Vehicle path planning method and system, device, vehicle, medium, and product

Abstract

A vehicle path planning method and system, a device, a vehicle, a medium, and a product. In the present application, the method comprises: on the basis of an acquired image of a pothole area in front of a vehicle, obtaining an area division map of the pothole area, wherein the area division map comprises a drivable area, and the drivable area is an area where the vehicle can safely drive in the pothole area; and on the basis of the drivable area in the area division map, obtaining the shortest path for passing through the pothole area for reference of the driver. In this way, it is ensured that the vehicle can safely and quickly pass through the pothole area on the road surface.

Description

Vehicle path planning method, system, device, vehicle, medium and product

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application filed on January 31, 2024, with application number 202410143032.0 and invention name “Vehicle Path Planning Method, System, Device, Vehicle, Medium and Product”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application relates to the field of vehicle technology, and in particular to a vehicle path planning method, system, device, vehicle, medium and product. Background Art

[0004] Potholes refer to holes formed in local areas of the road due to problems such as aggregate loss. They are a relatively serious road condition. The current method of dealing with potholes is basically based on the intuition of vehicle drivers. That is, they manually judge whether the pothole area can be passed. If not, they choose to bypass it. However, this method of relying on the driver's intuition to pass through potholes cannot guarantee the safety of vehicles and passengers.

[0005] In related technologies, intelligent systems are often used to identify potholes on the road and issue warnings to drivers after identifying potholes, but they are unable to guide drivers on how to safely pass through potholes. Technical issues

[0006] The vehicle path planning method, system, device, vehicle, medium and product provided by the embodiments of the present application can solve the technical problem of being unable to guide the driver to safely pass through potholes on the road. Technical Solutions

[0007] The Summary of the Invention introduces a series of simplified concepts that will be further described in the Detailed Description of the Invention. The Summary of the Invention of this application is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0008] In order to solve the existing problems, the present application provides a vehicle path planning method, which includes:

[0009] acquiring an image of a pothole area in front of the vehicle;

[0010] obtaining a region division map of the pothole region based on the image of the pothole region, wherein the region division map is divided into drivable regions;

[0011] A shortest path through the pothole area is obtained based on the drivable area in the area division map.

[0012] Exemplarily, the method further includes: controlling the vehicle to pass through the pothole area along the shortest path.

[0013] Illustratively, after obtaining the area division map of the pothole area and before obtaining the shortest path through the pothole area based on the drivable area in the area division map, the method further includes:

[0014] The area division map is preprocessed to obtain a preprocessed area division map; wherein the shortest path through the pothole area is obtained based on the drivable area in the preprocessed area division map.

[0015] Exemplarily, the area other than the drivable area in the area division map is divided into a non-drivable area, and the preprocessing of the area division map to obtain a preprocessed area division map includes:

[0016] An image opening operation is performed on the drivable area in the area division map to re-divide part of the drivable area into the non-drivable area, thereby obtaining an area division map after image opening operation, and the area division map after image opening operation is the preprocessed area division map.

[0017] Exemplarily, the preprocessing the region division map to obtain a preprocessed region division map further includes:

[0018] The lateral width of the drivable area in the area division map after the image opening operation is compared with the width of the vehicle, and the drivable area whose lateral width is less than a preset multiple of the width of the vehicle is re-divided into the non-drivable area to obtain the preprocessed area division map; wherein the lateral width is the width in a direction perpendicular to the driving direction of the vehicle.

[0019] Exemplarily, the preset multiple is 1.2.

[0020] Exemplarily, obtaining the shortest path through the pothole area based on the drivable area in the area division map includes:

[0021] An A-Star algorithm is used to obtain the shortest path through the pothole area based on the drivable area in the area division map.

[0022] Exemplarily, controlling the vehicle to pass through the pothole area along the shortest path includes:

[0023] establishing a kinematic model of the vehicle;

[0024] The vehicle is controlled to pass through the pothole area along the shortest path based on the kinematic model.

[0025] Exemplarily, establishing the kinematic model of the vehicle includes:

[0026] A kinematic model of the vehicle is established based on Ackermann steering geometry theory.

[0027] Exemplarily, it also includes:

[0028] An Ackermann correction rate is used to correct the kinematic model established based on the Ackermann steering geometry theory to obtain a corrected kinematic model; wherein the corrected kinematic model is used to control the vehicle to pass through the pothole area along the shortest path.

[0029] Exemplarily, controlling the vehicle to pass through the pothole area along the shortest path based on the kinematic model includes:

[0030] A model predictive control algorithm is adopted to control the vehicle to pass through the pothole area along the shortest path based on the kinematic model.

[0031] Another aspect of the present application provides a vehicle path planning system, comprising:

[0032] a sensor for acquiring an image of the pothole area in front of the vehicle;

[0033] The controller is used to: obtain an area division map of the pothole area based on the image of the pothole area, wherein the area division map is divided into drivable areas, and obtain the shortest path through the pothole area based on the drivable areas in the area division map.

[0034] Exemplarily, the controller is further configured to control the vehicle to pass through the pothole area along the shortest path.

[0035] Illustratively, after obtaining the area division map of the pothole area and before obtaining the shortest path through the pothole area based on the drivable area in the area division map, the controller is further configured to:

[0036] The area division map is preprocessed to obtain a preprocessed area division map; wherein the shortest path through the pothole area is obtained based on the drivable area in the preprocessed area division map.

[0037] Exemplarily, the area other than the drivable area in the area division map is divided into a non-drivable area, and the controller preprocesses the area division map to obtain a preprocessed area division map, including:

[0038] The controller performs an image opening operation on the drivable area in the area division map to re-divide part of the drivable area into the non-drivable area, and obtains an area division map after the image opening operation. The area division map after the image opening operation is the preprocessed area division map.

[0039] Exemplarily, the controller preprocesses the region division map to obtain a preprocessed region division map, further comprising:

[0040] The controller compares the lateral width of the drivable area in the area division map after the image opening operation with the width of the vehicle, and re-divides the drivable area whose lateral width is less than a preset multiple of the width of the vehicle into the non-drivable area to obtain the preprocessed area division map; wherein, the lateral width is the width in a direction perpendicular to the driving direction of the vehicle.

[0041] Exemplarily, the preset multiple is 1.2.

[0042] Exemplarily, the controller obtains the shortest path through the pothole area based on the drivable area in the area division map, including:

[0043] The controller uses an A-Star algorithm to obtain the shortest path through the pothole area based on the drivable area in the area division map.

[0044] Exemplarily, the controller controls the vehicle to pass through the pothole area along the shortest path, including:

[0045] The controller establishes a kinematic model of the vehicle;

[0046] The controller controls the vehicle to pass through the pothole area along the shortest path based on the kinematic model.

[0047] Exemplarily, the controller establishes the kinematic model of the vehicle, including: the controller establishes the kinematic model of the vehicle based on Ackermann steering geometry theory.

[0048] Exemplarily, the controller is further used to: use an Ackermann correction rate to correct the kinematic model established based on the Ackermann steering geometry theory to obtain a corrected kinematic model; wherein the corrected kinematic model is used to control the vehicle to pass through the pothole area along the shortest path.

[0049] Exemplarily, the controller controls the vehicle to pass through the pothole area along the shortest path based on the kinematic model, including:

[0050] The controller uses a model predictive control algorithm to control the vehicle to pass through the pothole area along the shortest path based on the kinematic model.

[0051] On the other hand, the present application provides an electronic device, including a processor and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the processor executes the aforementioned vehicle path planning method.

[0052] On the other hand, the present application provides a vehicle, which includes the aforementioned vehicle path planning system, or includes the aforementioned electronic device.

[0053] On the other hand, the present application provides a computer-readable storage medium having computer instructions stored thereon. When the computer instructions are executed by a processor, the processor is enabled to execute the aforementioned vehicle path planning method.

[0054] On the other hand, the present application provides a computer program product, including computer instructions, which implement the above-mentioned vehicle path planning method when executed by a processor.

[0055] The vehicle path planning method, system, device, vehicle, medium and product of the present application can obtain an area division map of the pothole area based on an image of the pothole area in front of the vehicle. The area division map is divided into drivable areas, and the drivable areas are areas where the vehicle can safely drive in the pothole area. The shortest path through the pothole area is then obtained based on the drivable areas in the area division map for the driver's reference, thereby ensuring that the vehicle passes through the pothole area on the road safely and quickly. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0057] In the attached figure:

[0058] FIG1 shows a schematic flow chart of a vehicle path planning method according to a specific embodiment of the present application.

[0059] FIG2 shows a schematic diagram of structural elements for image opening operation according to a specific embodiment of the present application.

[0060] FIG3 shows a schematic diagram of the Ackermann steering geometry theory according to another specific embodiment of the present application.

[0061] FIG4 shows a schematic structural block diagram of a vehicle path planning system according to a specific embodiment of the present application.

[0062] FIG5 shows a schematic structural block diagram of an electronic device according to another specific embodiment of the present application.

[0063] Implementation Methods of the Application

[0064] In order to make the purpose, technical solutions and advantages of the present application more apparent, example embodiments according to the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in this application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of this application.

[0065] FIG1 shows a schematic flow chart of a vehicle path planning method according to a specific embodiment of the present application.

[0066] As shown in FIG1 , the vehicle path planning method 100 may include the following steps:

[0067] In step S110 , an image of a pothole area in front of the vehicle is acquired.

[0068] In step S120 , a region division map of the pothole region is obtained based on the image of the pothole region, wherein the region division map is divided into drivable areas.

[0069] In step S130 , a shortest path passing through the pothole area is obtained based on the drivable area in the area division map.

[0070] In an embodiment of the present application, an image of a pothole area in front of a vehicle can be acquired; based on the acquired image of the pothole area, a region division map of the pothole area can be generated, wherein the region division map defines a drivable area; and based on the drivable area in the region division map, a shortest path through the pothole area can be obtained for the driver's reference. For example, an object detection algorithm can be used to identify potholes in the image acquired in front of the vehicle. For example, after identifying the pothole area in front of the vehicle, parameters such as the depth, size, location, morphology, and type of the pothole in the pothole area can be acquired using a binocular measurement algorithm or a laser ranging algorithm. These pothole parameters are then compared with parameters such as the vehicle's tire radius and vehicle length, and mathematical operations are performed to determine the drivable area of ​​the vehicle, which is the drivable area of ​​the pothole area. This drivable area is then displayed in the region division map of the pothole area.

[0071] Therefore, the vehicle path planning method of the embodiment of the present application can obtain an area division map of the pothole area based on the image of the pothole area in front of the vehicle. The area division map is divided into a drivable area, which is an area where the vehicle can safely drive in the pothole area. The shortest path through the pothole area is then obtained based on the drivable area in the area division map for the driver's reference, thereby ensuring that the vehicle passes through the pothole area on the road safely and quickly.

[0072] In an embodiment of the present application, after obtaining the shortest path through a pothole area, the method of the present application further includes: controlling the vehicle to pass through the pothole area along the shortest path. For example, after obtaining the shortest path through the pothole area, the shortest path can be provided to the driver for reference; alternatively, the vehicle's system can directly take over and control the vehicle to pass through the pothole area along the shortest path. Compared to the driver manually controlling the vehicle through the pothole area based on the shortest path, system-controlled vehicle control can ensure safer and more efficient passage through the pothole area.

[0073] In an embodiment of the present application, after obtaining a region division map of the pothole area and before obtaining the shortest path through the pothole area based on the drivable area in the region division map, the method of the present application further includes: preprocessing the region division map to obtain a preprocessed region division map; wherein the shortest path through the pothole area is obtained based on the drivable area in the preprocessed region division map. Exemplarily, the primary purpose of preprocessing the region division map is to further process the drivable area therein to reduce the difficulty and time of subsequent processing steps, thereby making the method of the present application more efficient.

[0074] Specifically, in the area division map, all areas except the drivable areas are divided into non-drivable areas, and the non-drivable areas indicate that vehicles cannot drive in the areas. The area division map is preprocessed to obtain a preprocessed area division map, including: performing an image opening operation on the drivable areas in the area division map to re-divide part of the drivable areas into non-drivable areas, and obtaining a area division map after the image opening operation. The area division map after the image opening operation is the preprocessed area division map. Exemplarily, the drivable areas in the obtained area division map are generally in a state of range connectivity, wherein there are some small drivable areas that are not connected to other drivable areas, or there are some small drivable areas isolated from the large range of drivable areas, and these small drivable areas are likely to interfere with subsequent processing steps, so it is necessary to perform an opening operation on the drivable areas in the area division map to eliminate these small drivable areas, so as to better serve the subsequent processing steps.

[0075] Specifically, an opening operation is performed on the drivable area in the region division map, including: first performing an erosion operation on the drivable area, and then performing an expansion operation on the drivable area after the erosion operation. Wherein, both the erosion operation and the expansion operation require the use of a structural element. Taking the region division map as a binary map as an example, where the pixel value of the drivable area is 1 and the pixel value of the non-drivable area is 0, the structural element shown in Figure 2 can be used to perform an erosion operation and an expansion operation on the drivable area in the region division map, where the origin of the structural element shown in Figure 2 is the center point. Exemplarily, the region division map can also be a grayscale map or a color map, and this application does not limit this. When the region division map is a grayscale map or a color map, the method of performing an opening operation on the drivable area in the region division map is similar to when the region division map is a binary map. Exemplarily, any other suitable structural element can also be used to perform an erosion operation and an expansion operation on the drivable area in the region division map, and this application does not limit this. Exemplarily, after performing an opening operation on the drivable area in the image area division map, a closing operation may be performed on the drivable area in the image area division map. Specifically, the operation includes first performing an expansion operation on the drivable area in the image area division map that has undergone the opening operation, and then performing an erosion operation.

[0076] In an embodiment of the present application, preprocessing the region division map to obtain a preprocessed region division map further includes: comparing the lateral width of the drivable area in the region division map subjected to the image opening operation with the width of the vehicle, and reclassifying the drivable area whose lateral width is less than a preset multiple of the vehicle width as a non-drivable area, thereby obtaining the preprocessed region division map; wherein the lateral width is the width in a direction perpendicular to the vehicle's travel direction. Specifically, the vehicle's travel direction refers to the direction of the vehicle when encountering a pothole. Assuming that the vehicle's travel direction when encountering the pothole is the y-axis direction, the lateral width of the drivable area refers to the width of the drivable area along the x-axis direction, where the x-axis is perpendicular to the y-axis. In summary, preprocessing the area division map may only include performing an opening operation on the drivable area in the area division map; or, preprocessing the area division map may include performing an opening operation on the drivable area in the area division map to obtain the area division map after the opening operation, and then comparing the lateral width of the drivable area in the area division map after the image opening operation with the width of the vehicle, and re-dividing the drivable area whose lateral width is less than the width of the vehicle and a preset multiple as a non-drivable area.

[0077] In an embodiment of the present application, the preset multiple of the vehicle's width is 1.2. This means that any drivable area with a lateral width less than 1.2 times the vehicle's width is reclassified as a non-drivable area, and the remaining drivable area has a lateral width greater than or equal to 1.2 times the vehicle's width. For example, the preset multiple of the vehicle's width should be greater than or equal to 1, meaning that the width of the drivable area should be at least equal to the vehicle's width. For example, to prevent accidents and to provide a safety margin, the preset multiple of the vehicle's width should be greater than 1.

[0078] In an embodiment of the present application, the shortest path through the pothole area is obtained based on the drivable area in the area division map, including: using the A-Star algorithm to obtain the shortest path through the pothole area based on the drivable area in the area division map. Exemplarily, when using the A-Star algorithm to obtain the shortest path, it is necessary to divide the area division map into grid-like nodes in rows and columns, and each node can be a square, triangle, polygon or other shape, wherein the nodes in the drivable area are defined as available nodes, and the nodes in the non-drivable area are defined as unavailable nodes, that is, the non-drivable area is equivalent to an obstacle. Exemplarily, when using the A-Star algorithm to obtain the shortest path, it is also necessary to predefine a heuristic function, as shown in the following formula:

[0079] f(n)=g(n)+h(n)

[0080] Where f(n) is the estimated cost from the starting point via node n to the target point, g(n) is the actual cost from the singular point to node n, and h(n) is the estimated cost of the shortest path from node n to the target point. The cost is usually calculated using distance (Manhattan distance / Euclidean distance, etc.). The starting point is the point where the vehicle enters the pothole area, and the target point is the point where the vehicle leaves the pothole area. Therefore, the starting point and the target point must be within the drivable area.

[0081] Next, we will describe in detail the logical steps of using the A-Star algorithm to obtain the shortest path through the pothole area based on the drivable area in the area partition graph.

[0082] First, add the starting point to the open list.

[0083] Then, repeat the following steps:

[0084] Traverse the open list, calculate f(n) for each node in the open list, and select the node with the smallest f(n) from the open list as the current node.

[0085] Perform a heuristic search. Specifically, expand all neighboring nodes of the current node. The following situations will be encountered: In case A, if the neighboring node is an unavailable node, it will be ignored; if the neighboring node is an available node and is not in the open list, it will be added to the open list, and the parent node of the neighboring node will be set to the current node, and g(n) and h(n) of the neighboring node will be calculated; In case B, if the neighboring node is already in the open list or the closed list (Close List), check whether this path (the path from the current node to the neighboring node) is better, with the reference index being g(n). If reaching the neighboring node through this path makes the g(n) of the neighboring node smaller, it means that the path is better, then the parent node of the neighboring node will be reset to the current node, and g(n) and h(n) of the neighboring node will be recalculated.

[0086] Move the current node to the closed list.

[0087] When one of the following conditions is met, the loop of the above steps is exited and the A-Star algorithm ends: (1) The target point is added to the open list. At this time, the shortest path from the starting point to the target point can be obtained by tracing back from the target point to the starting point; (2) If the target point cannot be found and the open list is empty, it means that there is no feasible path from the starting point to the target point.

[0088] Exemplarily, when the A-Star algorithm is used to obtain the shortest path, the state jump priority can also be predefined. For example, if the target point is located in front of the left of the starting point, the state jump priority can be defined as: F (front) > L (left) > R (right) > B (back). The state jump priority is used to select the order of nodes when there are multiple nodes with the smallest f(n) in the open list. For example, if there are two nodes with the smallest f(n) in the open list, one node is located in front of the current node, and the other node is located behind the current node, then the node located in front of the current node is given priority. Exemplarily, the state jump priority may not be predefined. In this case, when there are multiple nodes with the smallest f(n) in the open list, in order to speed up the calculation, the node with the smallest f(n) that is added to the open list last is generally given priority.

[0089] In an embodiment of the present application, controlling a vehicle to navigate a pothole area along the shortest path includes: establishing a kinematic model of the vehicle; and controlling the vehicle to navigate the pothole area along the shortest path based on the kinematic model. For example, after establishing the kinematic model of the vehicle, to enable subsequent control, the kinematic model must first be linearized and then discretized.

[0090] Specifically, establishing a kinematic model of the vehicle includes: establishing a kinematic model of the vehicle based on Ackermann steering geometry theory. As shown in the following formula, the following formula is a linear discrete model obtained by linearizing and discretizing the kinematic model of the vehicle based on Ackermann steering geometry theory:

[0091] ΔX(k+1)=A*ΔX(k)+B*ΔU(k)

[0092] Among them, X is the state vector, U is the input control vector, A is the state matrix, and B is the control matrix. Specifically:

[0093] As shown in Figure 3, v represents vehicle speed (rear axle), L represents wheelbase, represents the vehicle heading angle, δ represents the front wheel turning angle, and (x, y) represents the coordinates of the rear axle center.

[0094] For example, the above is a linear discrete model obtained by linearizing and discretizing the kinematic model of the vehicle established based on the Ackerman steering geometry theory under ideal conditions. In actual situations, due to the existence of tire slip angle and tire wear rate, it is necessary to introduce the Ackerman correction rate to correct the kinematic model of the vehicle established based on the Ackerman steering geometry theory to obtain a corrected kinematic model; wherein the corrected kinematic model is used to control the vehicle to pass through the pothole area along the shortest path. For example, the Ackerman correction rate R A As shown in the following formula:

[0095] Among them, θ o is the outer front wheel angle, θ i According to θ o The theoretical inner front wheel turning angle is calculated using Ackerman steering geometry theory, and θ ia The outer front wheel turning angle is θ o The actual inner front wheel angle of the car.

[0096] The linear discrete model obtained by linearizing and discretizing the corrected motion model is shown as follows:

[0097] ΔX(k+1)=A*R A *ΔX(k)+B*R A *ΔU(k)

[0098] In an embodiment of the present application, controlling a vehicle to pass through a pothole area along the shortest path based on a kinematic model includes: using a model predictive control (MPC) algorithm to control the vehicle to pass through the pothole area along the shortest path based on the kinematic model. The MPC algorithm is shown in the following formula:

[0099] min

[0100] stu min ≤u k ≤u max ,y min ≤y k ≤y max

[0101] Among them, J is the cost function, P is the final state weight matrix, Q is the process state weight matrix, R is the input weight matrix, x(k) is the process state vector, u(k) is the control input vector, x N is the final state vector; the inequality is the input u k With the output y k The equality and inequality constraints that should be satisfied.

[0102] In the embodiments of the present application, although the model predictive control algorithm is independent of the specific model, the actual implementation requires the use of a vehicle model. The aforementioned A-Star algorithm does not consider the dynamic model of the vehicle when obtaining the shortest path. Therefore, the model predictive control algorithm can consider the dynamic model of the vehicle based on the shortest path obtained by the aforementioned A-Star algorithm. At the same time, the model prediction algorithm will also consider the control within the step length in the future, so that the actual driving trajectory planning of the vehicle can be continuously optimized based on the shortest path.

[0103] The above exemplifies a vehicle path planning method according to a specific embodiment of the present application. Based on the above description, the vehicle path planning method according to a specific embodiment of the present application can obtain a region division map of the pothole area based on an image of the pothole area in front of the vehicle obtained, wherein the region division map is divided into drivable areas, and the drivable areas are areas where the vehicle can safely drive in the pothole area. The shortest path through the pothole area is then obtained based on the drivable areas in the region division map for the driver's reference, thereby ensuring that the vehicle passes through the pothole area on the road safely and quickly. For example, after obtaining the shortest path, the system on the vehicle can also take over to control the vehicle to pass through the pothole area along the shortest path. Compared with the driver manually controlling the vehicle to pass through the pothole area with reference to the shortest path, the system controlling the vehicle can ensure that the vehicle passes through the pothole area more safely and efficiently.

[0104] Next, a vehicle path planning system according to a specific embodiment of the present application will be described with reference to Figure 4. Figure 4 shows a schematic structural block diagram of a vehicle path planning system according to a specific embodiment of the present application.

[0105] As shown in Figure 4, the vehicle path planning system 400 of the present application includes a sensor 410 and a controller 420, wherein: the sensor 410 is used to obtain an image of the pothole area in front of the vehicle; the controller 420 is used to: obtain an area division map of the pothole area based on the image of the pothole area, the area division map is divided into drivable areas, and obtain the shortest path through the pothole area based on the drivable areas in the area division map.

[0106] In an embodiment of the present application, sensor 410 can capture an image of a pothole area in front of a vehicle. Based on the captured image of the pothole area, controller 420 then generates a map of the pothole area, where the map defines drivable areas. Based on the drivable areas in the map, controller 420 then determines the shortest path through the pothole area for the driver's reference. For example, controller 420 can use an object detection algorithm to identify potholes in the image captured in front of the vehicle. After identifying the pothole area in front of the vehicle, controller 420 can use a binocular measurement algorithm or a laser ranging algorithm to determine parameters such as the depth, size, location, morphology, and type of the potholes in the pothole area. The controller then compares these pothole parameters with parameters such as the vehicle's tire radius and vehicle length, and performs mathematical operations to determine the drivable area of ​​the pothole area. This drivable area is then displayed in the map of the pothole area. For example, sensor 410 includes a binocular camera, a depth camera, and a lidar. Illustratively, the controller 420 includes a microcontroller.

[0107] Therefore, in the vehicle path planning system of an embodiment of the present application, the controller can obtain an area division map of the pothole area based on the image of the pothole area in front of the vehicle obtained, and the area division map is divided into a drivable area, which is an area where the vehicle can safely drive in the pothole area. The controller then obtains the shortest path through the pothole area based on the drivable area in the area division map for the driver's reference, thereby ensuring that the vehicle passes through the pothole area on the road safely and quickly.

[0108] In an embodiment of the present application, after obtaining the shortest path through a pothole area, controller 420 is further configured to control the vehicle to pass through the pothole area along the shortest path. For example, after obtaining the shortest path through the pothole area, the shortest path can be provided to the driver for reference; alternatively, controller 420 in the vehicle path planning system can directly take over and control the vehicle to pass through the pothole area along the shortest path. Compared to the driver manually controlling the vehicle through the pothole area based on the shortest path, control by controller 420 can ensure safer and more efficient passage through the pothole area.

[0109] In an embodiment of the present application, after obtaining a region division map of the pothole area and before determining the shortest path through the pothole area based on the drivable area in the region division map, controller 420 is further configured to preprocess the region division map to obtain a preprocessed region division map; wherein the shortest path through the pothole area is determined based on the drivable area in the preprocessed region division map. Exemplarily, the primary purpose of preprocessing the region division map is to further process the drivable area therein, thereby reducing the difficulty and time required for subsequent processing steps, thereby making the system of the present application more efficient.

[0110] In an embodiment of the present application, the area other than the drivable area in the area division map is divided into a non-drivable area, and the controller 420 pre-processes the area division map to obtain a pre-processed area division map, including: the controller 420 performs an image opening operation on the drivable area in the area division map to re-divide part of the drivable area into a non-drivable area, and obtains a area division map after the image opening operation, and the area division map after the image opening operation is a pre-processed area division map. Exemplarily, the drivable area in the obtained area division map is generally in a state of range connectivity, wherein there are some small drivable areas that are not connected to other drivable areas, or there are some small drivable areas isolated from the large range of drivable areas, and these small drivable areas are likely to interfere with subsequent processing steps, so it is necessary to perform an opening operation on the drivable area in the area division map to eliminate these small drivable areas, so as to better serve the subsequent processing steps.

[0111] Specifically, the controller 420 performs an opening operation on the drivable area in the region division map, including: first performing an erosion operation on the drivable area, and then performing an expansion operation on the drivable area after the erosion operation. Wherein, both the erosion operation and the expansion operation require the use of a structural element. Taking the region division map as a binary map as an example, where the pixel value of the drivable area is 1 and the pixel value of the non-drivable area is 0, the structural element shown in Figure 2 can be used to perform an erosion operation and an expansion operation on the drivable area in the region division map, where the origin of the structural element shown in Figure 2 is the center point. Exemplarily, the region division map can also be a grayscale map or a color map, and this application does not limit this. When the region division map is a grayscale map or a color map, the method of performing an opening operation on the drivable area in the region division map is similar to when the region division map is a binary map. Exemplarily, any other suitable structural element can also be used to perform an erosion operation and an expansion operation on the drivable area in the region division map, and this application does not limit this. Exemplarily, after performing an opening operation on the drivable area in the image area division map, a closing operation may be performed on the drivable area in the image area division map. Specifically, the operation includes first performing an expansion operation on the drivable area in the image area division map that has undergone the opening operation, and then performing an erosion operation.

[0112] In an embodiment of the present application, the controller 420 preprocesses the region division map to obtain a preprocessed region division map, further comprising: comparing the lateral width of the drivable area in the region division map subjected to the image opening operation with the width of the vehicle, and reclassifying the drivable area whose lateral width is less than a preset multiple of the vehicle width as a non-drivable area, thereby obtaining a preprocessed region division map; wherein the lateral width is the width in a direction perpendicular to the vehicle's travel direction. Specifically, the vehicle's travel direction refers to the direction of the vehicle when encountering a pothole. Assuming that the vehicle's travel direction when encountering the pothole is the y-axis direction, the lateral width of the drivable area refers to the width of the drivable area along the x-axis direction, where the x-axis is perpendicular to the y-axis. In summary, the controller 420's preprocessing of the area division map may only include performing an opening operation on the drivable area in the area division map; or, the controller 420's preprocessing of the area division map may include performing an opening operation on the drivable area in the area division map to obtain the area division map after the opening operation, and then comparing the lateral width of the drivable area in the area division map after the image opening operation with the width of the vehicle, and re-dividing the drivable area whose lateral width is less than the width of the vehicle and a preset multiple as a non-drivable area.

[0113] In an embodiment of the present application, the preset multiple of the vehicle's width is 1.2. This means that any drivable area with a lateral width less than 1.2 times the vehicle's width is reclassified as a non-drivable area, and the remaining drivable area has a lateral width greater than or equal to 1.2 times the vehicle's width. For example, the preset multiple of the vehicle's width should be greater than or equal to 1, meaning that the width of the drivable area should be at least equal to the vehicle's width. For example, to prevent accidents and to provide a safety margin, the preset multiple of the vehicle's width should be greater than 1.

[0114] In an embodiment of the present application, the controller 420 obtains the shortest path through the pothole area based on the drivable area in the area division map, including: the controller 420 uses the A-Star algorithm to obtain the shortest path through the pothole area based on the drivable area in the area division map.

[0115] For example, when the controller 420 uses the A-Star algorithm to obtain the shortest path, it needs to divide the area partition map into grid-like nodes in rows and columns. Each node can be a square, triangle, polygon, etc., where nodes within the drivable area are defined as usable nodes, and nodes within the non-drivable area are defined as unusable nodes. That is, the non-drivable area is equivalent to an obstacle. For example, when the controller 420 uses the A-Star algorithm to obtain the shortest path, it also needs to predefine a heuristic function, as shown in the following formula:

[0116] f(n)=g(n)+h(n)

[0117] Where f(n) is the estimated cost from the starting point via node n to the target point, g(n) is the actual cost from the singular point to node n, and h(n) is the estimated cost of the shortest path from node n to the target point. The cost is usually calculated using distance (Manhattan distance / Euclidean distance, etc.). The starting point is the point where the vehicle enters the pothole area, and the target point is the point where the vehicle leaves the pothole area. Therefore, the starting point and the target point must be within the drivable area.

[0118] Next, the logical steps of the controller 420 using the A-Star algorithm to obtain the shortest path through the pothole area based on the drivable area in the area division map will be described in detail.

[0119] First, add the starting point to the open list.

[0120] Then, repeat the following steps:

[0121] Traverse the open list, calculate f(n) for each node in the open list, and select the node with the smallest f(n) from the open list as the current node.

[0122] Perform a heuristic search. Specifically, expand all neighboring nodes of the current node. The following situations will be encountered: In case A, if the neighboring node is an unavailable node, it will be ignored; if the neighboring node is an available node and is not in the open list, it will be added to the open list, and the parent node of the neighboring node will be set to the current node, and g(n) and h(n) of the neighboring node will be calculated; In case B, if the neighboring node is already in the open list or the closed list (Close List), check whether this path (the path from the current node to the neighboring node) is better, with the reference index being g(n). If reaching the neighboring node through this path makes the g(n) of the neighboring node smaller, it means that the path is better, then the parent node of the neighboring node will be reset to the current node, and g(n) and h(n) of the neighboring node will be recalculated.

[0123] Move the current node to the closed list.

[0124] When one of the following conditions is met, the loop of the above steps is exited and the A-Star algorithm ends: (1) The target point is added to the open list. At this time, the shortest path from the starting point to the target point can be obtained by tracing back from the target point to the starting point; (2) If the target point cannot be found and the open list is empty, it means that there is no feasible path from the starting point to the target point.

[0125] Exemplarily, the controller 420 may also predefine a state jump priority when using the A-Star algorithm to obtain the shortest path. For example, if the target point is located in front of the left of the starting point, the state jump priority may be defined as: F (front) > L (left) > R (right) > B (back). The state jump priority is used to select the order of nodes when there are multiple nodes with the smallest f(n) in the open list. For example, if there are two nodes with the smallest f(n) in the open list, one node is located in front of the current node, and the other node is located behind the current node, the node located in front of the current node is given priority. Exemplarily, the controller 420 may also not predefine a state jump priority. In this case, when there are multiple nodes with the smallest f(n) in the open list, in order to speed up the calculation, the node with the smallest f(n) that is added to the open list last is generally given priority.

[0126] In an embodiment of the present application, controller 420 controls a vehicle to pass through a pothole area along the shortest path, including: controller 420 establishing a kinematic model of the vehicle; and controller 420 controlling the vehicle to pass through the pothole area along the shortest path based on the kinematic model. For example, after establishing the kinematic model of the vehicle, to enable subsequent control using the kinematic model, the kinematic model must first be linearized and then discretized.

[0127] Specifically, the controller 420 establishes a kinematic model of the vehicle, including: the controller 420 establishes the kinematic model of the vehicle based on the Ackermann steering geometry theory. As shown in the following formula, the linear discrete model obtained by linearizing and discretizing the kinematic model of the vehicle established based on the Ackermann steering geometry theory is:

[0128] ΔX(k+1)=A*ΔX(k)+B*ΔU(k)

[0129] Among them, X is the state vector, U is the input control vector, A is the state matrix, and B is the control matrix. Specifically:

[0130] As shown in Figure 3, v represents vehicle speed (rear axle), L represents wheelbase, represents the vehicle heading angle, δ represents the front wheel turning angle, and (x, y) represents the coordinates of the rear axle center.

[0131] For example, the above is a linear discrete model obtained by linearizing and discretizing the kinematic model of the vehicle established based on the Ackerman steering geometry theory under ideal conditions. In actual situations, due to the existence of tire slip angle and tire wear rate, it is necessary to introduce an Ackerman correction rate, that is, the controller 420 is also used to use the Ackerman correction rate to correct the kinematic model of the vehicle established based on the Ackerman steering geometry theory to obtain a corrected kinematic model; wherein the corrected kinematic model is used to control the vehicle to pass through the pothole area along the shortest path. For example, the Ackerman correction rate R A As shown in the following formula:

[0132] Among them, θ o is the outer front wheel angle, θ i According to θ o The theoretical inner front wheel turning angle is calculated using Ackerman steering geometry theory, and θ ia The outer front wheel turning angle is θ o The actual inner front wheel angle of the car.

[0133] The linear discrete model obtained by linearizing and discretizing the corrected motion model is shown as follows:

[0134] ΔX(k+1)=A*R A *ΔX(k)+B*R A *ΔU(k)

[0135] In an embodiment of the present application, the controller 420 controls the vehicle to pass through the pothole area along the shortest path based on the kinematic model, including: the controller 420 uses a model predictive control (MPC) algorithm to control the vehicle to pass through the pothole area along the shortest path based on the kinematic model. The MPC algorithm is shown in the following formula:

[0136] min

[0137] stu min ≤u k ≤u max ,y min ≤y k ≤y max

[0138] Among them, J is the cost function, P is the final state weight matrix, Q is the process state weight matrix, R is the input weight matrix, x(k) is the process state vector, u(k) is the control input vector, x N is the final state vector; the inequality is the input u k With the output y k The equality and inequality constraints that should be satisfied.

[0139] In the embodiments of the present application, although the model predictive control algorithm is independent of the specific model, the actual implementation requires the use of a vehicle model. The aforementioned A-Star algorithm does not consider the dynamic model of the vehicle when obtaining the shortest path. Therefore, the model predictive control algorithm can consider the dynamic model of the vehicle based on the shortest path obtained by the aforementioned A-Star algorithm. At the same time, the model prediction algorithm will also consider the control within the step length in the future, so that the actual driving trajectory planning of the vehicle can be continuously optimized based on the shortest path.

[0140] The above exemplary description of a vehicle path planning system according to a specific embodiment of the present application is provided. For example, the vehicle path planning system may also include other components, which are not limited in the present embodiment.

[0141] Based on the above description, a vehicle path planning system according to a specific embodiment of the present application can obtain a region division map of the pothole area based on an image of the pothole area in front of the vehicle. The region division map is divided into a drivable area, which is an area where the vehicle can safely drive in the pothole area. The system can then obtain the shortest path through the pothole area based on the drivable area in the region division map for the driver's reference, thereby ensuring that the vehicle can safely and quickly pass through the pothole area on the road. For example, after obtaining the shortest path, the controller in the vehicle path planning system can take over to control the vehicle to pass through the pothole area along the shortest path. Compared to the driver manually controlling the vehicle to pass through the pothole area with reference to the shortest path, the controller controlling the vehicle can ensure that the vehicle passes through the pothole area more safely and efficiently.

[0142] Below, an electronic device according to a specific embodiment of the present application is described with reference to FIG5 . FIG5 shows a schematic structural block diagram of an electronic device according to a specific embodiment of the present application. As shown in FIG5 , electronic device 500 includes a processor 510 and a memory 520 . Memory 520 stores computer instructions. When the computer instructions are executed by processor 510 , processor 510 executes the vehicle path planning method described above.

[0143] The present application also provides a vehicle, which includes the vehicle path planning system described above, or the vehicle includes the electronic device described above. For example, the vehicle may also include other components, which are not limited by the present application.

[0144] An embodiment of the present application further provides a computer-readable storage medium having computer instructions stored thereon. When the computer instructions are executed by a processor, the processor is enabled to execute the aforementioned vehicle path planning method.

[0145] An embodiment of the present application also provides a computer program product, including computer instructions, which implement the aforementioned vehicle path planning method when executed by a processor.

[0146] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely illustrative and are not intended to limit the scope of the present application. Various changes and modifications may be made therein by those skilled in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0147] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0148] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, other division methods may be used. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not performed.

[0149] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0150] Similarly, it should be understood that in order to streamline the present application and aid in understanding one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present application should not be interpreted as reflecting the following intention: that the application claimed for protection requires more features than the features explicitly recited in each claim. More precisely, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with features that are less than all the features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present application.

[0151] It will be understood by those skilled in the art that, except where mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus disclosed herein may be combined in any combination. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature providing the same, equivalent, or similar purpose.

[0152] Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of this application and to form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

[0153] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules in the article analysis device according to the embodiment of the present application. The application can also be implemented as a device program (e.g., computer instructions and computer program product) for executing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0154] It should be noted that the above embodiments illustrate rather than limit the present application, and that a person skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbols placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0155] The above is merely a description of specific embodiments of the present application, and the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. The scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A vehicle path planning method, wherein: The method comprises: acquiring an image of a pothole area in front of the vehicle; Obtaining a region division map of the pothole region based on the image of the pothole region, wherein the region division map is divided into drivable regions; and A shortest path through the pothole area is obtained based on the drivable area in the area division map.

2. The vehicle path planning method according to claim 1, wherein: Also includes: The vehicle is controlled to pass through the pothole area along the shortest path.

3. The vehicle path planning method according to any one of claims 1 to 2, wherein: After obtaining the area division map of the pothole area and before obtaining the shortest path through the pothole area based on the drivable area in the area division map, the method further includes: Preprocessing the region division map to obtain a preprocessed region division map; The shortest path through the pothole area is obtained based on the drivable area in the pre-processed area division map.

4. The vehicle path planning method according to claim 3, wherein: The area in the area division map except the drivable area is divided into a non-drivable area, and the preprocessing of the area division map to obtain a preprocessed area division map includes: An image opening operation is performed on the drivable area in the area division map to re-divide part of the drivable area into the non-drivable area, thereby obtaining an area division map after image opening operation, and the area division map after image opening operation is the preprocessed area division map.

5. The vehicle path planning method according to claim 4, wherein: The preprocessing of the region division map to obtain a preprocessed region division map further includes: comparing the lateral width of the drivable area in the region division map subjected to the image opening operation with the width of the vehicle, and reclassifying the drivable area whose lateral width is smaller than a preset multiple of the width of the vehicle as the non-drivable area, to obtain the preprocessed region division map; The lateral width is the width in a direction perpendicular to the traveling direction of the vehicle.

6. The vehicle path planning method according to claim 5, wherein: The preset multiple is 1.

2.

7. The vehicle path planning method according to any one of claims 1 to 6, wherein: The obtaining of the shortest path through the pothole area based on the drivable area in the area division map includes: An A-Star algorithm is used to obtain the shortest path through the pothole area based on the drivable area in the area division map.

8. The vehicle path planning method according to any one of claims 2 to 7, wherein: The controlling the vehicle to pass through the pothole area along the shortest path includes: establishing a kinematic model of the vehicle; and, The vehicle is controlled to pass through the pothole area along the shortest path based on the kinematic model.

9. The vehicle path planning method according to claim 8, wherein: The establishing of the kinematic model of the vehicle comprises: A kinematic model of the vehicle is established based on Ackermann steering geometry theory.

10. The vehicle path planning method according to claim 9, wherein: Also includes: Using an Ackerman correction rate to correct the kinematic model established based on the Ackerman steering geometry theory to obtain a corrected kinematic model; The corrected kinematic model is used to control the vehicle to pass through the pothole area along the shortest path.

11. The vehicle path planning method according to any one of claims 8 to 10, wherein: The controlling the vehicle to pass through the pothole area along the shortest path based on the kinematic model includes: A model predictive control algorithm is used to control the vehicle to pass through the pothole area along the shortest path based on the kinematic model.

12. A vehicle path planning system, wherein: include: a sensor (410) for acquiring an image of a pothole area in front of the vehicle; A controller (420) is configured to obtain a region division map of the pothole region based on an image of the pothole region, wherein the region division map is divided into drivable regions, and to obtain a shortest path through the pothole region based on the drivable regions in the region division map.

13. The vehicle path planning system according to claim 12, wherein: The controller is also used to: The vehicle is controlled to pass through the pothole area along the shortest path.

14. The vehicle path planning system according to any one of claims 12 to 13, wherein: After obtaining the area division map of the pothole area and before obtaining the shortest path through the pothole area based on the drivable area in the area division map, the controller is further configured to: Preprocessing the region division map to obtain a preprocessed region division map; The shortest path through the pothole area is obtained based on the drivable area in the pre-processed area division map.

15. The vehicle path planning system according to claim 14, wherein: The area except the drivable area in the area division map is divided into a non-drivable area, and the controller preprocesses the area division map to obtain a preprocessed area division map, including: The controller performs an image opening operation on the drivable area in the area division map to re-divide part of the drivable area into the non-drivable area, and obtains an area division map after the image opening operation. The area division map after the image opening operation is the preprocessed area division map.

16. The vehicle path planning system according to claim 15, wherein: The controller preprocesses the region division map to obtain a preprocessed region division map, further comprising: The controller compares the lateral width of the drivable area in the area division map subjected to the image opening operation with the width of the vehicle, and reclassifies the drivable area whose lateral width is smaller than a preset multiple of the width of the vehicle as the non-drivable area, thereby obtaining the pre-processed area division map; The lateral width is the width in a direction perpendicular to the traveling direction of the vehicle.

17. The vehicle path planning system according to claim 16, wherein: The preset multiple is 1.

2.

18. The vehicle path planning system according to any one of claims 12 to 17, wherein: The controller obtains the shortest path through the pothole area based on the drivable area in the area division map, including: The controller uses an A-Star algorithm to obtain the shortest path through the pothole area based on the drivable area in the area division map.

19. The vehicle path planning system according to any one of claims 13 to 18, wherein: The controller controls the vehicle to pass through the pothole area along the shortest path, including: The controller establishes a kinematic model of the vehicle; and, The controller controls the vehicle to pass through the pothole area along the shortest path based on the kinematic model.

20. The vehicle path planning system according to claim 19, wherein: The controller establishes a kinematic model of the vehicle, including: The controller establishes a kinematic model of the vehicle based on Ackermann steering geometry theory.

21. The vehicle path planning system according to claim 20, wherein: The controller is also used to: Using an Ackerman correction rate to correct the kinematic model established based on the Ackerman steering geometry theory to obtain a corrected kinematic model; The corrected kinematic model is used to control the vehicle to pass through the pothole area along the shortest path.

22. The vehicle path planning system according to any one of claims 19 to 21, wherein: The controller controls the vehicle to pass through the pothole area along the shortest path based on the kinematic model, comprising: The controller uses a model predictive control algorithm to control the vehicle to pass through the pothole area along the shortest path based on the kinematic model.

23. An electronic device, wherein: The method comprises a processor and a memory, wherein computer instructions are stored in the memory. When the computer instructions are executed by the processor, the processor executes the vehicle path planning method according to any one of claims 1 to 11.

24. A vehicle, wherein The vehicle includes the vehicle path planning system according to any one of claims 12 to 22, or the electronic device according to claim 23.

25. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer instructions, which, when executed by a processor, enable the processor to execute the vehicle path planning method according to any one of claims 1 to 11.

26. A computer program product comprising computer instructions, wherein: When the computer instructions are executed by a processor, the vehicle path planning method according to any one of claims 1 to 11 is implemented.

Images