Parking path planning method and device, vehicle and storage medium

Abstract

The embodiment of the invention provides a parking path planning method and device, a vehicle and a storage medium, and the method comprises the steps: determining an initial position and a target parking position under the condition that a target vehicle is located in a parking region; determining a current node in the open list and a subsequent node set corresponding to the current node based on the initial position; calculating a comprehensive anthropomorphic penalty function value of each subsequent node in the subsequent node set, and determining a first target evaluation function value of each subsequent node; continuously updating the open list based on the first target evaluation function value, and determining a final open list; and when the target parking position is in the final open list, performing backtracking based on the target node and the starting node, and determining a parking path of the target vehicle. According to the scheme, the vehicle is far away from the parking safety boundary by integrating the personified penalty function value, the collision risk is reduced, and the safety of the vehicle and garage facilities is guaranteed, so that the safety of parking path planning is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving of vehicles, and particularly to a parking path planning method, device, vehicle, and storage medium. Background Art

[0002] With the development of the economy, automobiles have become the basic means of transportation for social travel. With the development of intelligent connected vehicles, a new generation of intelligent vehicles are basically equipped with chips with medium and high computing power, which promotes the application of path planning algorithms. Currently, most mid - to - high - end models in the industry use path planning algorithms for parking. However, traditional algorithms have many problems when dealing with the boundaries of the parking environment, and the generated paths may not conform to the parking habits of human drivers; for example, it is easy to make the parking path close to a square column, increasing the collision risk; or the parking path crosses a solid line, increasing potential safety hazards, resulting in poor safety of the planned parking path. Summary of the Invention

[0003] Embodiments of the present application provide a parking path planning method, device, vehicle, and storage medium, which can effectively improve the safety of parking path planning.

[0004] The technical solution of the present application is realized as follows:

[0005] Embodiments of the present application provide a parking path planning method, and the parking path planning method includes:

[0006] When the target vehicle is in a parking area, determining the starting position and the target parking position of the target vehicle;

[0007] Based on the starting node corresponding to the starting position, determining the current node in the open list and the set of successor nodes corresponding to the current node;

[0008] For the successor nodes in the set of successor nodes corresponding to the current node, by calculating the comprehensive anthropomorphic penalty function values of each successor node, determining the first target evaluation function values of each successor node; wherein, the comprehensive anthropomorphic penalty function value includes a boundary distance penalty value and a boundary crossing penalty value; the boundary distance penalty value is determined based on the shortest distance between the node and the boundary, and the boundary crossing penalty value is determined based on the node sequence that crosses the boundary and the distance between the node and the boundary when crossing the boundary;

[0009] Based on the first target evaluation function values of each successor node, continuously updating the open list to determine the final open list;

[0010] When the target node corresponding to the target parking position is in the final open list, performing backtracking based on the target node and the starting node to determine the parking path of the target vehicle.

[0011] It can be understood that, on the one hand, since the comprehensive anthropomorphic penalty function value includes the boundary distance penalty value and the boundary crossing penalty value, the boundary distance penalty value can keep the vehicle away from the parking safety boundary, reduce the collision risk, and ensure the safety of the vehicle and garage facilities; the boundary crossing penalty value can prevent the vehicle from crossing the safety boundary, reduce the collision risk, and ensure the safety of the host vehicle and other vehicles. On the other hand, based on the first target evaluation function values of each successor node, the open list is continuously updated to determine the final open list; when the target node corresponding to the target parking position is in the final open list, backtracking is performed based on the target node and the starting node to determine the parking path of the target vehicle. Since the boundary distance penalty and the boundary crossing penalty are added during the entire process of determining the parking path, the collision risk can be reduced, making the planned parking path safer.

[0012] In the above solution, determining the current node in the open list and the set of successor nodes corresponding to the current node based on the starting node corresponding to the starting position includes:

[0013] Based on the starting node corresponding to the starting position, determining the open list and the closed list;

[0014] Based on at least one node in the open list, calculating the second target evaluation function values of each node;

[0015] Based on the second target evaluation function values, determining the current node and the set of successor nodes corresponding to the current node.

[0016] It can be understood that by using the starting node corresponding to the starting position to determine the open list and the closed list, and then calculating the second target evaluation function values of each node through at least one node in the open list; the second target evaluation function values are used to screen the current node, and then generate the set of successor nodes corresponding to the current node, which is convenient for subsequent loop search, updating the open list and planning the parking path.

[0017] In the above solution, calculating the second target evaluation function values of each node based on at least one node in the open list includes:

[0018] Based on at least one node in the open list, calculating the motion cost function value and the heuristic cost function value of each node;

[0019] Based on the motion cost function value and the heuristic cost function value of each node, performing operations to determine the second target evaluation function values of the nodes.

[0020] It can be understood that by calculating the motion cost function value and the heuristic cost function value of each node in the open list; based on the motion cost function value and the heuristic cost function value of each node, operations are performed to determine the second target evaluation function value of each node, facilitating subsequent screening of the current node based on the nodes in the open list.

[0021] In the above solution, for the successor nodes in the successor node set corresponding to the current node, by calculating the comprehensive anthropomorphic penalty function value of each successor node, determining the first target evaluation function value of each successor node includes:

[0022] Based on the successor nodes in the successor node set and the obtained parking environment boundary, calculate the comprehensive anthropomorphic penalty function value of each successor node;

[0023] Based on the comprehensive anthropomorphic penalty function value of each successor node, determine the first target evaluation function value of each successor node.

[0024] It can be understood that based on the successor nodes in the successor node set and the obtained parking environment boundary, calculate the comprehensive anthropomorphic penalty function value of each successor node; since the comprehensive anthropomorphic penalty function value can reduce the collision risk, the first target evaluation function value of each successor node determined based on the comprehensive anthropomorphic penalty function value of each successor node can also reduce the collision risk.

[0025] In the above solution, the calculating the comprehensive anthropomorphic penalty function value of each successor node based on the successor nodes in the successor node set and the obtained parking environment boundary includes:

[0026] Based on the successor nodes in the successor node set, the obtained parking environment boundary, and the environmental information, call the penalty coefficient corresponding to the environmental information to calculate the boundary distance penalty value of each successor node;

[0027] Based on the successor nodes in the successor node set and the obtained parking environment boundary, calculate the boundary crossing penalty value of each successor node;

[0028] Based on the boundary distance penalty value and the boundary crossing penalty value, determine the comprehensive anthropomorphic penalty function value of each successor node.

[0029] It can be understood that, based on the successor nodes in the successor node set, the obtained parking environment boundary, and the environmental information, the penalty coefficient corresponding to the environmental information is called to calculate the boundary distance penalty value of each successor node. Since the boundary distance penalty value can keep the vehicle away from the parking safety boundary, the collision risk is reduced, and the safety of the vehicle and garage facilities is ensured. Based on the successor nodes in the successor node set and the obtained parking environment boundary, the boundary crossing penalty value of each successor node is calculated. Since the boundary crossing penalty value can prevent the vehicle from crossing the safety boundary, the collision risk is reduced, and the safety of the ego vehicle and other vehicles is ensured. Based on the boundary distance penalty value and the boundary crossing penalty value, the comprehensive anthropomorphic penalty function value of each successor node is determined. Since the boundary distance penalty value and the boundary crossing penalty value can reduce the collision risk, the comprehensive anthropomorphic penalty function value of each successor node determined based on the boundary distance penalty value and the boundary crossing penalty value can also reduce the collision risk, thereby further improving the safety of the planned parking path.

[0030] In the above solution, determining the first target evaluation function value of each successor node based on the comprehensive anthropomorphic penalty function value of each successor node includes:

[0031] Calculating the motion cost function value of each successor node and the heuristic cost function value of each successor node;

[0032] Based on the comprehensive anthropomorphic penalty function value of each successor node, the motion cost function value of each successor node, and the heuristic cost function value of each successor node, determining the first target evaluation function value of each successor node.

[0033] It can be understood that the target vehicle calculates the motion cost function value of each successor node and the heuristic cost function value of each successor node; based on the comprehensive anthropomorphic penalty function value of each successor node, the motion cost function value of each successor node, and the heuristic cost function value of each successor node, the first target evaluation function value of each successor node is determined. Since the comprehensive anthropomorphic penalty function value can reduce the collision risk, the first target evaluation function value of each successor node determined based on the comprehensive anthropomorphic penalty function value of each successor node can also reduce the collision risk.

[0034] In the above solution, continuously updating the open list based on the first target evaluation function value of each successor node to determine the final open list includes:

[0035] For each successor node, if the successor node does not belong to the open list and does not belong to the closed list, then update the open list based on the successor node;

[0036] If the successor node belongs to the open list or the closed list, and the first target evaluation function value is less than the second target evaluation value, then update the open list;

[0037] Continue to determine a new current node and the set of successor nodes corresponding to the new current node, and continue to update the open list until the open list meets the preset conditions, stop updating the open list, and determine the final open list.

[0038] It can be understood that by using the first target evaluation function values of the successor nodes to update the open list, for the updated open list, continue to determine a new current node and the set of successor nodes corresponding to the new current node, and continue to update the open list until the open list meets the preset conditions, stop updating the open list, and determine the final open list, which can quickly complete the node search and facilitate subsequent parking path planning.

[0039] In the above solution, the preset condition is that the open list includes the target node corresponding to the target parking position or the open list is empty.

[0040] It can be understood that the setting of the preset condition can help to quickly search and determine the parking path.

[0041] An embodiment of the present application provides a parking path planning device, including a determination unit, a calculation unit, and an update unit; wherein,

[0042] The determination unit is configured to, when the target vehicle is in the parking area, determine the starting position and the target parking position of the target vehicle; based on the starting node corresponding to the starting position, determine the current node in the open list and the set of successor nodes corresponding to the current node;

[0043] The calculation unit is configured to, for the successor nodes in the set of successor nodes corresponding to the current node, determine the first target evaluation function values of the successor nodes by calculating the comprehensive anthropomorphic penalty function values of the successor nodes; wherein, the comprehensive anthropomorphic penalty function value includes a boundary distance penalty value and a boundary crossing penalty value; the boundary distance penalty value is determined based on the shortest distance between the node and the boundary, and the boundary crossing penalty value is determined based on the node sequence crossing the boundary and the distance between the node and the boundary when crossing the boundary;

[0044] The update unit is configured to continuously update the open list based on the first target evaluation function values of the successor nodes to determine the final open list;

[0045] The determining unit is further configured to, when the target node corresponding to the target parking position is in the open list, perform backtracking based on the target node and the starting node to determine the parking path of the target vehicle.

[0046] An embodiment of the present application provides a vehicle, including:

[0047] A memory for storing executable data instructions;

[0048] A processor for implementing the parking path planning method when executing the executable instructions stored in the memory.

[0049] An embodiment of the present application provides a computer-readable storage medium storing executable instructions for causing a processor to implement the parking path planning method when executed.

[0050] An embodiment of the present application provides a parking path planning method, apparatus, vehicle, and computer-readable storage medium. The parking path planning method includes: when a target vehicle is in a parking area, determining a starting position and a target parking position of the target vehicle; based on a starting node corresponding to the starting position, determining a current node in an open list and a set of successor nodes corresponding to the current node; for a successor node in the set of successor nodes corresponding to the current node, determining a first target evaluation function value of each successor node by calculating a comprehensive anthropomorphic penalty function value of each successor node; where the comprehensive anthropomorphic penalty function value includes a boundary distance penalty value and a boundary crossing penalty value; the boundary distance penalty value is determined based on the shortest distance between a node and a boundary, and the boundary crossing penalty value is determined based on a sequence of nodes crossing the boundary and the distance between a node and the boundary when crossing the boundary; continuously updating the open list based on the first target evaluation function values of the successor nodes to determine a final open list; when a target node corresponding to the target parking position is in the final open list, performing backtracking based on the target node and the starting node to determine a parking path of the target vehicle. By adopting the above solution, on the one hand, since the comprehensive anthropomorphic penalty function value includes a boundary distance penalty value and a boundary crossing penalty value, the boundary distance penalty value can keep the vehicle away from the parking safety boundary, reduce the collision risk, and ensure the safety of the vehicle and garage facilities; the boundary crossing penalty value can prevent the vehicle from crossing the safety boundary, reduce the collision risk, and ensure the safety of the vehicle itself and other vehicles. On the other hand, continuously updating the open list based on the first target evaluation function values of the successor nodes to determine a final open list; when a target node corresponding to the target parking position is in the final open list, performing backtracking based on the target node and the starting node to determine a parking path of the target vehicle. Since boundary distance penalty and boundary crossing penalty are added during the whole process of determining the parking path, the collision risk can be reduced, and the safety of the planned parking path is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is an alternative flowchart of a parking path planning method provided by an embodiment of the present application Figure 1 ;

[0052] Figure 2 is an alternative flowchart of a parking path planning method provided by an embodiment of the present application Figure 2 ;

[0053] Figure 3 is an alternative flowchart of a parking path planning method provided by an embodiment of the present application Figure 3 ;

[0054] Figure 4Schematic diagram of an optional boundary distance penalty term function curve for a parking path planning method provided by an embodiment of the present application;

[0055] Figure 5 Optional process schematic of a parking path planning method provided by an embodiment of the present application Figure 4 ;

[0056] Figure 6 Schematic diagram of an optional typical boundary distance control parking scenario for a parking path planning method provided by an embodiment of the present application;

[0057] Figure 7 Schematic diagram of an optional typical boundary crossing control parking scenario for a parking path planning method provided by an embodiment of the present application;

[0058] Figure 8 Schematic diagram of the structure of a parking path planning device provided by an embodiment of the present application;

[0059] Figure 9 Schematic diagram of the structure of a vehicle provided by an embodiment of the present application. Detailed implementation manners

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will further describe the specific technical solutions of the present application in detail with reference to the accompanying drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application but are not intended to limit the scope of the present application.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0062] In the following descriptions, references to "some embodiments", "this embodiment", "embodiments of the present application", and examples, etc., describe subsets of all possible embodiments. However, it can be understood that "some embodiments" can be the same subsets or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0063] If similar descriptions such as "first / second" appear in the application documents, the following explanation is added. In the following descriptions, the terms "first\second\third" only distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence when permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0064] Based on the analysis of human driver parking behavior, when a human driver parks a vehicle, they are highly vigilant about the boundaries of the parking space and the surrounding environment. They will estimate the parking space and angle based on the conditions of the parking space, and keep the vehicle in a safe area during parking to avoid collisions and unnecessary crossings. A typical example is to increase the safety distance for obstacles such as narrow doors and square columns that are difficult to judge accurately. When parking by the roadside, the vehicle will not cross the lane solid line demarcation line to avoid high risks. The actual situation is that current intelligent driving sensors also have limitations in such scenarios. Therefore, it is necessary to optimize the strategy in the backend path planning. Based on this, the present application provides a parking path planning method.

[0065] An embodiment of the present application provides a parking path planning method. Figure 1 It is an optional process schematic diagram of a parking path planning method provided by an embodiment of the present application. Figure 1 It will be described in conjunction with Figure 1 the steps shown.

[0066] S101. When the target vehicle is in the parking area, determine the starting position and the target parking position of the target vehicle.

[0067] In an embodiment of the present application, the target vehicle refers to a vehicle that currently needs to park in the parking area, and the parking area refers to an area where vehicles can park continuously or temporarily.

[0068] Exemplarily, the parking area can be a parking lot or an area where parking spaces can be parked by the roadside. The present application does not make specific limitations on the parking area.

[0069] In some embodiments of the present application, the starting position of the target vehicle refers to the position where the target vehicle is currently located in the parking area; the target parking position is the position where the target vehicle is to be parked.

[0070] In some embodiments of the present application, the execution subject of the parking path planning method is the vehicle, that is, the target vehicle.

[0071] In some embodiments of the present application, the parking path planning method is applicable to the parking path planning scenario of an intelligent vehicle cockpit.

[0072] In some embodiments of the present application, when the target vehicle is in the parking area, determine the starting position and the target parking position of the target vehicle.

[0073] S102. Based on the starting node corresponding to the starting position, determine the current node in the open list and the set of successor nodes corresponding to the current node.

[0074] In some embodiments of the present application, the Open List is the core data structure used to manage the node states during the path search process of the hybrid A* algorithm. The parking path planning of the present application mainly improves the hybrid A* algorithm and uses the improved hybrid A* algorithm for path planning.

[0075] In some embodiments of the present application, the hybrid A* algorithm is a path planning method designed for robots or vehicles with kinematic constraints, which combines the heuristic search of the traditional A* algorithm and the continuous motion model, taking into account both path optimality and geometric feasibility.

[0076] In some embodiments of the present application, the target vehicle can determine the Open List and the Closed List based on the starting node corresponding to the starting position; and determine the current node and the set of successor nodes corresponding to the current node based on at least one node in the Open List.

[0077] It should be noted that the Open List stores candidate nodes to be evaluated. Each node contains state information such as position (x, y), heading angle θ, speed, etc., as well as the total cost and the parent node pointer. In the hybrid A* algorithm, the expansion of nodes needs to combine the vehicle kinematic model to generate continuous path segments that meet the steering constraints. For example, the actual trajectory is simulated by discretizing the front wheel steering angle. The Closed List stores the evaluated nodes to avoid repeated calculation of the same state and improve the search efficiency. After a node is removed from the Open List, it is added to the Closed List and marked as "processed", and will not be actively expanded in subsequent searches.

[0078] In some embodiments of the present application, the target vehicle can calculate the second target evaluation function values of each node based on at least one node in the Open List; and determine the current node and the set of successor nodes corresponding to the current node based on the second target evaluation function values.

[0079] In some embodiments of the present application, the target vehicle can add the starting node to the Open List based on the starting node corresponding to the starting position, calculate the second target evaluation function values of each node in the Open List; and screen the nodes in the Open List through the second target evaluation function values to determine the current node and the set of successor nodes corresponding to the current node.

[0080] S103. For the successor nodes in the set of successor nodes corresponding to the current node, determine the first target evaluation function values of each successor node by calculating the comprehensive anthropomorphic penalty function values of each successor node; wherein, the comprehensive anthropomorphic penalty function values include the boundary distance penalty value and the boundary crossing penalty value; the boundary distance penalty value is determined based on the shortest distance between the node and the boundary, and the boundary crossing penalty value is determined based on the node sequence that crosses the boundary and the distance between the node and the boundary when crossing the boundary.

[0081] In some embodiments of the present application, the comprehensive anthropomorphic penalty function value includes a boundary distance penalty value and a boundary crossing penalty value. The boundary distance penalty value is mainly used to keep the path away from the boundary; the boundary crossing penalty value is mainly used to check the path node sequence to determine whether there is a node crossing the key boundary of the parking environment.

[0082] In some embodiments of the present application, the first target evaluation function value is mainly used to update the open list. For each node, the first target evaluation function value includes a comprehensive anthropomorphic penalty function value, a motion cost function value, and a heuristic cost function value.

[0083] In some embodiments of the present application, the target vehicle can calculate the comprehensive anthropomorphic penalty function value of each successor node based on the successor nodes in the successor node set and the obtained parking environment boundary; based on the comprehensive anthropomorphic penalty function value of each successor node, determine the first target evaluation function value of each successor node.

[0084] S104. Continuously update the open list based on the first target evaluation function value of each successor node to determine the final open list.

[0085] In some embodiments of the present application, the final open list is divided into two cases. One is that the final open list includes the target node corresponding to the target parking position, and the other is that the final open list does not contain nodes, that is, the final open list is empty.

[0086] In some embodiments of the present application, the target vehicle can update the open list based on the first target evaluation function value of each successor node corresponding to the current node to obtain the updated open list; determine a new current node from the updated open list. According to the new current node, determine the successor node set corresponding to the new current node. Based on the successor nodes in the successor node set corresponding to the new current node, continue to update the open list until the final open list is determined.

[0087] In some embodiments of the present application, for each successor node, if the successor node does not belong to the open list and does not belong to the closed list, the open list is updated based on the successor node; if the successor node belongs to the open list or belongs to the closed list, and the first target evaluation function value is less than the second target evaluation value, the open list is updated; continue to determine the new current node and the successor node set corresponding to the new current node, and continue to update the open list until the open list reaches the preset condition, stop updating the open list, and determine the final open list.

[0088] In some embodiments of the present application, the preset condition is that the open list includes the target node corresponding to the target parking position or the open list is empty.

[0089] It should be noted that when the open list is empty, it means that the open list does not contain any nodes.

[0090] S105. When the target node corresponding to the target parking position is in the final open list, backtrack based on the target node and the starting node to determine the parking path of the target vehicle.

[0091] In some embodiments of the present application, after the target vehicle determines the final open list, when the target node corresponding to the target parking position appears in the final open list, the target vehicle can backtrack the path from the target node to the starting node to determine the finally planned parking path of the target vehicle.

[0092] It should be noted that the finally planned parking path is a path that the target vehicle can drive safely.

[0093] It can be understood that, on the one hand, since the comprehensive anthropomorphic penalty function value includes a boundary distance penalty value and a boundary crossing penalty value. The boundary distance penalty value can keep the vehicle away from the parking safety boundary, reduce the collision risk, and ensure the safety of the vehicle and garage facilities; the boundary crossing penalty value can prevent the vehicle from crossing the safety boundary, reduce the collision risk, and ensure the safety of the vehicle itself and other vehicles. On the other hand, based on the first target evaluation function values of each successor node, the open list is continuously updated to determine the final open list; when the target node corresponding to the target parking position is in the final open list, backtrack based on the target node and the starting node to determine the parking path of the target vehicle. Since boundary distance penalty and boundary crossing penalty are added during the whole process of determining the parking path, the collision risk can be reduced, making the planned parking path safer.

[0094] In some embodiments of the present application, as Figure 2 shown, S102 can be implemented through S201, S202, and S203 as follows:

[0095] S201. Based on the starting node corresponding to the starting position, determine the open list and the closed list.

[0096] In some embodiments of the present application, the open list and the closed list in the hybrid A* algorithm are core data structures for managing node states during the path search process, and their design takes into account both the search efficiency and the adaptability of kinematic constraints.

[0097] In some embodiments of the present application, the target vehicle can add the starting node corresponding to the starting position to the initialized open list to determine the open list and the closed list.

[0098] S202. Based on at least one node in the open list, calculate the second target evaluation function values of each node.

[0099] In some embodiments of the present application, the second target evaluation function value includes a motion cost function value and a heuristic cost function value.

[0100] In some embodiments of the present application, the target vehicle may calculate the second target evaluation function value of each node for each node in the open list.

[0101] In some embodiments of the present application, the target vehicle may calculate the motion cost function value and the heuristic cost function value of each node based on at least one node in the open list; perform operations based on the motion cost function value and the heuristic cost function value of each node to determine the second target evaluation function value of each node.

[0102] Exemplarily, determine the starting position and the target parking position of the target vehicle, and initialize the open list and the closed list. Add the starting node (i.e., the starting position of the target vehicle) to the open list. Taking the calculation of the second target evaluation function value of the starting node as an example, the calculation of the second target evaluation function value of each node will be described. The calculation of the second target evaluation function value of the starting node can be achieved through formula (1) as follows:

[0103] f(n s )=g(n s )+h(n s ) (1)

[0104] Where f(n s ) is the second target evaluation function value of the starting node; g(n s ) is the motion cost function value of the starting node corresponding to the starting position, and g(n s ) = 0; h(n s ) is the heuristic cost function value (such as the straight-line distance between the target point and the starting point).

[0105] It should be noted that the motion cost function value is the actual path cost from the starting point to the current node (such as the driving distance or time); the heuristic cost function value is the estimated remaining cost from the current node to the end point (such as the shortest distance of the Reeds-Shepp curve).

[0106] It can be understood that by calculating the motion cost function value and the heuristic cost function value of each node in the open list; performing operations based on the motion cost function value and the heuristic cost function value of each node to determine the second target evaluation function value of each node, it is convenient to screen the current node based on the nodes in the open list later.

[0107] S203. Determine the current node and the set of successor nodes corresponding to the current node based on the second target evaluation function value.

[0108] In some embodiments of the present application, the target vehicle can select a node with the smallest second target evaluation function value from each node as the current node according to the second target evaluation function value of each node. According to the current node, a set of successor nodes of the current node is generated through the vehicle kinematic model.

[0109] In some embodiments of the present application, the vehicle kinematic model is a mathematical expression that describes the law of vehicle motion, and describes the vehicle's motion characteristics in a plane through the mapping relationship between input (such as steering angle, speed) and output (position, heading angle, etc.). The vehicle kinematic model focuses on the geometric motion relationship, ignores dynamic factors such as tire slip and mass distribution, and focuses on solving the following problems:

[0110] State update: Infer the change of vehicle posture (x, y, θ) over time based on control input (speed, steering angle).

[0111] Path feasibility: constrains the vehicle's trajectory to ensure that physical constraints such as minimum turning radius are met.

[0112] It can be understood that the open list and the closed list are determined through the starting node corresponding to the starting position, and then the second target evaluation function value of each node is calculated through at least one node in the open list; the second target evaluation function value is used to filter the current node, and then generate a successor node set corresponding to the current node, which is convenient for subsequent cyclic search, updating the open list and planning the parking path.

[0113] In some embodiments of the present application, Figure 3 As shown, S103 can be implemented through S301 and S302 as follows:

[0114] S301 . Calculate a comprehensive anthropomorphic penalty function value of each successor node based on the successor nodes in the successor node set and the acquired parking environment boundary.

[0115] In some embodiments of the present application, based on the successor nodes in the successor node set and the acquired parking environment boundary, the boundary distance penalty value of each successor node and the boundary crossing penalty value of each successor node are calculated; based on the boundary distance penalty value and the boundary crossing penalty value, the comprehensive anthropomorphic penalty function value of each successor node is determined.

[0116] In some embodiments of the present application, based on the successor nodes in the successor node set, the obtained parking environment boundary and the environmental information, the penalty coefficient corresponding to the environmental information is called to calculate the boundary distance penalty value of each successor node; based on the successor nodes in the successor node set and the obtained parking environment boundary, the boundary crossing penalty value of each successor node is calculated; based on the boundary distance penalty value and the boundary crossing penalty value, the comprehensive anthropomorphic penalty function value of each successor node is determined.

[0117] Exemplarily, the boundary distance penalty value can be implemented by formula (2) as follows:

[0118]

[0119] where n is the current node of the target vehicle, the coordinates of the current node are (x n , y n ), B is the boundary of the parking environment, and d(n, B) is the shortest distance from the node to the boundary; P d (n) is the boundary distance penalty value. When d(n, B) > d min , where k d1 , k d2 are distance penalty coefficients, ε is a minimum value to prevent the denominator from being zero, and d min is the minimum safety distance threshold. When the vehicle approaches the boundary, d(n, B) becomes smaller, P d (n) increases, and the quadratic reciprocal form enhances the penalty strength when approaching the boundary, prompting the algorithm to select a path far from the boundary. The distance between the vehicle and specific obstacles (such as square columns, narrow doors, etc.) is sensed by on-vehicle sensors (such as ultrasonic sensors, cameras, etc.).

[0120] The boundary crossing penalty value can be implemented by formula (3) as follows:

[0121]

[0122] where n1, n2, …, n m is the node sequence, k c is the crossing penalty coefficient, m is the length of the node sequence crossing the boundary, is the weight coefficient. P c (n1, n2, …, n m ) is the boundary crossing penalty value. The boundary crossing penalty value not only penalizes the number of nodes crossing the boundary but also considers the distance from the boundary when crossing the boundary. The closer to the boundary the crossing is, the heavier the penalty is, so as to strictly restrict the vehicle from crossing unnecessary boundaries and improve the safety and standardization of the parking process.

[0123] The comprehensive anthropomorphic penalty function value can be implemented by formula (4) as follows:

[0124] P n = P d (n) + P c (n 1, n 2, …, n m )

[0125] where P nIt is the comprehensive anthropomorphic penalty function value of the current node. This function comprehensively considers the distance between the vehicle and the boundary and the crossing situation, simulates the way of human drivers dealing with the environmental boundary, and guides the hybrid A* algorithm to generate a reasonable and safe path.

[0126] The penalty coefficient corresponding to the environmental information (the function curve of the boundary distance penalty term), see Figure 4 , the horizontal axis d(n,B) is the shortest distance from the node to the boundary; the vertical axis P d (n) is the boundary distance penalty value; the specific description is as follows:

[0127] 1) Figure 4 Three curve examples are shown in , Curve 10, Curve 11 and Curve 12, corresponding to different scenarios with different penalty coefficients. The system can also set more penalty coefficient curves for refined control;

[0128] 2) The penalty coefficient of Vehicle Curve 10 is relatively large and is applied to obstacles with large perception deviations such as narrow doors. During the parking process, due to the large penalty, the system will appropriately increase the safety distance to give priority to ensuring a sense of security and comfort;

[0129] 3) The penalty coefficient of Vehicle Curve 11 is relatively small and is applied to obstacles with relatively accurate perception such as columns. During the parking process, due to the small penalty, the system will appropriately reduce the safety distance;

[0130] 4) The penalty coefficient of Vehicle Curve 12 is small and is applied to obstacles with very accurate perception such as vehicles. During the parking process, due to the small penalty, the system will further reduce the safety distance to improve space utilization.

[0131] By setting different penalty coefficients for different scenarios, the best balance of safety, comfort and adaptability can be ensured.

[0132] It can be understood that based on the successor nodes in the successor node set, the obtained parking environment boundary and the environmental information, the penalty coefficient corresponding to the environmental information is called to calculate the boundary distance penalty value of each successor node. Since the boundary distance penalty value can keep the vehicle away from the parking safety boundary, the collision risk is reduced, and the safety of the vehicle and the garage facilities is guaranteed. Based on the successor nodes in the successor node set and the obtained parking environment boundary, the boundary crossing penalty value of each successor node is calculated. Since the boundary crossing penalty value can prevent the vehicle from crossing the safety boundary, the collision risk is reduced, and the safety of the vehicle itself and other vehicles is guaranteed. Based on the boundary distance penalty value and the boundary crossing penalty value, the comprehensive anthropomorphic penalty function value of each successor node is determined. Since the boundary distance penalty value and the boundary crossing penalty value can reduce the collision risk, the comprehensive anthropomorphic penalty function value of each successor node determined based on the boundary distance penalty value and the boundary crossing penalty value can also reduce the collision risk, thereby further improving the safety of the planned parking path.

[0133] S302. Determine the first target evaluation function value of each successor node based on the comprehensive anthropomorphic penalty function value of each successor node.

[0134] In some embodiments of the present application, calculate the motion cost function value of each successor node and the heuristic cost function value of each successor node; determine the first target evaluation function value of each successor node based on the comprehensive anthropomorphic penalty function value of each successor node, the motion cost function value of each successor node, and the heuristic cost function value of each successor node.

[0135] In some embodiments of the present application, select the node n with the smallest f value (i.e., the second target evaluation function value) from the open list as the current node. Generate a set S of successor nodes of the current node according to the vehicle kinematic model (considering wheelbase, maximum steering angle, etc.). For each successor node n' ∈ S: calculate the motion cost function value (comprehensively considering the actual driving distance of the vehicle from the starting node to n', the change in steering angle, etc. for the motion cost); calculate the heuristic cost function value (using traditional heuristic estimated cost, such as the Euclidean distance to the target point).

[0136] Exemplarily, calculating the first target evaluation function value can be achieved through formula (5) as follows:

[0137] f(n') = g(n') + h(n') + P(n') (5)

[0138] Wherein, P(n') is the comprehensive anthropomorphic penalty function value of the successor node; g(n') is the motion cost function value of the successor node; h(n') is the heuristic cost function value of the successor node; f(n') is the first target evaluation function value.

[0139] It can be understood that based on the successor nodes in the successor node set and the obtained parking environment boundary, calculate the comprehensive anthropomorphic penalty function value of each successor node; since the comprehensive anthropomorphic penalty function value can reduce the collision risk, the first target evaluation function value of each successor node determined based on the comprehensive anthropomorphic penalty function value of each successor node can also reduce the collision risk.

[0140] In some embodiments of the present application, S104 can be implemented through S401, S402, and S403 as follows:

[0141] S401. For each successor node, if the successor node does not belong to the open list and does not belong to the closed list, update the open list based on the successor node.

[0142] In some embodiments of the present application, for each successor node in the set of successor nodes corresponding to the current node of the target vehicle, if the successor node does not belong to the open list and does not belong to the closed list, add this successor node to the open list.

[0143] S402. If the successor node belongs to the open list or the closed list, and the first target evaluation function value is less than the second target evaluation value, update the open list.

[0144] In some embodiments of the present application, for each successor node in the successor node set corresponding to the current node of the target vehicle, if the successor node belongs to the open list or the closed list, and the first target evaluation function value of this successor node is less than the second target evaluation value, add this successor node to the open list.

[0145] S403. Continue to determine a new current node and the successor node set corresponding to the new current node, and continue to update the open list until the open list meets the preset conditions, stop updating the open list, and determine the final open list.

[0146] In some embodiments of the present application, based on the updated open list, the target vehicle continues to determine a new current node and the successor node set corresponding to the new current node, and continues to update the open list until the open list meets the preset conditions, stop updating the open list, and determine the final open list.

[0147] Exemplarily, if n' is not in the open list and the closed list, add it to the open list; if n' is already in the open list and the newly calculated f(n') is smaller, update the values related to n' in the open list; if n' is in the closed list and the newly calculated f(n') is smaller, move it back from the closed list to the open list and update the related values.

[0148] It should be noted that the preset condition is that when the target node is added to the open list or the open list is empty, the search ends.

[0149] It can be understood that by updating the open list with the first target evaluation function values of each successor node, for the updated open list, continue to determine a new current node and the successor node set corresponding to the new current node, continue to update the open list until the open list meets the preset conditions, stop updating the open list, and determine the final open list, the node search can be completed quickly, which is convenient for subsequent parking path planning.

[0150] The embodiments of the present application provide a parking path planning method. Refer to Figure 5 , and the steps of the parking path planning method are as follows:

[0151] S1. The user drives the target vehicle to the parking area.

[0152] S2. When the system is normal, perceive and model the parking environment through on-vehicle sensors.

[0153] It should be noted that the system is the parking system of the target vehicle.

[0154] S3. Confirm the parking environment boundary B and the starting position n of the target vehicle s .

[0155] S4. Call relevant parameters and initialize the open list and the closed list.

[0156] In some embodiments of the present application, relevant preset parameters are called according to the perceived environmental conditions, and the open list and the closed list are initialized. The starting node is added to the open list and the initial g(n s ), h(n s ), and f(n s ) are calculated.

[0157] S5. Enter the search loop phase.

[0158] In some embodiments of the present application, a set S of successor nodes of the current node is generated according to the vehicle kinematic model. For each successor node n′, the distance information between the vehicle and the boundary is obtained through on-vehicle sensors, d(n′, B) is calculated, and then the boundary distance penalty value P d (nn′) of the successor node is calculated; at the same time, it is checked whether there is a boundary crossing situation. If so, the boundary crossing penalty value P c (n′) of the successor node is calculated, and then the comprehensive anthropomorphic penalty function value P(n′) and the first target evaluation function value f(n′) of the successor node are calculated. The nodes are processed according to the value of f(n′), and the open list and the closed list are updated.

[0159] In some embodiments of the present application, after S5, S6 or S7 will be executed according to specific situations.

[0160] S6. The target node is added to the open list.

[0161] In some embodiments of the present application, when the target node is added to the open list and the termination condition is met, S8-S10 are continued to be executed.

[0162] S7. The open list is empty.

[0163] In some embodiments of the present application, when the open list is empty and the termination condition is met, S8 and S11 are continued to be executed.

[0164] S8. The search stops.

[0165] S9. Backtrack to obtain the final parking path.

[0166] S10. The control system controls the vehicle to perform automatic parking according to the planned path.

[0167] S11. The path planning fails.

[0168] It should be noted that the continuous search loop continues until the termination condition is met, that is, the target node is added to the open list or the open list is empty; if the open list is empty after the search, the search terminates, indicating that the path cannot be planned and a path planning failure is prompted; if a target node is added to the open list and the search also terminates, the target parking path is obtained by backtracking; the parking system parks in the target parking space according to the target parking path obtained by backtracking.

[0169] Exemplarily, referring to Figure 6 , Figure 6 shows a typical parking scenario example in an underground parking lot. Figure 6 In it, there are the target vehicle 1, the target vertical parking space 2, the square column 3, the selected path 4 before improvement, and the selected path 5 after improvement. The specific description is as follows:

[0170] 1) The position of the target vehicle 1, as shown in Figure 6 , the system finds the target vertical parking space 2 and constructs the scenario

[0171] Map graph;

[0172] 2) Based on the scenario Map graph and the real-time Freespace, when the boundary distance penalty function (i.e., the boundary distance penalty function value) is not added, the system parks according to the selected path 4 before improvement. During the parking process of the selected path 4 before improvement, there will be a problem that the distance from the square column 3 is too close. When there is a perception error, it may cause sudden braking or even scratching during the parking process;

[0173] 3) Based on the scenario Map graph and the real-time Freespace, after adding the boundary distance penalty function, the system parks according to the selected path 5 after improvement. The selected path 5 after improvement will increase the safety distance from the square column 3 to ensure the safety and smoothness of the parking process.

[0174] Exemplarily, referring to Figure 7 , Figure 7 shows a typical parking scenario example at a roadside parking space. Figure 7 In it, there are the target vehicle 13, the target parallel parking space 6, the lane solid line boundary 7, the selected path 14 before improvement, and the selected path 15 after improvement. The specific description is as follows:

[0175] 1) The position of the target vehicle 13, as shown in Figure 7 , the system finds the target parallel parking space 6 and constructs the scenario Map graph;

[0176] 2) Based on the scenario Map and real-time Freespace, when the boundary crossing penalty function (i.e., the boundary crossing penalty function value) is not added, the system parks according to the pre-improved selected path 14. During the parking process of the pre-improved selected path 14, there will be a problem of crossing the solid lane boundary 7. When it senses that there is an oncoming vehicle in the oncoming lane, it may suddenly brake or even collide;

[0177] 3) Based on the scenario Map and real-time Freespace, after adding the boundary crossing penalty function, the system parks according to the improved selected path 15. During the parking process of the improved selected path 15, the system will ensure that it does not cross the solid lane boundary 7, ensuring the safety and smoothness of the parking process.

[0178] It can be understood that the parking path planning method of the present application has the following effects:

[0179] 1) Improve parking safety: The boundary distance penalty value makes the vehicle stay away from the parking safety boundary, reducing the collision risk and ensuring the safety of the vehicle and garage facilities; The boundary crossing penalty value makes the vehicle not cross the safety boundary, reducing the collision risk and ensuring the safety of the vehicle itself and other vehicles.

[0180] 2) Optimize parking comfort: The entire parking path is smoother, reducing inaccurate boundary perception and path adjustments and sudden brakes caused by mutations, improving the riding comfort of passengers and making the parking process stable and natural.

[0181] 3) Enhance environmental adaptability: It can adapt to different types of parking environments, such as vertical, parallel, irregular parking spaces or narrow garage spaces, and flexibly plan appropriate paths according to the environmental boundary characteristics and the initial position of the vehicle, improving the usability of the vehicle's automatic parking system in complex environments.

[0182] The embodiment of the present application also provides a parking path planning device, as Figure 8 shown, Figure 8 is a schematic structural diagram of a parking path planning device provided by an embodiment of the present application. The parking path planning device 8 includes: a determination unit 801, a calculation unit 802, and an update unit 803; wherein,

[0183] The determination unit 801 is configured to determine the starting position and the target parking position of the target vehicle when the target vehicle is in a parking area; based on the starting node corresponding to the starting position, determine the current node in the open list and the set of successor nodes corresponding to the current node;

[0184] The calculation unit 802 is configured to determine the first target evaluation function values of the successor nodes in the successor node set corresponding to the current node by calculating the comprehensive anthropomorphic penalty function values of the successor nodes; wherein, the comprehensive anthropomorphic penalty function value includes a boundary distance penalty value and a boundary crossing penalty value; the boundary distance penalty value is determined based on the shortest distance between the node and the boundary, and the boundary crossing penalty value is determined based on the node sequence crossing the boundary and the distance between the node and the boundary when crossing the boundary;

[0185] The update unit 803 is configured to continuously update the open list based on the first target evaluation function values of the successor nodes to determine the final open list;

[0186] The determination unit 801 is further configured to, when the target node corresponding to the target parking position is in the final open list, perform backtracking based on the target node and the starting node to determine the parking path of the target vehicle.

[0187] In some embodiments of the present application, the determination unit 801 is further configured to determine the open list and the closed list based on the starting node corresponding to the starting position;

[0188] The calculation unit 802 is further configured to calculate the second target evaluation function values of the nodes based on at least one node in the open list;

[0189] The determination unit 801 is further configured to determine the current node and the successor node set corresponding to the current node based on the second target evaluation function value.

[0190] In some embodiments of the present application, the calculation unit 802 is further configured to calculate the motion cost function value and the heuristic cost function value of each node based on at least one node in the open list;

[0191] The determination unit 801 is further configured to perform an operation based on the motion cost function value and the heuristic cost function value of each node to determine the second target evaluation function values of the nodes.

[0192] In some embodiments of the present application, the calculation unit 802 is further configured to calculate the comprehensive anthropomorphic penalty function values of the successor nodes based on the successor nodes in the successor node set and the obtained parking environment boundary;

[0193] The determination unit 801 is further configured to determine the first target evaluation function values of the successor nodes based on the comprehensive anthropomorphic penalty function values of the successor nodes.

[0194] In some embodiments of the present application, the computing unit 802 is further configured to calculate the boundary distance penalty value of each successor node by invoking a penalty coefficient corresponding to the environmental information based on the successor nodes in the successor node set, the obtained parking environment boundary, and the environmental information; calculate the boundary crossing penalty value of each successor node based on the successor nodes in the successor node set and the obtained parking environment boundary;

[0195] The determining unit 801 is further configured to determine the comprehensive anthropomorphic penalty function value of each successor node based on the boundary distance penalty value and the boundary crossing penalty value.

[0196] In some embodiments of the present application, the computing unit 802 is further configured to calculate the motion cost function value of each successor node and the heuristic cost function value of each successor node;

[0197] The determining unit 801 is further configured to determine the first target evaluation function value of each successor node based on the comprehensive anthropomorphic penalty function value of each successor node, the motion cost function value of each successor node, and the heuristic cost function value of each successor node.

[0198] In some embodiments of the present application, for each successor node, the updating unit 803 is further configured to update the open list based on the successor node if the successor node does not belong to the open list and does not belong to the closed list; update the open list if the successor node belongs to the open list or belongs to the closed list and the first target evaluation function value is less than the second target evaluation value;

[0199] The determining unit 801 is further configured to continue to determine a new current node and the successor node set corresponding to the new current node, and continue to update the open list until the open list meets a preset condition, stop updating the open list, and determine the final open list.

[0200] Based on the parking path planning method of the above embodiments, an embodiment of the present application further provides a vehicle, as Figure 9 shown, Figure 9 FIG. is a schematic structural diagram of a vehicle provided by an embodiment of the present application. The vehicle 9 includes: a processor 901 and a memory 902. The memory 902 is used to store a computer program; the processor 901 is used to call and run the computer program from the memory 902 to execute the parking path planning method as described in the above embodiments.

[0201] In an embodiment of the present application, the above-mentioned processor 901 may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor. It can be understood that for different devices, the electronic devices for implementing the above-mentioned processor functions may be others, and the embodiments of the present application do not make specific limitations.

[0202] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which is used to implement the parking path planning method described in any of the above embodiments when executed by a processor.

[0203] Exemplarily, the program instructions corresponding to a parking path planning method in this embodiment may be stored on a storage medium such as an optical disc, a hard disk, or a USB flash drive. When the program instructions corresponding to a parking path planning method in the storage medium are read or executed by an electronic device, the parking path planning method described in any of the above embodiments can be implemented.

[0204] In addition, in the embodiments of the present application, each functional module may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional module.

[0205] In addition, in the embodiments of the present application, each functional module may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional module.

[0206] When the integrated unit is implemented in the form of a software functional module and is not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a vehicle to execute all or part of the steps of the method of this embodiment.

[0207] It should be understood that the "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the "in one embodiment" or "in an embodiment" or "in some embodiments" that appear throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the order numbers of the above processes do not mean the sequence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The serial numbers of the embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments. The above descriptions of the various embodiments tend to emphasize the differences between the various embodiments. Their similarities or similarities can be referred to each other. For the sake of brevity, they will not be repeated herein.

[0208] The modules described above as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules; they may be located in one place or distributed to multiple network units; some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0209] In addition, in each embodiment of the present application, the functional modules can all be integrated in one processing unit, or each module can be separately used as a unit, or two or more modules can be integrated in one unit; the above integrated modules can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0210] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments.

[0211] The methods disclosed in several method embodiments provided by the embodiments of the present application can be arbitrarily combined without conflict to obtain new method embodiments.

[0212] The features disclosed in several product embodiments provided by the embodiments of the present application can be arbitrarily combined without conflict to obtain new product embodiments.

[0213] The features disclosed in several method or device embodiments provided by the embodiments of the present application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0214] As described above, it is only the implementation manner of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should be covered within the protection scope of the embodiments of the present application.

Claims

1. A parking path planning method, characterized in that, The parking path planning method includes: When the target vehicle is in the parking area, determining the starting position and the target parking position of the target vehicle; Based on the starting node corresponding to the starting position, determining the current node in the open list and the set of successor nodes corresponding to the current node; For the successor nodes in the set of successor nodes corresponding to the current node, by calculating the comprehensive anthropomorphic penalty function values of the successor nodes, determining the first target evaluation function values of the successor nodes; wherein, the comprehensive anthropomorphic penalty function value includes a boundary distance penalty value and a boundary crossing penalty value; the boundary distance penalty value is determined based on the shortest distance between the node and the boundary, and the boundary crossing penalty value is determined based on the node sequence crossing the boundary and the distance between the node and the boundary when crossing the boundary; Based on the first target evaluation function values of the successor nodes, continuously updating the open list to determine the final open list; When the target node corresponding to the target parking position is in the final open list, performing backtracking based on the target node and the starting node to determine the parking path of the target vehicle.

2. The parking path planning method according to claim 1, wherein The determining the current node in the open list and the set of successor nodes corresponding to the current node based on the starting node corresponding to the starting position includes: Based on the starting node corresponding to the starting position, determining the open list and the closed list; Based on at least one node in the open list, calculating the second target evaluation function values of the nodes; Based on the second target evaluation function values, determining the current node and the set of successor nodes corresponding to the current node.

3. The parking path planning method according to claim 2, wherein The calculating the second target evaluation function values of the nodes based on at least one node in the open list includes: Based on at least one node in the open list, calculating the motion cost function value and the heuristic cost function value of each node; Based on the motion cost function value and the heuristic cost function value of each node, performing an operation to determine the second target evaluation function values of the nodes.

4. The parking path planning method according to claim 1, wherein The determining the first target evaluation function values of the successor nodes by calculating the comprehensive anthropomorphic penalty function values of the successor nodes in the set of successor nodes corresponding to the current node includes: Based on the successor nodes in the set of successor nodes and the obtained parking environment boundary, calculating the comprehensive anthropomorphic penalty function values of the successor nodes; Based on the comprehensive anthropomorphic penalty function values of the successor nodes, determining the first target evaluation function values of the successor nodes.

5. The parking path planning method according to claim 4, wherein The calculating the comprehensive anthropomorphic penalty function values of the successor nodes based on the successor nodes in the set of successor nodes and the obtained parking environment boundary includes: Based on the successor nodes in the set of successor nodes, the obtained parking environment boundary, and the environment information, calling the penalty coefficient corresponding to the environment information to calculate the boundary distance penalty values of the successor nodes; Based on the successor nodes in the set of successor nodes and the obtained parking environment boundary, calculating the boundary crossing penalty values of the successor nodes; Based on the boundary distance penalty value and the boundary crossing penalty value, determine the comprehensive anthropomorphic penalty function value of each successor node.

6. The parking path planning method according to claim 4, wherein Determining the first target evaluation function value of each successor node based on the comprehensive anthropomorphic penalty function value of each successor node includes: Calculate the motion cost function value of each successor node and the heuristic cost function value of each successor node; Based on the comprehensive anthropomorphic penalty function value of each successor node, the motion cost function value of each successor node, and the heuristic cost function value of each successor node, determine the first target evaluation function value of each successor node.

7. The parking path planning method according to any one of claims 1-6, characterized in that, Based on the first target evaluation function value of each successor node, continuously update the open list to determine the final open list, including: For each successor node, if the successor node does not belong to the open list and does not belong to the closed list, update the open list based on the successor node; If the successor node belongs to the open list or belongs to the closed list, and the first target evaluation function value is less than the second target evaluation value, update the open list; Continue to determine the new current node and the set of successor nodes corresponding to the new current node, and continue to update the open list until the open list reaches a preset condition, stop updating the open list, and determine the final open list.

8. The parking path planning method according to claim 7, wherein The preset condition is that the open list includes the target node corresponding to the target parking position or the open list is empty.

9. A parking path planning device, characterized in that, Includes a determination unit, a calculation unit, and an update unit; wherein, The determination unit is configured to, when the target vehicle is in the parking area, determine the starting position and the target parking position of the target vehicle; based on the starting node corresponding to the starting position, determine the current node in the open list and the set of successor nodes corresponding to the current node; The calculation unit is configured to, for the successor nodes in the set of successor nodes corresponding to the current node, determine the first target evaluation function value of each successor node by calculating the comprehensive anthropomorphic penalty function value of each successor node; wherein, the comprehensive anthropomorphic penalty function value includes a boundary distance penalty value and a boundary crossing penalty value; the boundary distance penalty value is determined based on the shortest distance between the node and the boundary, and the boundary crossing penalty value is determined based on the node sequence crossing the boundary and the distance between the node and the boundary when crossing the boundary; The update unit is configured to continuously update the open list based on the first target evaluation function value of each successor node to determine the final open list; The determination unit is further configured to, when the target node corresponding to the target parking position is in the final open list, perform backtracking based on the target node and the starting node to determine the parking path of the target vehicle.

10. A vehicle, characterized in that, Includes: A memory for storing executable data instructions; A processor, when executing the executable instructions stored in the memory, implements the parking path planning method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, Stored with executable instructions for causing a processor to implement the parking path planning method according to any one of claims 1-8 when executed.

Images