Path planning navigation method, device and server applied to parking lot

Abstract

The application discloses a path planning navigation method and device applied to a parking lot and a server, relates to path planning technology, and comprises the following steps: acquiring all road sections in a parking lot where a vehicle is currently located, screening a plurality of target road sections available for the vehicle to pass through, and a topological relationship between the target road sections; taking the target road sections as nodes in a directed graph, determining arrow directions in the directed graph according to the topological relationship between the target road sections, and generating the directed graph; determining a longest path contained in the directed graph; and determining the longest path as a target path, so that the vehicle is navigated to park according to the target path. In the path planning navigation method and device applied to the parking lot and the server, the concept of graph theory is used to convert a parking lot map into a directed graph, and then a longest path in the directed graph is determined, and the longest path is the target path. The target path has high path coverage and few repeated road sections, and is suitable for a parking lot scene.

Description

Technical Field

[0001] The present disclosure relates to path planning technology, and more particularly to a path planning and navigation method, device, and server for parking lots. Background Art

[0002] Currently, path planning for autonomous vehicles generally involves planning a reasonable route from a starting point to a destination. In parking lot scenarios, it's often difficult to accurately determine where vacant parking spaces are (i.e., there's no clear destination). Therefore, how to plan paths in parking lots to facilitate the vehicle's ability to find empty spaces while cruising through the lot is a pressing issue.

[0003] In existing technologies, path planning for autonomous vehicles requires clarifying the starting and destination locations, and then finding an optimal (short distance, short time) path.

[0004] However, the above method is only suitable for scenarios with a clear destination and is not applicable to parking lot scenarios. Summary of the Invention

[0005] The present disclosure provides a path planning and navigation method, device, and server for parking lots, so as to solve the problem that the path planning methods in the prior art are not applicable to parking lot scenarios.

[0006] According to a first aspect of the present disclosure, a path planning and navigation method for a parking lot is provided, comprising:

[0007] Obtain all road sections in the parking lot where the vehicle is currently located, and filter out multiple target road sections that the vehicle can pass through, as well as the topological relationship between the target road sections;

[0008] The target road segments are used as nodes in a directed graph, and the directions of arrows in the directed graph are determined according to the topological relationships between the target road segments to generate a directed graph; wherein the road segment currently located by the vehicle is used as a starting road segment, and the node in the directed graph corresponding to the starting road segment is used as a starting node;

[0009] Determine the longest path included in the directed graph; and determine the longest path as a target path, so that the vehicle navigates and parks according to the target path.

[0010] According to a second aspect of the present disclosure, a path planning and navigation device for a parking lot is provided, comprising:

[0011] an acquisition unit, configured to acquire all road sections in the parking lot where the vehicle is currently located, and screen out a plurality of target road sections that the vehicle can pass through, as well as a topological relationship between the target road sections;

[0012] a directed graph generating unit, configured to use the target road segments as nodes in a directed graph, and determine the directions of arrows in the directed graph based on the topological relationships between the target road segments, thereby generating a directed graph; wherein the road segment currently located by the vehicle is used as a starting road segment, and the node in the directed graph corresponding to the starting road segment is used as a starting node;

[0013] The determining unit is configured to determine the longest path included in the directed graph; and determine the longest path as a target path, so that the vehicle navigates and parks according to the target path.

[0014] According to a third aspect of the present disclosure, a server is provided, comprising a memory and a processor; wherein:

[0015] The memory is used to store computer programs;

[0016] The processor is configured to read the computer program stored in the memory and execute the path planning and navigation method for a parking lot as described in the first aspect according to the computer program in the memory.

[0017] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the path planning and navigation method applied to a parking lot as described in the first aspect is implemented.

[0018] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program. When the computer program is executed by a processor, the computer program implements the path planning and navigation method applied to a parking lot as described in the first aspect.

[0019] The path planning and navigation method, device, and server for parking lots provided by the present disclosure include: obtaining all road segments in the parking lot where a vehicle is currently located, screening multiple target road segments that are navigable by the vehicle, and the topological relationships between the target road segments; treating the target road segments as nodes in a directed graph, and determining the directions of arrows in the directed graph based on the topological relationships between the target road segments to generate a directed graph; wherein the road segment where the vehicle is currently located is treated as the starting road segment, and the node in the directed graph corresponding to the starting road segment is used as the starting node; determining the longest path contained in the directed graph; and determining the longest path as the target path, so that the vehicle navigates and parks according to the target path. The path planning and navigation method, device, and server for parking lots provided by this solution utilize graph theory concepts to convert the parking lot map into a directed graph, and then determine the longest path in the directed graph, which is the target path. The target path obtained using this solution has a high path coverage rate for the parking lot map, thereby providing users with a correspondingly larger number of parking spaces to choose from. Furthermore, the target path has a small number of repeated road segments, thereby improving the efficiency of users in finding parking spaces, making it suitable for parking lot scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a flow chart of a path planning and navigation method applied to a parking lot according to an exemplary embodiment of the present disclosure;

[0022] Figure 2 This is a flow chart of a path planning and navigation method applied to a parking lot according to another exemplary embodiment of the present disclosure;

[0023] Figure 3 A schematic diagram of a process for determining strongly connected components contained in a directed graph according to an exemplary embodiment of the present disclosure;

[0024] Figure 4 A schematic diagram of a process for determining strongly connected components contained in a directed graph, shown as another exemplary embodiment of the present disclosure;

[0025] Figure 5 A schematic diagram of a process for determining strongly connected components contained in a directed graph is shown as another exemplary embodiment of the present disclosure;

[0026] Figure 6A schematic diagram of a process for determining strongly connected components contained in a directed graph, shown as another exemplary embodiment of the present disclosure;

[0027] Figure 7 A schematic diagram of a directed acyclic graph according to an exemplary embodiment of the present disclosure;

[0028] Figure 8 A schematic diagram illustrating determining the longest path contained in a directed acyclic graph according to an exemplary embodiment of the present disclosure;

[0029] Figure 9 This is a structural diagram of a path planning and navigation device applied to a parking lot, showing an exemplary embodiment of the present disclosure;

[0030] Figure 10 This is a structural diagram of a server according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] Currently, path planning for autonomous vehicles generally involves planning a reasonable route from a starting point to a destination. In parking lot scenarios, it's often difficult to accurately determine where vacant parking spaces are (i.e., there's no clear destination). Therefore, how to plan paths in parking lots to facilitate the vehicle's ability to find empty spaces while cruising through the lot is a pressing issue.

[0032] In existing technologies, path planning for autonomous vehicles requires clearly defining the starting and destination locations, and then finding an optimal path (shortest distance and shortest time). Path planning for outdoor local areas, such as those used by outdoor sweepers, agricultural vehicles, and robot vacuums, requires high path coverage.

[0033] However, existing path planning methods for autonomous vehicles are only suitable for scenarios with a clear destination and are not applicable to parking lots. Path planning for outdoor areas, such as those for street sweepers, agricultural vehicles, and robot vacuums, also differs from parking lots. For example, some parking lot paths have only one entrance and no exit, making it difficult for vehicles to turn around. Therefore, these paths can be excluded from parking lot scenarios. Consequently, path coverage in parking lots is not as high as that for outdoor street sweepers, agricultural vehicles, and robot vacuums.

[0034] To address the aforementioned technical issues, the solution provided in this disclosure utilizes graph theory to convert a parking map into a directed graph, thereby determining the longest path within the directed graph. This longest path serves as the target path. The target path obtained using this solution offers high path coverage for parking maps, providing users with a correspondingly larger number of available parking spaces. Furthermore, the solution also minimizes repeated sections, significantly improving user efficiency in finding parking spaces and making it suitable for parking scenarios.

[0035] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0036] The following detailed description of the technical solution of the present disclosure and how the technical solution of the present disclosure solves the above-mentioned technical problems is provided with specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. The embodiments of the present disclosure will be described below in conjunction with the accompanying drawings.

[0037] Figure 1 The figure is a flow chart of a path planning and navigation method applied to a parking lot according to an exemplary embodiment of the present disclosure.

[0038] like Figure 1 As shown, the path planning and navigation method applied to a parking lot provided in this embodiment includes:

[0039] Step 101: Acquire all road sections in the parking lot where the vehicle is currently located, and screen out a plurality of target road sections that the vehicle can pass through, as well as the topological relationship between the target road sections.

[0040] Among them, the execution entity of the method provided by the present disclosure can be a server.

[0041] Specifically, all road sections in the parking lot where the vehicle is currently located can be obtained from a map of the parking lot. The map of the parking lot can be pre-stored in a server.

[0042] Specifically, multiple target road sections accessible to vehicles can be screened from all acquired road sections. For example, pedestrian sections and dead-end sections can be identified from all acquired road sections, and the identified pedestrian sections and dead-end sections can be removed to obtain a target map. The target map includes multiple target road sections and the topological relationships between the target road sections.

[0043] A link is the smallest unit of a road on a map.

[0044] Among them, walking sections refer to sections marked on the map that are only for walking and not for vehicles.

[0045] Among them, a dead end section refers to a section that can only be entered but not exited, that is, a section with only one entrance and no exit.

[0046] Step 102: The target road section is used as a node in a directed graph, and the direction of the arrow in the directed graph is determined according to the topological relationship between the target road sections to generate a directed graph; wherein the road section where the vehicle is currently located is used as the starting road section, and the node in the directed graph corresponding to the starting road section is used as the starting node.

[0047] Among them, a directed graph is a directional graph consisting of a vertex and a set of directed edges, and each directional edge connects a pair of ordered vertices.

[0048] Specifically, the target road segments can be used as nodes in a directed graph, and based on the topological relationship between the target road segments, the edges connecting the nodes in the directed graph and the arrow directions of the edges (i.e., the directions of the edges) are determined to generate a directed graph.

[0049] Specifically, the road section where the vehicle is currently located can be used as the starting road section, and the node in the directed graph corresponding to the starting road section can be used as the starting node.

[0050] Step 103 , determining the longest path included in the directed graph; determining the longest path as the target path, so that the vehicle navigates and parks according to the target path.

[0051] Specifically, a pre-set method can be used to determine the longest path included in the directed graph. This longest path can then be determined as the target path. The vehicle can navigate and park according to the target path.

[0052] Specifically, the target path may be sent to a map application for display by the map application.

[0053] Specifically, the autonomous vehicle can use the target path to navigate the parking lot and, combined with the autonomous driving function, complete automatic parking. This process can be either driver-controlled or automatic.

[0054] (1) If the driver is in control of the vehicle, during the cruise, the driver can select an empty parking space on either side of the road at any time to park. If the automatic parking function is selected at this time, the vehicle can also automatically park in the designated parking space. If the driver does not select a parking space at all, when the vehicle reaches the end of the route, it will be prompted that it has reached the cruise end point.

[0055] (2) If the driver does not control the vehicle, the automatic parking space selection function can be selected. Once an empty parking space is found during cruising, the vehicle will automatically park. If the automatic parking space selection function is not selected, the driver needs to specify a parking space during cruising, and then the vehicle will automatically park. If the automatic parking space selection function is not selected and the driver does not specify a parking space during cruising, when the vehicle reaches the end of the route, it will be prompted that it has reached the cruising end point and will automatically park.

[0056] The path planning and navigation method for parking lots provided in the present disclosure includes: obtaining all road sections in the parking lot where a vehicle is currently located, screening multiple target road sections that are accessible to the vehicle, and the topological relationships between the target road sections; treating the target road sections as nodes in a directed graph, and determining the directions of arrows in the directed graph based on the topological relationships between the target road sections to generate a directed graph; wherein the road section where the vehicle is currently located is treated as the starting road section, and the node in the directed graph corresponding to the starting road section is used as the starting node; determining the longest path contained in the directed graph; and determining the longest path as the target path, so that the vehicle can navigate and park according to the target path. This solution utilizes graph theory concepts to convert a parking lot map into a directed graph, and then determines the longest path in the directed graph, which is the target path. The target path obtained using this solution has a high path coverage rate for the parking lot map, thereby providing users with a correspondingly larger number of parking spaces to choose from. Furthermore, the solution has few repeated road sections, thereby improving the efficiency of users in finding parking spaces, making it suitable for parking lot scenarios.

[0057] Figure 2 The figure is a flowchart of a path planning and navigation method applied to a parking lot according to another exemplary embodiment of the present disclosure.

[0058] like Figure 2 As shown, the path planning and navigation method applied to a parking lot provided in this embodiment includes:

[0059] Step 201 : Acquire all road sections in the parking lot where the vehicle is currently located, and screen out a plurality of target road sections that the vehicle can pass through, as well as the topological relationship between the target road sections.

[0060] Specifically, the principle and implementation of step 201 are similar to those of step 101 and will not be described in detail.

[0061] In step 202, the target road section is used as a node in a directed graph, and the direction of the arrow in the directed graph is determined according to the topological relationship between the target road sections to generate a directed graph; wherein the road section where the vehicle is currently located is used as the starting road section, and the node in the directed graph corresponding to the starting road section is used as the starting node.

[0062] Specifically, after step 202, step 203 may be executed, or step 205 may be executed.

[0063] Specifically, the principle and implementation of step 202 are similar to those of step 102 and will not be described in detail.

[0064] Step 203: If it is determined that the directed graph is not a strongly connected graph, then the strongly connected components included in the directed graph are determined according to a preset method.

[0065] In a directed graph G, if there is at least one path between two vertices, the two vertices are said to be strongly connected. If every two vertices in a directed graph G are strongly connected, G is said to be a strongly connected graph. If a directed graph G is not a strongly connected graph, then G is not a strongly connected graph. A maximal strongly connected subgraph of a directed graph that is not a strongly connected graph is called a strongly connected component.

[0066] Specifically, if it is determined that the directed graph is not a strongly connected graph, all strongly connected components included in the directed graph may be determined according to a preset method.

[0067] In step 204 , a directed acyclic graph is generated based on each strongly connected component, and the longest path included in the directed acyclic graph is determined using a preset method; the longest path is determined as the target path, so that the vehicle navigates and parks according to the target path.

[0068] Specifically, each strongly connected component can be regarded as a whole, and then the strongly connected components can be connected according to the connection relationship between the strongly connected components to generate a directed acyclic graph.

[0069] A directed acyclic graph is a directed graph without loops.

[0070] Specifically, all paths included in the directed acyclic graph can be searched in a pre-set manner, and the longest path can be selected from them. The longest path can be determined as the target path. Then, the vehicle can be navigated and parked according to the target path.

[0071] In one implementable manner, the strongly connected components are used as nodes in a directed acyclic graph, and the directions of arrows in the directed acyclic graph are determined according to the directions of arrows between the strongly connected components to generate a directed acyclic graph.

[0072] Specifically, if it is determined that the directed graph is not a strongly connected graph, all strongly connected components included in the directed graph may be determined according to a preset method.

[0073] The preset method may be the Tarjan algorithm, which is an algorithm invented by Robert Tarjan for finding strongly connected components in a directed graph.

[0074] Specifically, the Tarjan algorithm is based on a depth-first search of a graph, treating each strongly connected component as a subtree in the search tree. During the search, unprocessed nodes in the current search tree are added to a stack. During backtracking, the algorithm determines whether the node at the top of the stack is a strongly connected component.

[0075] Define DFN(u) as the search sequence number (timestamp) of node u, and Low(u) as the sequence number of the earliest node in the stack that can be traced back to u or its subtree. From the definition, it can be seen that when DFN(u) = LOW(u), all nodes in the search subtree rooted at u are a strongly connected component.

[0076] like Figure 3 In the directed graph shown, let node 1 be the starting node, and start depth-first exploration from node 1. The traversed nodes are added to the stack, and the stack contains 1, 3, 5, and 6. And DFN[6] = LOW[6] = 4, then the strongly connected component {6} is found.

[0077] Then, return to node 5, such as Figure 4 As shown, DFN[5]=LOW[5]=3, so {5} is a strongly connected component.

[0078] Then, return to node 3, such as Figure 5 As shown, the search continues to node 4, and 4 is added to the stack. Node 4 is found to be a backward edge of node 1, and node 1 is still in the stack, so LOW[4] = 1. Node 6 has been popped from the stack, so 6 is no longer visited, and the search returns to 3. (3, 4) is a branch edge, so LOW[3] = LOW[4] = 1.

[0079] Continue back to node 1, such as Figure 6 As shown, the last node visited is 2. When the edge (2, 4) is visited, 4 is still in the stack, so LOW[2] = 4. After returning to 1, it is found that DFN[1] = LOW[1]. All nodes in the stack are taken out to form a strongly connected component {1, 3, 4, 2}

[0080] Finally, the strongly connected components are subgraphs {1,2,3,4}, {5}, and {6}.

[0081] It's important to note that the graph theory discussed above describes point-to-point relationships within a graph. In path planning, the goal is to traverse the most links. Therefore, when modeling, consider links as points in the graph, and the relationships between links (i.e., whether they are passable) as arrows. Next, use the Tarjan algorithm to find all strongly connected components in the target parking map.

[0082] Then, each strongly connected component can be regarded as a whole, and each strongly connected component can be regarded as a node in a directed acyclic graph. The edges in the directed acyclic graph and the direction of the arrows (i.e., the direction of the edges) are determined according to the direction of the arrows between the strongly connected components, thereby generating a directed acyclic graph.

[0083] Specifically, such as Figure 7As shown in Figure 1, the strongly connected components in a directed graph are collapsed. Points in the same strongly connected component are combined into a single new node, whose value is equal to the sum of the weights of all nodes in the strongly connected component. The length of the target road segment corresponding to the node can be used as the node weight. After collapsing, a new graph (directed acyclic graph) is obtained from the original graph (directed graph).

[0084] The sum of the lengths of the target road sections corresponding to the strongly connected components is determined as the weight of the strongly connected components; and the path with the largest weight in the directed acyclic graph is searched; the path with the largest weight contains at least one target strongly connected component.

[0085] Specifically, the sum of the lengths of the target paths corresponding to all nodes in the strongly connected component may be used as the weight of the strongly connected component.

[0086] Specifically, you can use a pre-defined method to search for all paths in a directed acyclic graph. For example, you can start from the starting link and explore the longest path in the new graph. You can use a depth-first search (DFS) method. In short, the process involves searching every possible branch path until it can't go any deeper. The detailed process is as follows:

[0087] Depth traverses the nodes of the graph, searching the branches of the tree as deeply as possible. When all the edges of node v have been explored, the search will backtrack to the starting node of the edge where node v was found. The whole process is repeated until all nodes have been visited. Figure 8 The DFS traversal process of the directed acyclic graph shown is: a, b, d, e, f, c. Figure 7 The DFS traversal process of the directed acyclic graph shown is: {1,2,3,4}, {5}, {6}.

[0088] Then, a path with the largest weight is selected from the paths in the searched directed acyclic graph, where the path with the largest weight contains at least one target strongly connected component.

[0089] According to a preset method, a first path including each target node in the target strongly connected component is determined; and each first path is connected to generate a target path.

[0090] Specifically, according to the node contained in the path with the largest weight, if it is a new point synthesized by the strongly connected component, the new node is replaced with the strongly connected component to generate the target path. Figure 7 For the directed acyclic graph shown in the figure, the paths with the largest weights found include {1,2,3,4}, {5}, and {6}.

[0091] Specifically, a first path including each node in the target strongly connected component can be determined in a pre-set manner, and then, based on the topological relationship between each target strongly connected component in the directed acyclic graph, each first path is connected to generate a target path.

[0092] In one implementation, a first number of arrows entering a target node is determined, and a second number of arrows exiting the target node is determined.

[0093] Specifically, each target strongly connected component includes at least one target node. A first number of arrows entering the target node and a second number of arrows exiting the target node corresponding to each target node can be calculated.

[0094] If it is determined that the first quantity is not equal to the second quantity, the arrows corresponding to the target nodes are supplemented so that the supplemented first quantity is equal to the second quantity, and the target strongly connected component is updated.

[0095] Specifically, if it is determined that the first number corresponding to the target node is not equal to the second number, the edge corresponding to the target node (that is, the arrow corresponding to the target node) can be supplemented so that the first number corresponding to the supplemented target node is equal to the second number, and the strongly connected component is updated.

[0096] Optionally, if it is determined that the first number is greater than the second number, arrows going out from the target node are supplemented so that the supplemented second number is equal to the first number, and the target strongly connected component is updated.

[0097] Specifically, if it is determined that the first number of target nodes is greater than the second number, arrows going out of the target node may be supplemented so that the supplemented second number is equal to the first number, and the target strongly connected component is updated.

[0098] If it is determined that the first number is less than the second number, arrows entering the target node are supplemented so that the supplemented first number is equal to the second number, and the target strongly connected component is updated.

[0099] Specifically, if it is determined that the first number of target nodes is less than the second number, arrows entering the target node may be supplemented so that the supplemented first number is equal to the second number, and the target strongly connected component is updated.

[0100] For example, Figure 6The directed graph shown in the figure includes the target strongly connected component {1,2,3,4}. The first quantity corresponding to node 1 is 1, and the second quantity is 2; the first quantity and the second quantity corresponding to node 2 are both 1; the first quantity and the second quantity corresponding to node 3 are both 1; and the first quantity and the second quantity corresponding to node 4 are 2 and 1. Therefore, an edge can be added between node 4 and node 1, with the arrow pointing from node 4 to node 1, and the target strongly connected component {1,2,3,4} can be updated. In the updated target strongly connected component {1,2,3,4}, the first quantity of each node is equal to the second quantity.

[0101] The updated target strongly connected component is processed using the Euler algorithm to obtain a first path containing each target node in the target strongly connected component.

[0102] Specifically, the Euler algorithm can be used to process the updated target strongly connected component to obtain a first path containing each target node in the target strongly connected component, and the first path traverses all edges in the target strongly connected component, and each edge is passed only once.

[0103] For example, according to Figure 6 The target strongly connected component {1, 2, 3, 4} in the directed graph shown in FIG is an updated target strongly connected component {1, 2, 3, 4}. The Euler algorithm can be used to process the updated target strongly connected component {1, 2, 3, 4}, and the obtained first path can be: 1241241.

[0104] In one implementable manner, the target path is generated by connecting the first paths with the shortest distance according to the topological relationship between the target road segments.

[0105] Specifically, after obtaining the first paths corresponding to the target strongly connected components, the shortest distance connecting the first paths can be found according to the topological relationship between the target paths corresponding to the target strongly connected components, and the first paths can be connected to generate the target path.

[0106] Then, the vehicle can navigate and park according to the target path.

[0107] In step 205 , if the directed graph is determined to be a strongly connected graph, a second path including the nodes in the strongly connected graph is determined according to a preset method, and the second path is determined as the target path, so that the vehicle navigates and parks according to the target path.

[0108] Specifically, if the directed graph is determined to be a strongly connected graph, a second path including each node in the strongly connected graph can be determined according to a pre-defined method, and the second path can be determined as the target path. Then, the vehicle can navigate and park according to the target path.

[0109] Specifically, the principle and implementation of determining the second path are similar to those of determining the first path, and will not be described in detail.

[0110] Figure 9 This is a structural diagram of a path planning and navigation device applied to a parking lot, showing an exemplary embodiment of the present disclosure.

[0111] like Figure 9 As shown, the path planning and navigation device 900 provided by the present disclosure for use in a parking lot includes:

[0112] An acquisition unit 910 is configured to acquire all road sections in the parking lot where the vehicle is currently located, and to select a plurality of target road sections that the vehicle can pass through, as well as the topological relationship between the target road sections;

[0113] A directed graph generation unit 920 is configured to use the target road segments as nodes in a directed graph and determine the directions of arrows in the directed graph based on the topological relationships between the target road segments to generate a directed graph; wherein the road segment currently located by the vehicle is used as the starting road segment, and the node in the directed graph corresponding to the starting road segment is used as the starting node;

[0114] The determination unit 930 is configured to determine the longest path included in the directed graph and determine the longest path as the target path so that the vehicle navigates and parks according to the target path.

[0115] The determining unit 930 is specifically configured to determine the strongly connected components included in the directed graph according to a preset method if the directed graph is determined to be a non-strongly connected graph;

[0116] A directed acyclic graph is generated according to each strongly connected component, and the longest path contained in the directed acyclic graph is determined using a preset method.

[0117] The determining unit 930 is specifically configured to use the strongly connected components as nodes in a directed acyclic graph, determine the direction of arrows in the directed acyclic graph according to the direction of arrows between the strongly connected components, and generate a directed acyclic graph;

[0118] The sum of the lengths of the target road segments corresponding to the strongly connected components is determined as the weight of the strongly connected components; and the path with the largest weight in the directed acyclic graph is searched; the path with the largest weight contains at least one target strongly connected component;

[0119] According to a preset method, a first path including each target node in the target strongly connected component is determined; and each first path is connected to generate a target path.

[0120] a determining unit 930, specifically configured to determine a first number of arrows entering a target node and a second number of arrows exiting the target node;

[0121] If it is determined that the first number is not equal to the second number, then supplement the arrows corresponding to the target node so that the supplemented first number is equal to the second number, and update the target strongly connected component;

[0122] The updated target strongly connected component is processed using the Euler algorithm to obtain a first path containing each target node in the target strongly connected component.

[0123] The determining unit 930 is specifically configured to, if it is determined that the first number is greater than the second number, supplement the arrows going out of the target node so that the supplemented second number is equal to the first number, and update the target strongly connected component;

[0124] If it is determined that the first number is less than the second number, arrows entering the target node are supplemented so that the supplemented first number is equal to the second number, and the target strongly connected component is updated.

[0125] The determining unit 930 is specifically configured to connect the first paths with the shortest distance according to the topological relationship between the target road segments to generate a target path.

[0126] The determining unit 930 is further configured to determine, if the directed graph is determined to be a strongly connected graph, a second path including each node in the strongly connected graph according to a preset method, and determine the second path as the target path.

[0127] Figure 10 This is a structural diagram of a server according to an exemplary embodiment of the present disclosure.

[0128] like Figure 10 As shown, the server provided in this embodiment includes:

[0129] Memory 1001;

[0130] Processor 1002; and

[0131] computer programs;

[0132] The computer program is stored in the memory 1001 and is configured to be executed by the processor 1002 to implement any of the above path planning and navigation methods applied to a parking lot.

[0133] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. The computer program is executed by a processor to implement any of the above-mentioned path planning and navigation methods applied to a parking lot.

[0134] This embodiment further provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements any of the above-mentioned path planning and navigation methods applied to a parking lot.

[0135] This embodiment further provides a software development kit, including a map data engine; wherein the map data engine includes any of the above-mentioned path planning and navigation devices applied to a parking lot.

[0136] This embodiment also provides a vehicle, which includes any of the above-mentioned path planning and navigation devices applied to parking lots.

[0137] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A path planning and navigation method applied to a parking lot, characterized in that: include: Obtain all road sections in the parking lot where the vehicle is currently located, and filter out multiple target road sections that the vehicle can pass through, as well as the topological relationship between the target road sections; The target road segments are used as nodes in a directed graph, and the directions of arrows in the directed graph are determined according to the topological relationships between the target road segments to generate a directed graph; wherein the road segment currently located by the vehicle is used as a starting road segment, and the node in the directed graph corresponding to the starting road segment is used as a starting node; Determining the longest path included in the directed graph; determining the longest path as a target path, so that the vehicle navigates and parks according to the target path; determining the longest path included in the directed graph includes: If it is determined that the directed graph is not a strongly connected graph, then determining the strongly connected components included in the directed graph according to a preset method; The strongly connected components are used as nodes in a directed acyclic graph, and the directions of arrows in the directed acyclic graph are determined according to the directions of arrows between the strongly connected components to generate a directed acyclic graph; Determining the sum of the lengths of the target road sections corresponding to the strongly connected components as the weight of the strongly connected components; and searching for a path with the largest weight in the directed acyclic graph; wherein the path with the largest weight contains at least one target strongly connected component; According to a preset method, a first path including each target node in the target strongly connected component is determined; and each of the first paths is connected to generate a target path.

2. The method according to claim 1, characterized in that The determining, according to a preset method, a first path including each target node in the target strongly connected component includes: determining a first number of arrows entering the target node, and determining a second number of arrows exiting the target node; If it is determined that the first number is not equal to the second number, supplement the arrows corresponding to the target node so that the supplemented first number is equal to the second number, and update the target strongly connected component; The updated target strongly connected component is processed using the Euler algorithm to obtain a first path including each target node in the target strongly connected component.

3. The method according to claim 2, characterized in that If it is determined that the first quantity is not equal to the second quantity, supplementing the arrow corresponding to the target node so that the supplemented first quantity is equal to the second quantity includes: If it is determined that the first number is greater than the second number, then supplement the arrows going out from the target node so that the supplemented second number is equal to the first number, and update the target strongly connected component; If it is determined that the first number is less than the second number, arrows entering the target node are supplemented so that the supplemented first number is equal to the second number, and the target strongly connected component is updated.

4. The method according to claim 1, wherein The connecting the first paths to generate a target path includes: According to the topological relationship between the target road segments, the first paths are connected with the shortest distance to generate a target path.

5. The method according to claim 1, wherein Determining the longest path contained in the directed graph includes: If it is determined that the directed graph is a strongly connected graph, a second path including each node in the strongly connected graph is determined according to a preset method, and the second path is determined as the target path.

6. A path planning and navigation device for a parking lot, characterized in that: include: an acquisition unit, configured to acquire all road sections in the parking lot where the vehicle is currently located, and screen out a plurality of target road sections that the vehicle can pass through, as well as a topological relationship between the target road sections; a directed graph generating unit, configured to use the target road segments as nodes in a directed graph, and determine the directions of arrows in the directed graph based on the topological relationships between the target road segments, thereby generating a directed graph; wherein the road segment currently located by the vehicle is used as a starting road segment, and the node in the directed graph corresponding to the starting road segment is used as a starting node; a determining unit, configured to determine the longest path included in the directed graph; and determine the longest path as a target path, so that the vehicle navigates and parks according to the target path; The determining unit is specifically configured to, if it is determined that the directed graph is not a strongly connected graph, determine the strongly connected components contained in the directed graph according to a preset method; use the strongly connected components as nodes in a directed acyclic graph, determine the directions of arrows in the directed acyclic graph according to the directions of arrows between the strongly connected components, and generate a directed acyclic graph; determine the sum of the lengths of target road sections corresponding to the strongly connected components as the weights of the strongly connected components; and search for a path with the largest weight in the directed acyclic graph; the path with the largest weight contains at least one target strongly connected component; According to a preset method, a first path including each target node in the target strongly connected component is determined; and each of the first paths is connected to generate a target path.

7. A software development kit, characterized in that: It comprises a map data engine; wherein, the map data engine comprises the path planning and navigation device for parking lots as described in claim 6.

8. A vehicle, characterized in that: The invention comprises the path planning and navigation device for use in a parking lot as described in claim 6.

Images