as costs to start the path search based on the search method of the A* algorithm. The cost function f(n) can be composed of historical cost g(n) and heuristic cost h(n), as shown in the following formulas (1) to (3): f(n)=g(n)+h(n) (1) g(n)=Length*w direction +w gear +steer*w steer +steerDif*w steerDif (2) h(n) = disCostmap(n) * w t (3)

[0089] In formulas (1) to (3) above, Length is the path length, steer is the turning angle, steerDif is the turning direction, and w direction For gear penalty weights (different values ​​for forward and reverse gears), w gear For shift penalty weighting, w steer To shift the penalty weight, w steerDif For the penalty weight of direction change, w t The cost map weights are represented by disCostmap(n), which represents the cost of the grid cell containing node n in the cost map.

[0090] During at least one path search process, every m iterations, a Reed-sheep curve is attempted to connect the endpoint once. If the connecting line of the Reed-sheep curve satisfies the collision-free condition, the Reed-sheep curve is considered to be successfully connected, where m is a positive integer.

[0091] In some implementations, to reduce the consumption of computational resources during the path planning process, the above-mentioned path planning operation may include any of the following: The search ends when all nodes in the static raster cost map have been searched; The search ends when, in the vertical direction, the endpoints of the searched paths have entered the end range, and the absolute value of the angle between the endpoint's heading and the reference line direction is less than an angle threshold, and the distance between the endpoint and the reference line is less than a distance threshold; The search ends when the Reed-sheep curve is successfully connected.

[0092] The search ends when all nodes in the static grid cost map have been searched. Alternatively, the search can end when the static grid cost map has been searched for the reachable grids (i.e., road closed area 73) located in the road.

[0093] Additionally, the aforementioned ending range can be the road area located in front of the target escape point in the vehicle's direction of travel. For example, as shown in Figure 6, the aforementioned ending range can be the road area 66 in front of the target escape point 65.

[0094] It should be noted that the operation of determining the target escape point in step 101 above can be performed during the path planning operation in step 102 above; or it can be performed before step 102. Figure 1 only shows the case where step 101 is performed before step 102, and no limitation is made here.

[0095] In step 103, if the escape path is successfully generated and there is a reversal path in the escape path, the vehicle is controlled to move according to the escape path to guide the vehicle out of the trapped situation.

[0096] In step 104, if the path planning operation is executed a preset number of times and no escape path is generated, or if the escape path is successfully generated but there is no reversal path in the escape path, the path planning operation is stopped to end the control of the vehicle to escape the trapped scenario.

[0097] In this embodiment, when a vehicle is detected to be in a target entrapment scenario, a target escape point corresponding to the target entrapment scenario is determined. The target escape point is located on a road reference line in front of the vehicle in the vehicle's direction of travel. A path planning operation is performed with the target escape point as the endpoint to generate an escape planning path. If the escape planning path is successfully generated and there is a reversal path within the escape planning path, the vehicle is controlled to move along the escape planning path to guide the vehicle out of the entrapment scenario. If the path planning operation is performed a preset number of times without generating an escape planning path, or if the path planning operation successfully generates an escape planning path but there is no reversal path within the escape planning path, the path planning operation is stopped to end the process of controlling the vehicle to escape the entrapment scenario. Thus, by pre-setting the stop condition for stopping the path planning operation, the possibility of repeatedly performing path planning operations can be reduced, thereby saving computational resources during the autonomous driving process.

[0098] The vehicle control method for trapped scenarios provided in this application can be executed by a vehicle control device for trapped scenarios. This application uses the example of a vehicle control device for trapped scenarios executing the vehicle control method for trapped scenarios to illustrate the vehicle control device for trapped scenarios provided in this application.

[0099] Figure 8 shows a schematic diagram of the vehicle control device in a trapped scenario according to an embodiment of this application. As shown in Figure 8, the vehicle control device 800 in a trapped scenario according to this application includes: a slack-out point determination module 801, used to determine a target slack-out point corresponding to the target trapped scenario when the vehicle is detected to be in a target trapped scenario, wherein the target slack-out point is located on a road reference line in front of the vehicle in the vehicle's driving direction; a path planning module 802, used to perform a path planning operation with the target slack-out point as the endpoint to generate a slack-out planning path; a motion control module 803, used to control the vehicle to move according to the slack-out planning path when the slack-out planning path is successfully generated and there is a backward path in the slack-out planning path, so as to guide the vehicle to escape the trapped scenario; and a path planning stop module 804, used to stop the execution of the path planning operation when the path planning operation is executed a preset number of times and no slack-out planning path is generated, or when the slack-out planning path is successfully generated and there is no backward path in the slack-out planning path, so as to end the control of the vehicle to escape the trapped scenario.

[0100] In some embodiments, the vehicle control device 800 further includes: a congestion detection module, used to perform a vehicle congestion detection operation based on a preset set of multiple entrapment scenario detection strategies in response to the vehicle stopping during vehicle operation, wherein the multiple entrapment scenario detection strategies correspond to different entrapment scenarios; and an entrapment scenario determination module, used to determine the entrapment scenario in which the vehicle is located, corresponding to the target entrapment scenario detection strategy, as the target entrapment scenario when a vehicle congestion is detected during the vehicle congestion detection operation based on the target entrapment scenario detection strategy.

[0101] In some implementations, the multiple entrapment scenario detection strategies include a first entrapment scenario detection strategy corresponding to a first entrapment scenario where the vehicle is blocked by a road boundary.

[0102] The congestion detection module can be used to: obtain a preset sector detection range corresponding to the vehicle; determine the congestion angle of the vehicle on the road boundary within the preset sector detection range; and determine whether the vehicle is in the first trapped scenario based on the non-congestion angles within the preset sector detection range, excluding the congestion angles, where the target trapped scenario includes the first trapped scenario.

[0103] In some implementations, the congestion detection module can be specifically used to: determine a first intersection point and a second intersection point formed between a preset sector detection range and a road boundary, wherein the first intersection point and the second intersection point are located on the road boundary; and determine the angle within the preset sector detection range between the first intersection point and the second intersection point as the congestion angle of the vehicle on the road boundary.

[0104] In some implementations, the blockage detection module can be specifically used to: determine the unblocked arc length corresponding to the non-blocked angle; and determine that the vehicle is in a first trapped scenario when the unblocked arc length is less than or equal to a preset arc length threshold.

[0105] In some implementations, the escape point determination module is specifically used to: determine a first mapping point on the road reference line where the foremost edge of the vehicle is mapped in the vehicle's direction of travel; and determine the coordinate point on the road reference line that is a first preset distance away from the first mapping point as the target escape point.

[0106] In some implementations, the multiple entrapment scenario detection strategies include a second entrapment scenario detection strategy corresponding to a second entrapment scenario where the vehicle is blocked by an obstacle.

[0107] The blockage detection module can be used to: detect obstacles within the vehicle's obstacle detection range, which is a preset distance in the vehicle's direction of travel; and determine that the vehicle is in a second entrapment scenario when an obstacle is detected within the obstacle detection range, wherein the target entrapment scenario includes the second entrapment scenario.

[0108] In some implementations, the escape point determination module is specifically used to: When the second entrapment scenario only has the first obstacle, determine the target escape point as a coordinate point on the road reference line that is a second preset distance away from the second mapping point, wherein the second mapping point is the coordinate point on the road reference line mapped from the foremost point of the first obstacle in the vehicle's driving direction; or, when the second entrapment scenario has multiple obstacles, determine the target escape point as a coordinate point on the road reference line that is a third preset distance away from the third mapping point, wherein the third mapping point is the coordinate point on the road reference line mapped from the foremost point of the second obstacle in the vehicle's driving direction; the second obstacle is the obstacle furthest from the vehicle among the multiple obstacles in the driving direction, and the mapping distance between two adjacent obstacles on the road reference line is less than or equal to the third preset distance.

[0109] In some implementations, the path planning module 802 is specifically used to: generate a static grid cost map corresponding to the vehicle's driving road, the static grid cost map including multiple grids; perform an initial path search on the static grid cost map, starting from the target escape point, to obtain the costs from multiple grids to the target escape point, and record the costs from multiple grids to the target escape point to generate a distance cost map; and perform at least one path search based on the static grid cost map and the distance cost map, ending at the target escape point, to generate an escape planning path, wherein the heuristic cost of each node in the at least one path search is associated with the cost from the grid where that node is located to the target escape point in the distance cost map.

[0110] In some implementations, the path planning module 802 is further specifically used to: identify unreachable and reachable grids in the static grid cost map based on congestion information on the driving road, wherein the congestion information is used to indicate obstacles and road boundaries, unreachable grids are grids where obstacles or road boundaries are located, and reachable grids are grids other than unreachable grids; wherein the initial path search and at least one path search use reachable grids located on the road in the static grid cost map as nodes.

[0111] The vehicle control device 800 in the trapped scenario provided in this application embodiment can execute the scheme shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be repeated here.

[0112] Figure 9 shows a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application.

[0113] The electronic device may include a processor 901 and a memory 902 storing computer program instructions.

[0114] Specifically, the processor 901 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0115] Memory 902 may include mass storage for storing data or instructions. For example, and not limitingly, memory 902 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 902 may include removable or non-removable (or fixed) media. Where appropriate, memory 902 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 902 is non-volatile solid-state memory.

[0116] In some embodiments, memory 902 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of this disclosure.

[0117] The processor 901 implements the vehicle control method in the trapped scenario in any of the above embodiments by reading and executing computer program instructions stored in the memory 902.

[0118] In one example, the electronic device may also include a communication interface 903 and a bus 910. As shown in Figure 9, the processor 901, memory 902, and communication interface 903 are connected via bus 910 and communicate with each other.

[0119] The communication interface 903 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0120] Bus 910 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 910 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0121] The electronic device can execute the vehicle control method in the trapped scenario in the embodiments of this application, thereby realizing the vehicle control method and device in the trapped scenario described in conjunction with Figures 1 to 9.

[0122] In addition, in conjunction with the vehicle control method in the trapped scenario described in the above embodiments, this application also provides a computer storage medium. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement the vehicle control method in the trapped scenario described in the above embodiments.

[0123] In conjunction with the vehicle control method in the trapped scenario described in the above embodiments, this application also provides a computer program product. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device implements the vehicle control method in the trapped scenario described in the above embodiments.

[0124] In conjunction with the electronic devices in the above embodiments, this application also provides a vehicle that includes the electronic devices in the above embodiments.

[0125] Vehicles can be private cars, such as sedans, SUVs (Sport Utility Vehicles), MPVs (Multi-Purpose Vehicles), or pickup trucks. Vehicles can also be commercial vehicles, such as vans, buses, small trucks, or large semi-trailers. Vehicles can be either gasoline-powered or new energy vehicles. When a vehicle is a new energy vehicle, it can be a hybrid or a pure electric vehicle.

[0126] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0127] The functional modules / units shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When a functional module / unit is implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When a functional module / unit is implemented in software, the elements of this application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0128] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0129] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods (apparatus / devices / systems) and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0130] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for controlling a vehicle in a trapped scenario, comprising: When the vehicle is detected to be in a target distress scenario, a target escape point corresponding to the target distress scenario is determined, and the target escape point is located on the road reference line in front of the vehicle in the direction of the vehicle's travel; A path planning operation is performed with the target escape point as the endpoint to generate an escape planning path; If the escape route is successfully generated and there is a reversal path within the escape route, the vehicle is controlled to move according to the escape route to guide the vehicle out of the trapped situation. If the path planning operation is executed a preset number of times and no escape path is generated, or if the escape path is successfully generated but no reversal path exists in the escape path, the path planning operation is stopped to end the control of the vehicle to escape the trapped situation.

2. The method according to claim 1, wherein, Before determining the target escape point corresponding to the target entrapment scenario when the vehicle is detected to be in a target entrapment scenario, the method further includes: During the vehicle's operation, in response to the vehicle coming to a stop, a vehicle congestion detection operation is performed based on a preset set of multiple congestion scenario detection strategies, which correspond to different congestion scenarios. If a vehicle is detected to be stuck in traffic while performing a vehicle traffic jam detection operation based on a target stuck scenario detection strategy, the stuck scenario in which the vehicle is located, corresponding to the target stuck scenario detection strategy, is determined as the target stuck scenario.

3. The method according to claim 2, wherein, The multiple entrapment scenario detection strategies include a first entrapment scenario detection strategy corresponding to the first entrapment scenario, where the vehicle is blocked by a road boundary. The vehicle congestion detection operation based on preset multiple congestion scenario detection strategies includes: Obtain the preset sector detection range corresponding to the vehicle; Determine the blocking angle of the vehicle on the road boundary within the preset sector detection range; Based on the non-blockage angles within the preset sector detection range, excluding the blockage angle, it is determined whether the vehicle is in the first trapped scenario. The target trapped scenario includes the first trapped scenario.

4. The method according to claim 3, wherein, Determining the blocking angle of the vehicle on the road boundary within the preset sector detection range includes: Determine the first intersection point and the second intersection point formed between the preset sector detection range and the road boundary, wherein the first intersection point and the second intersection point are located on the road boundary; The angle between the first intersection point and the second intersection point within the preset sector detection range is determined as the blocking angle of the vehicle on the road boundary.

5. The method according to claim 4, wherein, The step of determining whether the vehicle is in the first trapped scenario based on the non-blocking angles within the preset fan-shaped detection range, excluding the blockage angle, includes: Determine the unblocked arc length corresponding to the unblocked angle; If the unblocked arc length is less than or equal to a preset arc length threshold, the vehicle is determined to be in the first trapped scenario.

6. The method according to any one of claims 3 to 5, wherein, When the vehicle is in the first trapped scenario, the step of determining the target escape point corresponding to the target trapped scenario when the vehicle is detected to be in the target trapped scenario includes: In the direction of travel of the vehicle, determine the first mapping point on the road reference line where the foremost part of the vehicle is mapped. The coordinate point on the road reference line that is a first preset distance away from the first mapping point is determined as the target escape point.

7. The method according to claim 2, wherein, The multiple entrapment scenario detection strategies include a second entrapment scenario detection strategy corresponding to the second entrapment scenario, where the vehicle is blocked by one or more obstacles. The vehicle congestion detection operation based on preset multiple congestion scenario detection strategies includes: Obstacle detection is performed within the obstacle detection range of the vehicle, which is a range within a preset distance in the direction of travel of the vehicle. If one or more obstacles are detected within the obstacle detection range, the vehicle is determined to be in the second trapped scenario. The target trapped scenario includes the second trapped scenario.

8. The method according to claim 7, wherein, When the vehicle is in the second entrapment scenario, the step of determining the target escape point corresponding to the target entrapment scenario upon detecting that the vehicle is in the target entrapment scenario includes: In the second trapped scenario where there is only one obstacle, the coordinate point on the road reference line that is a second preset distance away from the second mapping point is determined as the target escape point. The second mapping point is the coordinate point on the road reference line mapped from the foremost point of the obstacle in the vehicle's direction of travel; or... In the case of multiple obstacles in the second trapped scenario, the coordinate point on the road reference line that is a third preset distance away from the third mapping point is determined as the target escape point. The third mapping point is the coordinate point on the road reference line mapped from the foremost front end of the first obstacle among the multiple obstacles in the direction of vehicle travel. The first obstacle is the obstacle farthest from the vehicle among the multiple obstacles in the direction of travel, and the mapping distance between two adjacent obstacles on the road reference line is less than or equal to the third preset distance.

9. The method according to any one of claims 1 to 8, wherein, The step of performing path planning operation with the target escape point as the endpoint to generate an escape planning path includes: Generate a static grid cost map corresponding to the driving road of the vehicle, the static grid cost map comprising multiple grids; On the static grid cost map, an initial path search is performed starting from the target escape point to obtain the cost from the multiple grids to the target escape point, and the cost from the multiple grids to the target escape point is recorded to generate a distance cost map. Based on the static grid cost map and the distance cost map, at least one path search is performed with the target escape point as the endpoint to generate the escape planning path. For each of the multiple nodes in the at least one path search, the heuristic cost of the node is associated with the cost from the grid where the node is located to the target escape point in the distance cost map.

10. The method according to claim 9, wherein, After generating the static raster cost map corresponding to the vehicle's driving path, the method further includes: Based on the congestion information on the driving road, unreachable and reachable grids in the static grid cost map are identified, wherein the congestion information is configured to indicate obstacles and road boundaries, the unreachable grid is the grid where the obstacle or the road boundary is located, and the reachable grid is the grid other than the unreachable grid; In the initial path search and the at least one path search, the reachable grid located in the road in the static grid cost map is a plurality of nodes.

11. A control device for a vehicle in a trapped situation, comprising: The escape point determination module is configured to determine a target escape point corresponding to the target entrapment scenario when the vehicle is detected to be in a target entrapment scenario. The target escape point is located on a road reference line in front of the vehicle in the vehicle's direction of travel. The path planning module is configured to perform path planning operations with the target escape point as the endpoint to generate an escape planning path; The motion control module is configured to control the vehicle to move along the escape path when the escape path is successfully generated and there is a reversal path in the escape path, so as to guide the vehicle to get out of the trapped scene; The path planning stop module is configured to stop executing the path planning operation when the path planning operation is executed a preset number of times and no escape path is generated, or when the escape path is successfully generated and no back path exists in the escape path, so as to end the control of the vehicle to escape from the trapped scenario.

12. An electronic device, comprising: At least one processor; as well as At least one memory, coupled to the at least one processor, and configured to store computer program instructions; The at least one processor is configured to read the computer program instructions from the at least one memory and execute the computer program instructions to implement the vehicle control method in the trapped scenario as described in any one of claims 1-10.

13. A non-transitory computer-readable storage medium, wherein, The non-transitory computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the vehicle control method in a trapped scenario as described in any one of claims 1-10.

14. A vehicle comprising the electronic equipment as claimed in claim 12.

15. A computer program product comprising a computer program executed by at least one processor to implement a method for controlling a vehicle in a trapped scenario as claimed in any one of claims 1 to 10.

Images