Vehicle path planning method, device, equipment, storage medium and product

Abstract

The present application discloses a vehicle path planning method, device, equipment, storage medium and product, belonging to the field of vehicle technology. The method includes: forming a node set with a path end point and multiple candidate path nodes; taking the path starting point as a reference node; determining a first target node from the node set based on the reference node; determining multiple neighbor nodes from the node set based on the first target node; respectively determining the distance between the reference node and each neighbor node; determining the target neighbor node based on the distance between the reference node and each neighbor node, and taking the target neighbor node as the predecessor node of the first target node; taking the target neighbor node as a reference node, and then executing the step of determining the first target node from the node set based on the reference node, until the node set is empty or the first target node is the path end point; and performing path tracing to obtain the driving path. The present application can improve the planning efficiency of the driving path.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle path planning method, device, equipment, storage medium and product. Background Art

[0002] Autonomous vehicles, also known as driverless cars, are intelligent products driven by the global development of internet technology. This technology has revolutionized the world of cars and transportation, revolutionizing the way cars are driven and how they are used. Path planning is one of the most fundamental functions of autonomous vehicles. This means that autonomous vehicles automatically find the optimal route from their starting point to their destination based on the actual road conditions and then drive themselves along this optimal route. Summary of the Invention

[0003] The embodiments of the present application provide a vehicle path planning method, apparatus, device, storage medium, and product that can improve the efficiency of driving path planning. The technical solution is as follows:

[0004] In one aspect, a vehicle path planning method is provided, the method comprising:

[0005] Determine the path starting point, path ending point, and multiple candidate path nodes of the autonomous vehicle;

[0006] Combining the path endpoint and the plurality of candidate path nodes into a node set;

[0007] Taking the starting point of the path as a reference node;

[0008] Determine a first target node from the node set based on the reference node, and delete the first target node from the node set, where the first target node is the node closest to the reference node;

[0009] Based on the first target node, determining a plurality of neighbor nodes of the first target node from the node set;

[0010] Determining the distance between the reference node and each neighbor node respectively;

[0011] Determine a target neighbor node based on the distance between the reference node and each of the neighbor nodes, and use the target neighbor node as a predecessor node of the first target node;

[0012] Taking the target neighbor node as a reference node, and then performing the step of determining a first target node from the node set based on the reference node until the node set is empty or the first target node is the end point of the path;

[0013] Starting from the end point of the path, tracing back along the predecessor node to the starting point of the path, a driving path from the starting point of the path to the end point of the path is obtained.

[0014] In a possible implementation, determining the target neighbor node based on the distance between the reference node and each neighbor node includes:

[0015] For a first neighbor node, the distance between the starting point of the path and the first neighbor node is used as the target distance, and the first neighbor node is used as the target neighbor node;

[0016] For the next neighbor node, if the distance between the starting point of the path and the next neighbor node is less than the target distance, the target distance is updated to the distance between the starting point of the path and the next neighbor node, and the target neighbor node is updated to the next neighbor node, and so on, until the multiple neighbor nodes are determined and the target neighbor node is obtained.

[0017] In another possible implementation, determining the target neighbor node based on the distance between the reference node and each neighbor node includes:

[0018] For a first neighbor node, determining a first quality parameter value based on a distance between the starting point of the path and the first neighbor node and a time required for the autonomous vehicle to travel the distance, the first quality parameter value being used to indicate a quality of the first neighbor node as a path node, the first quality parameter value being used as a target quality parameter value, and the first neighbor node being used as the target neighbor node;

[0019] For the next neighbor node, a second quality parameter value is determined based on the distance between the starting point of the path and the next neighbor node and the time required for the autonomous driving vehicle to travel the distance. The second quality parameter value is used to represent the quality of using the next neighbor node as a path node. When the second quality parameter value is greater than the target quality parameter value, the target quality parameter value is updated to the second quality parameter value, and the target neighbor node is updated to the next neighbor node. This process is repeated until the multiple neighbor nodes are determined and the target neighbor node is obtained.

[0020] In another possible implementation, determining the target neighbor node based on the distance between the reference node and each neighbor node includes:

[0021] For a first neighbor node, based on the distance between the starting point of the path and the first neighbor node and the safety factor of the autonomous vehicle passing through the first neighbor node, determining a third quality parameter value, the third quality parameter value being used to indicate the quality of the first neighbor node as a path node, using the third quality parameter value as a target quality parameter value, and using the first neighbor node as the target neighbor node;

[0022] For the next neighbor node, a fourth quality parameter value is determined based on the distance between the starting point of the path and the next neighbor node and the safety factor of the autonomous driving vehicle passing through the next neighbor node. The fourth quality parameter value is used to represent the quality of the next neighbor node as a path node. When the fourth quality parameter value is greater than the target quality parameter value, the target quality parameter value is updated to the fourth quality parameter value, and the target neighbor node is updated to the next neighbor node, and so on, until the multiple neighbor nodes are determined and the target neighbor node is obtained.

[0023] In another possible implementation, the process of determining the end point of the path of the autonomous vehicle includes:

[0024] Activating the endpoint recognition function of the autonomous vehicle;

[0025] While the driver is driving the autonomous vehicle, the body sensor of the autonomous vehicle is activated by the endpoint recognition function;

[0026] Acquiring first environmental data of the autonomous driving vehicle through the vehicle body sensor;

[0027] Based on the first environmental data, the parking end point of the autonomous driving vehicle is determined, and the parking end point is used as the path end point of the autonomous driving vehicle.

[0028] In another possible implementation, determining, based on the first target node, a plurality of neighbor nodes of the first target node from the node set includes:

[0029] Acquire second environment data of the first target node;

[0030] When the second environmental data indicates that an obstacle exists around the first target node, determining an obstacle direction of the obstacle at the first target node based on the second environmental data;

[0031] Determining a pathfinding direction of the autonomous vehicle based on the obstacle direction;

[0032] Based on the routing direction, a plurality of neighbor nodes of the first target node are determined from the node set, where the plurality of neighbor nodes are located in the routing direction of the first target node.

[0033] In another aspect, a vehicle path planning device is provided, the device comprising:

[0034] A first determination module is used to determine a path starting point, a path ending point, and a plurality of candidate path nodes of the autonomous driving vehicle;

[0035] a composition module, configured to combine the path endpoint and the plurality of candidate path nodes into a node set;

[0036] As a module, used to take the starting point of the path as a reference node;

[0037] A second determining module is configured to determine a first target node from the node set based on the reference node, and delete the first target node from the node set, wherein the first target node is the node closest to the reference node;

[0038] a third determining module, configured to determine, based on the first target node, a plurality of neighboring nodes of the first target node from the node set;

[0039] a fourth determining module, configured to respectively determine the distance between the reference node and each neighboring node;

[0040] a fifth determining module, configured to determine a target neighboring node based on a distance between the reference node and each of the neighboring nodes, and use the target neighboring node as a predecessor node of the first target node;

[0041] The module is further configured to use the target neighbor node as a reference node;

[0042] The second determining module is further configured to determine a first target node from the node set based on the reference node until the node set is empty or the first target node is a path end point;

[0043] The backtracking module is used to start from the end point of the path and backtrack along the predecessor node to the starting point of the path to obtain the driving path from the starting point of the path to the end point of the path.

[0044] In one possible implementation, the fifth determination module is used to, for the first neighbor node, use the distance between the starting point of the path and the first neighbor node as the target distance, and use the first neighbor node as the target neighbor node; for the next neighbor node, if the distance between the starting point of the path and the next neighbor node is less than the target distance, update the target distance to the distance between the starting point of the path and the next neighbor node, and update the target neighbor node to the next neighbor node, and so on, until the multiple neighbor nodes are determined and the target neighbor node is obtained.

[0045] In another possible implementation, the fifth determination module is configured to determine, for a first neighbor node, a first quality parameter value based on the distance between the path starting point and the first neighbor node and the time required for the autonomous vehicle to travel the distance, where the first quality parameter value is used to indicate the quality of the first neighbor node as a path node, the first quality parameter value is used as the target quality parameter value, and the first neighbor node is used as the target neighbor node; and for a next neighbor node, determine, based on the distance between the path starting point and the next neighbor node and the time required for the autonomous vehicle to travel the distance, a second quality parameter value, where the second quality parameter value is used to indicate the quality of the next neighbor node as a path node, and if the second quality parameter value is greater than the target quality parameter value, update the target quality parameter value to the second quality parameter value, and update the target neighbor node to the next neighbor node, and so on, until all the multiple neighbor nodes are determined and the target neighbor node is obtained.

[0046] In another possible implementation, the fifth determination module is used to determine, for the first neighbor node, a third quality parameter value based on the distance between the path starting point and the first neighbor node and the safety factor of the autonomous driving vehicle passing through the first neighbor node, the third quality parameter value being used to indicate the quality of the first neighbor node as a path node, the third quality parameter value being used as the target quality parameter value, and the first neighbor node being used as the target neighbor node; for the next neighbor node, based on the distance between the path starting point and the next neighbor node and the safety factor of the autonomous driving vehicle passing through the next neighbor node, a fourth quality parameter value being used to indicate the quality of the next neighbor node as a path node, and if the fourth quality parameter value is greater than the target quality parameter value, the target quality parameter value is updated to the fourth quality parameter value, and the target neighbor node is updated to the next neighbor node, and so on, until the multiple neighbor nodes are determined and the target neighbor node is obtained.

[0047] In another possible implementation, the first determination module is used to enable an endpoint recognition function of the autonomous vehicle; while the driver is driving the autonomous vehicle, the body sensor of the autonomous vehicle is enabled through the endpoint recognition function; first environmental data of the autonomous vehicle is obtained through the body sensor; based on the first environmental data, the parking endpoint of the autonomous vehicle is determined, and the parking endpoint is used as the path endpoint of the autonomous vehicle.

[0048] In another possible implementation, the third determination module is used to obtain second environmental data of the first target node; when the second environmental data is used to indicate that there is an obstacle around the first target node, the obstacle direction of the obstacle at the first target node is determined based on the second environmental data; based on the obstacle direction, the pathfinding direction of the autonomous driving vehicle is determined; based on the pathfinding direction, multiple neighbor nodes of the first target node are determined from the node set, and the multiple neighbor nodes are located in the pathfinding direction of the first target node.

[0049] On the other hand, a vehicle-mounted terminal is provided, which includes a processor and a memory, wherein the memory stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the above-mentioned vehicle path planning method.

[0050] On the other hand, a computer-readable storage medium is provided, in which at least one program code is stored. The at least one program code is loaded and executed by a processor to implement the above-mentioned vehicle path planning method.

[0051] On the other hand, a computer program product is provided, wherein the product stores at least one program code, and the at least one program code is used to be executed by a processor to implement the above-mentioned vehicle path planning method.

[0052] In an embodiment of the present application, when determining the driving path from the starting point of the path to the end point of the path, the starting point of the path is first used as a reference node, the first target node is determined based on the reference node, and the target neighbor node is determined based on the first target node. In this way, part of the driving path is determined as the reference node-first target node-target neighbor node, and then the target neighbor node is used as the reference node, and the above process is performed again until the end point of the path is found; it can be seen that the embodiment of the present application is to evaluate each path node to select the best position and then perform the next search until the end point of the path is found, that is, the embodiment of the present application uses a heuristic search algorithm to plan the driving path, which can effectively omit a large number of unnecessary driving paths, thereby improving the planning efficiency of the driving path.

[0053] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a schematic diagram of an implementation environment of a vehicle path planning method according to an exemplary embodiment of the present application;

[0055] Figure 2 is a flow chart of a vehicle path planning method shown in an exemplary embodiment of the present application;

[0056] Figure 3 is a schematic diagram of a vehicle path planning method shown in an exemplary embodiment of the present application;

[0057] Figure 4 is a flow chart of a vehicle path planning method shown in an exemplary embodiment of the present application;

[0058] Figure 5 is a schematic diagram of a vehicle path planning method shown in an exemplary embodiment of the present application;

[0059] Figure 6 is a flow chart of a vehicle path planning method shown in an exemplary embodiment of the present application;

[0060] Figure 7 is a flow chart of a vehicle path planning method shown in an exemplary embodiment of the present application;

[0061] Figure 8 is a block diagram of a vehicle path planning device shown in an exemplary embodiment of the present application;

[0062] Figure 9 It is a block diagram of a vehicle-mounted terminal shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the technical solutions and advantages of the present application clearer, the implementation methods of the present application are described in further detail below.

[0064] The terms "first," "second," "third," and "fourth," etc. in the specification and claims of this application and the accompanying drawings are used to distinguish different objects, not to describe a specific order. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0065] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all 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 the relevant countries and regions. For example, the path starting point, path end point and multiple candidate path nodes involved in this application are all obtained with full authorization.

[0066] Please refer to Figure 1 , which shows a schematic diagram of an implementation environment for a vehicle path planning method according to an exemplary embodiment of the present application. The implementation environment includes an onboard terminal 10 and an autonomous vehicle 20. The onboard terminal 10 is used to plan a driving path for the autonomous vehicle 20 and then control the autonomous vehicle 20 to drive autonomously according to the planned driving path.

[0067] In one possible implementation, the vehicle-mounted terminal 10 determines a route start point and a route end point, and based on the route start point and the route end point, determines a driving route from the route start point to the route end point. The driving end point can be the destination to which the autonomous vehicle is traveling; for example, the route end point can be a parking lot, a shopping mall entrance, a residential building entrance, a train station, a high-speed rail station, or an airport, or any other location to which the user is traveling.

[0068] In one possible implementation, the path endpoint is set by the user, that is, the vehicle-mounted endpoint 10 determines the path endpoint set by the user; in other embodiments, the path endpoint is automatically acquired by the autonomous driving vehicle 20 with the aid of ultrasonic parking radar, panoramic imaging, lidar, and millimeter-wave radar, and transmitted to the vehicle-mounted terminal 10; accordingly, the autonomous driving vehicle 10 is any vehicle equipped with an ultrasonic parking radar assistance system, a panoramic imaging system, a lidar system, and a millimeter-wave radar system; and the type of the autonomous driving vehicle 20 can be a pure electric vehicle, a hybrid vehicle, or a fuel vehicle, etc., without specific limitation.

[0069] Please refer to Figure 2 , which shows a flow chart of a vehicle path planning method according to an exemplary embodiment of the present application. Figure 2 , the method comprising:

[0070] Step 201: Determine the path starting point, path ending point, and multiple candidate path nodes of the autonomous driving vehicle.

[0071] The path starting point is the starting point of the autonomous vehicle's travel; for example, the path starting point is the current location of the autonomous vehicle, or the path starting point is the starting point set by the user. The path end point is the destination that the autonomous vehicle is heading to. For example, the path end point can be a parking lot, a shopping mall entrance, a residential complex entrance, a train station, a high-speed rail station, or an airport, any other location that the user wants to go to. The multiple candidate path nodes are nodes that may be passed from the path starting point to the path end point; and the step of determining the multiple candidate path nodes can be: determining multiple driving paths from the path starting point to the path end point, and sampling the nodes in the multiple driving paths to obtain multiple candidate path nodes; the multiple driving paths can be multiple driving paths determined by navigation based on the path starting point and the path end point.

[0072] In one possible implementation, the path endpoint is manually set by the user; accordingly, the step of determining the path endpoint of the autonomous vehicle may be: displaying a map interface, the map interface including an input box, and obtaining the path endpoint entered in the input box; or displaying a map interface and obtaining the path endpoint marked on the map interface, thereby enabling the user to manually set the path endpoint based on the map interface, thereby improving the flexibility of setting the path endpoint.

[0073] In another possible implementation, the path endpoint is automatically determined by the autonomous vehicle; accordingly, the step of determining the path endpoint of the autonomous vehicle on Penguin Island can be implemented by following the steps (1) to (5), including:

[0074] (1) Enable the endpoint recognition function of the autonomous vehicle.

[0075] In one possible implementation, the driver manually triggers the start of the autonomous vehicle's destination recognition function through the human-computer interaction module; accordingly, this step may be: displaying a setting interface, the setting interface including an on button and an off button for the autonomous vehicle's destination recognition function, the on button being used to start the destination recognition function, and the off button being used to stop the destination recognition function; at this time, the driver can click the on button to trigger the start of the destination recognition function; in response to the on button being triggered, the autonomous vehicle's destination recognition function is turned on, thereby enabling the user to manually start the autonomous vehicle's destination recognition function based on the setting interface, thereby improving the flexibility of starting the destination recognition function. For example, please refer to Figure 3 The driver clicks the start button, and the autonomous vehicle searches for the end of the path. When the end of the path is found, it tracks the path and then drives based on the tracked path to reach the end of the path.

[0076] In another possible implementation, the vehicle-mounted terminal can automatically enable the autonomous vehicle's destination recognition function. Furthermore, the vehicle-mounted terminal can automatically enable the destination recognition function when the autonomous vehicle is started and automatically disable the destination recognition function when the autonomous vehicle is turned off. Alternatively, the vehicle-mounted terminal can automatically enable the destination recognition function when the autonomous vehicle meets the conditions for enabling the destination recognition function and keep the destination recognition function disabled when the conditions for enabling the destination recognition function are not met.

[0077] Among them, if the autonomous driving car is parked in the same parking lot multiple times, it means that the parking lot is the permanent residence of the autonomous driving car; for example, the parking lot may be a unit parking lot or a home garage. In this scenario, the end point recognition function can be turned on to identify the end point of the path, and then the autonomous driving car can automatically park based on the end point of the path; accordingly, the step for the on-board terminal to determine whether the autonomous driving car meets the conditions for starting the end point recognition function can be: the on-board terminal determines the number of times the autonomous driving car has been parked in the same parking lot within a first preset time period closest to the current time. If the number exceeds the first preset number, it is determined that the autonomous driving car meets the conditions for starting the end point recognition function; if the number does not exceed the first preset number, it is determined that the autonomous driving car does not meet the conditions for starting the end point recognition function.

[0078] The autonomous driving car has an autonomous driving function. When the driver uses the autonomous driving function multiple times, it indicates that the end point of the path needs to be identified and then autonomous driving needs to be performed. Accordingly, the step for the on-board terminal to determine whether the autonomous driving car meets the conditions for starting the end point identification function can be: the on-board terminal determines the number of times the autonomous driving car uses the autonomous driving function within a second preset time period closest to the current time. If the number exceeds the second preset number, it is determined that the autonomous driving car meets the conditions for starting the end point identification function; if the number does not exceed the second preset number, it is determined that the autonomous driving car does not meet the conditions for starting the end point identification function.

[0079] In an embodiment of the present application, the endpoint recognition function of the autonomous driving vehicle is automatically turned on by the vehicle-mounted terminal, so that the driver does not need to operate manually, which not only improves the driver's driving experience, but also improves the driver's safety in driving the autonomous driving vehicle.

[0080] (2) While the driver is driving the autonomous vehicle, the vehicle body sensors of the autonomous vehicle are activated through the endpoint recognition function.

[0081] The vehicle body sensors include ultrasonic parking radar, panoramic image, laser radar and millimeter wave radar. After the vehicle terminal turns on the vehicle body sensors of the autonomous vehicle, the autonomous vehicle enters the endpoint search phase, and executes step (3) in the endpoint search phase.

[0082] (3) Obtain the first environmental data of the autonomous vehicle through the vehicle body sensors.

[0083] The first environmental data is environmental data surrounding the autonomous vehicle. In this embodiment of the present application, the endpoint of the path may be a parking terminal. The first environmental data includes parking space data in the parking lot. The parking space data includes the location of the parking space and the parking status of the parking space. The parking status of the parking space may be parked or not parked.

[0084] (4) Determine a parking destination of the autonomous vehicle based on the first environmental data.

[0085] Based on the first environmental data, an unparked target parking space is determined, and the location of the unparked target parking space is determined as the parking destination. There may be multiple unparked parking spaces. Based on the first environmental data, at least one unparked parking space is first determined, and the target parking space is determined from the at least one unparked parking space.

[0086] In a possible implementation, a target parking space may be randomly selected; accordingly, the step of determining the target parking space from at least one unparked parking space may be: randomly selecting a parking space from at least one unparked parking space as the target parking space.

[0087] In another possible implementation, a parking space where the driver frequently parks can be selected; accordingly, the step of determining the target parking space from at least one unparked parking space can be: determining the number of times the autonomous driving vehicle has parked in each unparked parking space, and based on the number of times the autonomous driving vehicle has parked in each unparked parking space, selecting the target parking space with the greatest number of parking times from the at least one unparked parking space.

[0088] In another possible implementation, a parking space that is relatively easy to park may be selected. The parking space that is relatively easy to park may be one where no parking spaces are parked on both sides or one side. Accordingly, the step of determining the target parking space from at least one unparked parking space may be: determining the parking difficulty of each unparked parking space, and based on the parking difficulty of each unparked parking space, determining the target parking space with the lowest parking difficulty from each unparked parking space.

[0089] In another possible implementation, the target parking space can be selected based on a combination of the number of parking attempts and the parking difficulty. Accordingly, the step of determining the target parking space from the at least one unparked parking space may include: determining the number of parking attempts and the parking difficulty of each unparked parking space by the autonomous vehicle; determining a first parking probability for each parking space based on the number of parking attempts and the parking difficulty of each unparked space; and selecting the target parking space with the highest first parking probability from the at least one unparked parking space based on the first parking probability of each parking space. For example, for any parking space, the first parking probability of the parking space is obtained by taking a weighted sum of the number of parking attempts and the parking difficulty. A higher first parking probability indicates a more suitable parking space.

[0090] In another possible implementation, a parking space close to an office or home can be selected. Accordingly, the step of determining a target parking space from the at least one unparked parking space may include determining the distance from each unparked parking space to a target location, and then determining the closest target parking space from the at least one unparked parking space based on the distance from each unparked parking space to the target location. The target location may be a location that the driver needs to go to after parking the autonomous vehicle; for example, if the driver drives to and from get off work every day, the target location may be the office or home.

[0091] In another possible implementation, a target parking space can be selected based on a combination of parking difficulty and distance. Accordingly, the step of determining a target parking space from the at least one unparked parking space may include: determining the parking difficulty and distance from the target location for each unparked parking space for the autonomous vehicle; determining a second parking probability for each unparked parking space based on the parking difficulty and distance from the target location; and selecting the target parking space with the highest second parking probability from the at least one unparked parking space based on the second parking probability for each parking space. For example, for any parking space, the second parking probability for that space is obtained by taking a weighted sum of the parking difficulty and distance for that space; a higher second parking probability for a particular space indicates a more suitable parking space.

[0092] In another possible implementation, the driver can rent or purchase a parking space, and the autonomous driving car has a fixed parking space; accordingly, the step of determining the target parking space from at least one undocked parking space may be: determining a marked target parking space from at least one undocked parking space, and the marked target parking space may be a parking space rented or purchased by the driver.

[0093] (5) The parking destination is used as the path destination of the autonomous vehicle.

[0094] It should be noted that steps (1) to (5) are steps performed before executing path planning, and after the path endpoint is determined based on steps (1) to (5), the path endpoint is stored; when performing path planning, the stored path endpoint is directly obtained.

[0095] Step 202: The path endpoint and multiple candidate path nodes are combined into a node set.

[0096] The node combination is used to determine the vehicle terminal to determine the driving path from the path starting point to the path end point

[0097] Step 203: Use the path starting point as a reference node.

[0098] One thing that needs to be explained is that in step 202, the path starting point can also be added to the node set, and then the distance between the path starting point and the path starting point is set to 0, and the distance between the path end point and the path starting point and the distance between multiple candidate path nodes and the path starting point are set to infinity; in this step, the node with the smallest distance to the path starting point is selected from the node set, and the selected node is used as the reference node, and the selected node is the path starting point.

[0099] Another point that needs to be explained is that there is no strict time sequence between step 202 and step 203. Step 202 may be performed first, and then step 203; or step 203 may be performed first, and then step 202.

[0100] Step 204: Based on the reference node, determine a first target node from the node set, and delete the first target node from the node set. The first target node is the node closest to the reference node.

[0101] In an embodiment of the present application, the driving path is determined based on a shortest path algorithm, i.e., in this step, the node closest to the reference node is selected. Accordingly, this step may include determining the distance between each node in the node set and the reference node, and then determining the first target node closest to the node set based on the distance between each node and the reference node. Because the driving path is determined based on the shortest path algorithm, the determined driving path is the shortest, saving energy (electricity or oil) for the autonomous vehicle.

[0102] Step 205: Based on the first target node, determine a plurality of neighbor nodes of the first target node from the node set.

[0103] A neighbor node refers to a node whose distance to the first target node is less than a preset distance; in one possible implementation, the neighbor node is selected based on the distance between each node in the node set and the first target node; accordingly, this step can be: based on the first target node, determine the distance between each node in the node set and the first target node; based on the distance between each node in the node set and the first target node, determine from the node set multiple nodes whose distance is less than a preset distance, and the determined multiple nodes are the multiple neighbor nodes of the first target node.

[0104] In another possible implementation, multiple neighbor nodes are comprehensively determined based on the distance between each node in the node set and the first target node, and with reference to whether there are obstacles around the first target node. Accordingly, this step can be implemented by the following steps (1) to (4), including:

[0105] (1) Obtain the second environment data of the first target node.

[0106] The second environmental data is environmental data around the first target node, and the second environmental data is an image around the first target node; accordingly, in this step, the vehicle-mounted terminal captures the environment around the first target node through panoramic imaging to obtain the second environmental data.

[0107] After the vehicle terminal determines the second environmental data, it determines whether there are obstacles around the first target node based on the second environmental data; if there are obstacles around the first target node, step (2) is performed; if there are no obstacles around the first target node, the distance between each node in the node set and the first target node is determined based on the first target node; based on the distance between each node in the node set and the first target node, multiple nodes whose distance is less than a preset distance are determined from the node set, and the multiple nodes determined are multiple neighboring nodes of the first target node. The vehicle terminal determines whether there are obstacles around the first target node by an image recognition method.

[0108] (2) When the second environment data indicates that an obstacle exists around the first target node, an obstacle direction of the obstacle at the first target node is determined based on the second environment data.

[0109] The obstacle direction is the direction of the obstacle at the first target node;

[0110] (3) Determine the path-finding direction of the autonomous vehicle based on the obstacle direction.

[0111] The pathfinding direction is the opposite direction of the obstacle direction; for example, if the obstacle is on the left side of the first target node, the obstacle direction is left and the pathfinding direction is right.

[0112] (4) Based on the path finding direction, determine multiple neighbor nodes of the first target node from the node set, and the multiple neighbor nodes are located in the path finding direction of the first target node.

[0113] Based on the first target node, determine the distance between each node in the node set and the first target node; based on the distance between each node in the node set and the first target node, based on the routing direction and the distance between each node and the first target node, determine from the node set multiple nodes whose distance is less than a preset distance and are located in the routing direction, and the determined multiple nodes are the multiple neighbor nodes of the first target node.

[0114] In an embodiment of the present application, if there is an obstacle on one side of the first target node, even if it is oblique to the obstacle node, its path-finding direction cannot be set to an oblique direction, that is, the path-finding direction is set to the opposite direction of the obstacle direction, thereby avoiding the problem of collision between the autonomous driving car and the obstacle, thereby improving the safety of the autonomous driving car.

[0115] Step 206: Determine the distance between the reference node and each neighbor node respectively.

[0116] For any neighbor node, the steps of determining the distance between the reference node and the neighbor node can be: determining the first distance between the reference node and the first target node, determining the second distance between the first target node and the neighbor node, and determining the sum of the first distance and the second distance to obtain the distance between the reference node and the neighbor node.

[0117] Step 207: Based on the distance between the reference node and each neighbor node, determine the target neighbor node, and use the target neighbor node as a predecessor node of the first target node.

[0118] The target neighbor node serves as the predecessor node of the first target node, and the determined partial driving path is the first target node-target neighbor node.

[0119] Step 208: Take the target neighbor node as a reference node, and then perform the step of determining the first target node from the node set based on the reference node until the node set is empty or the first target node is the end point of the path.

[0120] When the node set is empty or the first target node is the end point of the path, it means that the path planning has been completed, and the predecessor node of the determined first target node (one first target node is determined each time) is found. The driving path can be determined by backtracing the predecessor node through step 209.

[0121] Step 209: Starting from the end point of the path, trace back along the predecessor node to the starting point of the path to obtain the driving path from the starting point to the end point of the path.

[0122] For example, the path node is node 0, and the path end point is node n. The first target node determined for the first time is node 1, and the target neighbor node determined is node 2. The first target node determined for the second time is node 3, and the target neighbor node determined is node 4. The first target node determined for the third time is node 5, and the target neighbor node determined is node n. Then the backtracking path from node n to node 0 is node n-node 5-node 4-node 3-node 2-node 1-node 0. The reverse path of the backtracking path is the driving path, that is, the driving path is node 0-node 1-node 2-node 3-node 4-node 5-node n. The determined driving path is as follows: Figure 3 shown.

[0123] After the on-board terminal determines the driving path, the controller of the autonomous vehicle outputs the control strategy corresponding to the driving path to the actuator to perform vehicle tracking manipulation, so that the autonomous vehicle can travel along the path to the end of the path.

[0124] In an embodiment of the present application, when determining the driving path from the starting point of the path to the end point of the path, the starting point of the path is first used as a reference node, the first target node is determined based on the reference node, and the target neighbor node is determined based on the first target node. In this way, part of the driving path is determined as the reference node-first target node-target neighbor node, and then the target neighbor node is used as the reference node, and the above process is performed again until the end point of the path is found; it can be seen that the embodiment of the present application is to evaluate each path node to select the best position and then perform the next search until the end point of the path is found, that is, the embodiment of the present application uses a heuristic search algorithm to plan the driving path, which can effectively omit a large number of unnecessary driving paths, thereby improving the planning efficiency of the driving path.

[0125] Please refer to Figure 4 , which shows a flow chart of a vehicle path planning method according to an exemplary embodiment of the present application. Figure 4 , the method comprising:

[0126] Step 401: The vehicle-mounted terminal determines the path starting point, path ending point and multiple candidate path nodes of the autonomous driving vehicle.

[0127] In some embodiments, this step is the same as step 201 and will not be repeated here.

[0128] Step 402: The vehicle-mounted terminal groups the path endpoint and multiple candidate path nodes into a node set.

[0129] In some embodiments, this step is the same as step 202 and will not be repeated here.

[0130] Step 403: The vehicle-mounted terminal uses the starting point of the path as a reference node.

[0131] In some embodiments, this step is the same as step 203 and will not be repeated here.

[0132] Step 404: The vehicle-mounted terminal determines a first target node from the node set based on the reference node, and deletes the first target node from the node set. The first target node is the node closest to the reference node.

[0133] In some embodiments, this step is the same as step 204 and will not be repeated here.

[0134] Step 405: The vehicle-mounted terminal determines a plurality of neighbor nodes of the first target node from the node set based on the first target node.

[0135] In some embodiments, this step is the same as step 205 and will not be repeated here.

[0136] Step 406: The vehicle-mounted terminal determines the distance between the reference node and each neighbor node respectively.

[0137] In some embodiments, this step is the same as step 206 and will not be repeated here.

[0138] Step 407: For the first neighbor node, the vehicle-mounted terminal uses the distance between the starting point of the path and the first neighbor node as the target distance, and uses the first neighbor node as the target neighbor node.

[0139] The vehicle-mounted terminal sorts the multiple neighbor nodes to obtain an order of the multiple neighbor nodes; and then executes steps 407 and 408 based on the order of the multiple neighbor nodes.

[0140] Step 408: For the next neighbor node, when the distance between the starting point of the path and the next neighbor node is less than the target distance, the vehicle terminal updates the target distance to the distance between the starting point of the path and the next neighbor node, and updates the target neighbor node to the next neighbor node, and so on, until multiple neighbor nodes are determined and the target neighbor node is obtained.

[0141] When the distance between the path start point and the next neighbor node is greater than the target distance, the vehicle terminal keeps the target distance and the target neighbor node unchanged, that is, the target distance is still the distance between the path start point and the first neighbor node, and the target neighbor node is still the first neighbor node.

[0142] After the vehicle terminal completes processing the next neighbor node, it then determines the distance between the path starting point and the next neighbor node. If the distance between the path starting point and the next neighbor node is less than the target distance, the vehicle terminal updates the target distance to the distance between the path starting point and the next neighbor node, and updates the target neighbor node to the next neighbor node, and so on, until multiple neighbor nodes are determined and the target neighbor node is obtained.

[0143] Step 409: The vehicle-mounted terminal uses the target neighbor node as the predecessor node of the first target node.

[0144] In some embodiments, this step is the same as step 207 and will not be repeated here.

[0145] Step 410: The vehicle-mounted terminal uses the target neighbor node as a reference node, and then executes the step of determining the first target node from the node set based on the reference node until the node set is empty or the first target node is the end point of the path.

[0146] In some embodiments, this step is the same as step 208 and will not be repeated here.

[0147] Step 411: The vehicle-mounted terminal starts from the end point of the path and traces back along the predecessor node to the starting point of the path to obtain the driving path from the starting point to the end point of the path.

[0148] In some embodiments, this step is the same as step 209 and will not be repeated here.

[0149] In an embodiment of the present application, when determining the driving path from the starting point of the path to the end point of the path, the starting point of the path is first used as a reference node, the first target node is determined based on the reference node, and the target neighbor node is determined based on the first target node. In this way, part of the driving path is determined as the reference node-first target node-target neighbor node, and then the target neighbor node is used as the reference node, and the above process is performed again until the end point of the path is found; it can be seen that the embodiment of the present application is to evaluate each path node to select the best position and then perform the next search until the end point of the path is found, that is, the embodiment of the present application uses a heuristic search algorithm to plan the driving path, which can effectively omit a large number of unnecessary driving paths, thereby improving the planning efficiency of the driving path.

[0150] Please refer to Figure 6 , which shows a flow chart of a vehicle path planning method according to an exemplary embodiment of the present application. Figure 6 , the method comprising:

[0151] Step 601: The vehicle terminal determines the path starting point, path ending point and multiple candidate path nodes of the autonomous driving vehicle.

[0152] In some embodiments, this step is the same as step 201 and will not be repeated here.

[0153] Step 602: The vehicle-mounted terminal combines the path endpoint and multiple candidate path nodes into a node set.

[0154] In some embodiments, this step is the same as step 202 and will not be repeated here.

[0155] Step 603: The vehicle-mounted terminal uses the starting point of the path as a reference node.

[0156] In some embodiments, this step is the same as step 203 and will not be repeated here.

[0157] Step 604: The vehicle-mounted terminal determines a first target node from the node set based on the reference node, and deletes the first target node from the node set. The first target node is the node closest to the reference node.

[0158] In some embodiments, this step is the same as step 204 and will not be repeated here.

[0159] Step 605: The vehicle-mounted terminal determines a plurality of neighbor nodes of the first target node from the node set based on the first target node.

[0160] In some embodiments, this step is the same as step 205 and will not be repeated here.

[0161] Step 606: The vehicle-mounted terminal determines the distance between the reference node and each neighbor node respectively.

[0162] In some embodiments, this step is the same as step 206 and will not be repeated here.

[0163] Step 607: For the first neighbor node, the vehicle terminal determines a first quality parameter value based on the distance between the starting point of the path and the first neighbor node and the time required for the autonomous driving vehicle to travel the distance. The first quality parameter value is used to represent the quality of the first neighbor node as a path node, the first quality parameter value is used as the target quality parameter value, and the first neighbor node is used as the target neighbor node.

[0164] The on-board terminal performs a weighted summation of the distance between the starting point of the path to the first neighbor node and the time required for the autonomous driving vehicle to travel the distance to obtain a first quality parameter value.

[0165] Step 608: For the next neighbor node, a second quality parameter value is determined based on the distance between the starting point of the path and the next neighbor node and the time required for the autonomous vehicle to travel the distance. The second quality parameter value is used to represent the quality of the next neighbor node as a path node. When the second quality parameter value is greater than the first quality parameter value, the target quality parameter value is updated to the second quality parameter value, and the target neighbor node is updated to the next neighbor node. This process is repeated until multiple neighbor nodes are determined and the target neighbor node is obtained.

[0166] The vehicle terminal calculates a second quality parameter value by weightedly summing the distance from the path start point to the next neighbor node and the time required for the autonomous vehicle to travel that distance. If the second quality parameter value is not greater than the target quality parameter value, the vehicle terminal maintains the target quality parameter value and the target neighbor node unchanged. In other words, the target distance remains the distance from the path start point to the first neighbor node, and the target neighbor node remains the first neighbor node.

[0167] After the vehicle terminal completes processing the next neighbor node, it then determines the fifth quality parameter value based on the distance between the starting point of the path to the next neighbor node and the time required for the autonomous driving vehicle to travel that distance; if the fifth quality parameter value is greater than the target quality parameter value, the target quality parameter value is updated to the fifth quality parameter value, and the target neighbor node is updated to the next neighbor node, and so on, until multiple neighbor nodes are determined and the target neighbor node is obtained.

[0168] Step 609: The vehicle-mounted terminal uses the target neighbor node as the predecessor node of the first target node.

[0169] In some embodiments, this step is the same as step 207 and will not be repeated here.

[0170] Step 610: The vehicle-mounted terminal takes the target neighbor node as a reference node, and then executes the step of determining the first target node from the node set based on the reference node until the node set is empty or the first target node is the end point of the path.

[0171] In some embodiments, this step is the same as step 208 and will not be repeated here.

[0172] Step 611: The vehicle-mounted terminal starts from the end point of the path and traces back along the predecessor node to the starting point of the path to obtain the driving path from the starting point to the end point of the path.

[0173] In some embodiments, this step is the same as step 209 and will not be repeated here.

[0174] In an embodiment of the present application, when determining the driving path from the starting point of the path to the end point of the path, the starting point of the path is first used as a reference node, the first target node is determined based on the reference node, and the target neighbor node is determined based on the first target node. In this way, part of the driving path is determined as the reference node-first target node-target neighbor node, and then the target neighbor node is used as the reference node, and the above process is performed again until the end point of the path is found; it can be seen that the embodiment of the present application is to evaluate each path node to select the best position and then perform the next search until the end point of the path is found, that is, the embodiment of the present application uses a heuristic search algorithm to plan the driving path, which can effectively omit a large number of unnecessary driving paths, thereby improving the planning efficiency of the driving path.

[0175] Please refer to Figure 7 , which shows a flow chart of a vehicle path planning method according to an exemplary embodiment of the present application. Figure 7 , the method comprising:

[0176] Step 701: The vehicle terminal determines the path starting point, path ending point and multiple candidate path nodes of the autonomous driving vehicle.

[0177] In some embodiments, this step is the same as step 201 and will not be repeated here.

[0178] Step 702: The vehicle-mounted terminal combines the path endpoint and multiple candidate path nodes into a node set.

[0179] In some embodiments, this step is the same as step 202 and will not be repeated here.

[0180] Step 703: The vehicle-mounted terminal uses the starting point of the path as a reference node.

[0181] In some embodiments, this step is the same as step 203 and will not be repeated here.

[0182] Step 704: The vehicle-mounted terminal determines a first target node from the node set based on the reference node, and deletes the first target node from the node set. The first target node is the node closest to the reference node.

[0183] In some embodiments, this step is the same as step 204 and will not be repeated here.

[0184] Step 705: The vehicle-mounted terminal determines a plurality of neighbor nodes of the first target node from the node set based on the first target node.

[0185] In some embodiments, this step is the same as step 205 and will not be repeated here.

[0186] Step 706: The vehicle-mounted terminal determines the distance between the reference node and each neighbor node respectively.

[0187] In some embodiments, this step is the same as step 206 and will not be repeated here.

[0188] Step 707: For the first neighbor node, the vehicle terminal determines a third quality parameter value based on the distance between the starting point of the path and the first neighbor node and the safety factor of the autonomous driving vehicle passing through the first neighbor node. The third quality parameter value is used to represent the quality of the first neighbor node as a path node, the third quality parameter value is used as the target quality parameter value, and the first neighbor node is used as the target neighbor node.

[0189] The safety factor of the autonomous vehicle passing the first neighboring node is used to indicate the safety of the autonomous vehicle passing the first neighboring node. The vehicle-mounted terminal performs a weighted summation of the distance between the path node and the first neighboring node and the safety factor of the autonomous vehicle passing the first neighboring node to obtain a third quality parameter value.

[0190] In one possible implementation, the vehicle-mounted terminal may determine a safety factor based on road condition information. Accordingly, the step of determining the safety factor for the autonomous vehicle passing the first neighbor node by the vehicle-mounted terminal may include: the vehicle-mounted terminal determines road condition information from the path starting point to the first neighbor node, and based on the road condition information, determines the safety factor for the autonomous vehicle passing the first neighbor node. For example, the road condition information may indicate the smoothness of the driving path from the path starting point to the first neighbor node; and based on the smoothness, a safety factor corresponding to the smoothness is determined. For another example, the road condition information may indicate the average width of the driving path from the path starting point to the first neighbor node; and based on the average width, a safety factor corresponding to the average width is determined. For another example, the road condition information may indicate the average number of lanes in the driving path from the path starting point to the first neighbor node; and based on the average number of lanes, a safety factor corresponding to the average number of lanes is determined. For another example, the road condition information may indicate the number of intersections in the driving path from the path starting point to the first neighbor node; and based on the number of intersections, a safety factor corresponding to the number of intersections is determined. For another example, the road condition information is used to represent the number of traffic accidents that occurred in the history of the driving path from the starting point of the path to the first neighbor node, and a safety factor matching the number is obtained based on the number.

[0191] Step 708: For the next neighbor node, a fourth quality parameter value is determined based on the distance between the starting point of the path and the next neighbor node and the safety factor of the autonomous vehicle passing through the next neighbor node. The fourth quality parameter value is used to represent the quality of the next neighbor node as a path node. When the fourth quality parameter value is greater than the target quality parameter value, the target quality parameter value is updated to the fourth quality parameter value, and the target neighbor node is updated to the next neighbor node. This process is repeated until multiple neighbor nodes are determined and the target neighbor node is obtained.

[0192] The vehicle terminal calculates a fourth quality parameter value by weightedly adding the distance from the path start point to the next neighbor node and the safety factor of the autonomous vehicle passing the next neighbor node. If the fourth quality parameter value is not greater than the target quality parameter value, the vehicle terminal maintains the target quality parameter value and the target neighbor node unchanged. Specifically, the target distance remains the distance from the path start point to the first neighbor node, and the target neighbor node remains the first neighbor node.

[0193] After the vehicle terminal completes processing the next neighbor node, it determines the sixth quality parameter value based on the distance between the path starting point and the next neighbor node and the safety factor of the autonomous driving vehicle passing the next neighbor node; when the sixth quality parameter value is greater than the target quality parameter value, the target quality parameter value is updated to the sixth quality parameter value, and the target neighbor node is updated to the next neighbor node, and so on, until multiple neighbor nodes are determined and the target neighbor node is obtained.

[0194] Step 709: The vehicle-mounted terminal uses the target neighbor node as the predecessor node of the first target node.

[0195] In some embodiments, this step is the same as step 207 and will not be repeated here.

[0196] Step 710: The vehicle-mounted terminal takes the target neighbor node as a reference node, and then executes the step of determining the first target node from the node set based on the reference node until the node set is empty or the first target node is the end point of the path.

[0197] In some embodiments, this step is the same as step 208 and will not be repeated here.

[0198] Step 711: The vehicle-mounted terminal starts from the end point of the path and traces back along the predecessor node to the starting point of the path to obtain the driving path from the starting point to the end point of the path.

[0199] In some embodiments, this step is the same as step 209 and will not be repeated here.

[0200] In an embodiment of the present application, when determining the driving path from the starting point of the path to the end point of the path, the starting point of the path is first used as a reference node, the first target node is determined based on the reference node, and the target neighbor node is determined based on the first target node. In this way, part of the driving path is determined as the reference node-first target node-target neighbor node, and then the target neighbor node is used as the reference node, and the above process is performed again until the end point of the path is found; it can be seen that the embodiment of the present application is to evaluate each path node to select the best position and then perform the next search until the end point of the path is found, that is, the embodiment of the present application uses a heuristic search algorithm to plan the driving path, which can effectively omit a large number of unnecessary driving paths, thereby improving the planning efficiency of the driving path.

[0201] Please refer to Figure 8 , which shows a block diagram of a vehicle path planning device according to an exemplary embodiment of the present application. The device includes:

[0202] A first determination module 801 is configured to determine a path starting point, a path ending point, and a plurality of candidate path nodes of the autonomous driving vehicle;

[0203] A forming module 802 is used to form a node set by combining a path endpoint and a plurality of candidate path nodes;

[0204] As module 803, it is used to take the starting point of the path as a reference node;

[0205] A second determining module 804 is configured to determine a first target node from the node set based on the reference node, and delete the first target node from the node set, where the first target node is the node closest to the reference node;

[0206] A third determining module 805 is configured to determine, based on the first target node, a plurality of neighboring nodes of the first target node from the node set;

[0207] A fourth determining module 806 is configured to determine the distance between the reference node and each neighboring node respectively;

[0208] A fifth determining module 807 is configured to determine a target neighboring node based on a distance between the reference node and each neighboring node, and use the target neighboring node as a predecessor node of the first target node;

[0209] As module 803, it is also used to use the target neighbor node as a reference node;

[0210] The second determining module 804 is further configured to determine a first target node from the node set based on the reference node until the node set is empty or the first target node is the end point of the path;

[0211] The backtracking module 808 is configured to start from the end point of the path and backtrack along the predecessor node to the starting point of the path to obtain the driving path from the starting point of the path to the end point of the path.

[0212] In one possible implementation, the fifth determination module 807 is used to, for the first neighbor node, use the distance between the starting point of the path to the first neighbor node as the target distance, and use the first neighbor node as the target neighbor node; for the next neighbor node, when the distance between the starting point of the path to the next neighbor node is less than the target distance, update the target distance to the distance between the starting point of the path to the next neighbor node, and update the target neighbor node to the next neighbor node, and so on, until multiple neighbor nodes are determined and the target neighbor node is obtained.

[0213] In another possible implementation, the fifth determination module 807 is configured to determine, for the first neighbor node, a first quality parameter value based on the distance between the path starting point and the first neighbor node and the time required for the autonomous vehicle to travel the distance, the first quality parameter value being used to indicate the quality of the first neighbor node as a path node, the first quality parameter value being used as the target quality parameter value, and the first neighbor node being used as the target neighbor node; and for the next neighbor node, a second quality parameter value being determined based on the distance between the path starting point and the next neighbor node and the time required for the autonomous vehicle to travel the distance, the second quality parameter value being used to indicate the quality of the next neighbor node as a path node, and if the second quality parameter value is greater than the target quality parameter value, the target quality parameter value being updated to the second quality parameter value, and the target neighbor node being updated to the next neighbor node, and so on, until multiple neighbor nodes are determined and the target neighbor node is obtained.

[0214] In another possible implementation, the fifth determination module 807 is used to determine, for the first neighbor node, a third quality parameter value based on the distance between the path starting point and the first neighbor node and the safety factor of the autonomous vehicle passing through the first neighbor node, where the third quality parameter value is used to indicate the quality of the first neighbor node as a path node, the third quality parameter value is used as the target quality parameter value, and the first neighbor node is used as the target neighbor node; for the next neighbor node, a fourth quality parameter value is determined based on the distance between the path starting point and the next neighbor node and the safety factor of the autonomous vehicle passing through the next neighbor node, where the fourth quality parameter value is used to indicate the quality of the next neighbor node as a path node, and when the fourth quality parameter value is greater than the target quality parameter value, the target quality parameter value is updated to the fourth quality parameter value, and the target neighbor node is updated to the next neighbor node, and so on, until multiple neighbor nodes are determined and the target neighbor node is obtained.

[0215] In another possible implementation, the first determination module 801 is used to enable an endpoint recognition function of the autonomous driving vehicle; while the driver is driving the autonomous driving vehicle, the body sensor of the autonomous driving vehicle is enabled through the endpoint recognition function; first environmental data of the autonomous driving vehicle is obtained through the body sensor; based on the first environmental data, the parking endpoint of the autonomous driving vehicle is determined, and the parking endpoint is used as the path endpoint of the autonomous driving vehicle.

[0216] In another possible implementation, the third determination module 805 is used to obtain second environmental data of the first target node; when the second environmental data is used to indicate that there are obstacles around the first target node, the obstacle direction of the obstacle at the first target node is determined based on the second environmental data; based on the obstacle direction, the pathfinding direction of the autonomous driving vehicle is determined; based on the pathfinding direction, multiple neighbor nodes of the first target node are determined from the node set, and the multiple neighbor nodes are located in the pathfinding direction of the first target node.

[0217] In an embodiment of the present application, when determining the driving path from the starting point of the path to the end point of the path, the starting point of the path is first used as a reference node, the first target node is determined based on the reference node, and the target neighbor node is determined based on the first target node. In this way, part of the driving path is determined as the reference node-first target node-target neighbor node, and then the target neighbor node is used as the reference node, and the above process is performed again until the end point of the path is found; it can be seen that the embodiment of the present application is to evaluate each path node to select the best position and then perform the next search until the end point of the path is found, that is, the embodiment of the present application uses a heuristic search algorithm to plan the driving path, which can effectively omit a large number of unnecessary driving paths, thereby improving the planning efficiency of the driving path.

[0218] It should be noted that the vehicle path planning device provided in the above embodiment only uses the division of the above-mentioned functional modules as an example when performing vehicle path planning. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the vehicle terminal can be divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle path planning device provided in the above embodiment and the vehicle path planning method embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0219] Figure 9This is a structural block diagram of a vehicle-mounted terminal provided in an embodiment of the present application. Generally, the vehicle-mounted terminal 900 includes: a processor 901, a memory 902, a voice receiving device 903 and a controller 904. The processor 901 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 901 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor 901 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 901 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0220] Memory 902 may include one or more computer-readable storage media, which may be non-transitory. Memory 902 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in memory 902 is used to store at least one instruction, which is executed by processor 901 to implement the lighting control method provided in the method embodiments of this application.

[0221] In some embodiments, the in-vehicle terminal 900 may optionally include a peripheral device interface 905 and at least one peripheral device. The processor 901, memory 902, and peripheral device interface 905 may be connected via a bus or signal lines. Each peripheral device may be connected to the peripheral device interface 905 via a bus, signal lines, or circuit boards. Specifically, the peripheral device may include at least one of a radio frequency circuit 906, an audio circuit 907, and a power supply 908.

[0222] The peripheral device interface 905 can be used to connect at least one I / O (Input / Output)-related peripheral device to the processor 901 and the memory 902. In some embodiments, the processor 901, the memory 902, and the peripheral device interface 905 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 901, the memory 902, and the peripheral device interface 905 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0223] The RF circuit 906 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 906 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 906 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the RF circuit 906 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The RF circuit 906 can communicate with other terminals via at least one wireless communication protocol. Such wireless communication protocols include, but are not limited to, metropolitan area networks, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 906 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0224] The audio circuit 907 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 901 for processing, or input them into the radio frequency circuit 906 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there can be multiple microphones, which are respectively arranged in different parts of the vehicle-mounted terminal 900. The microphone can also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 901 or the radio frequency circuit 906 into sound waves. The speaker can be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 907 may also include a headphone jack.

[0225] The power supply 908 is used to power the various components of the vehicle-mounted terminal 900. The power supply 908 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When the power supply 908 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0226] Those skilled in the art will understand that Figure 9 The structure shown in the figure does not constitute a limitation on the vehicle-mounted terminal 900, and may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0227] The present application also provides a computer-readable storage medium having at least one program code stored therein, the at least one program code being loaded and executed by a processor to implement the vehicle path planning method described in any of the above implementations. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM (Read-Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, or an optical data storage device.

[0228] An embodiment of the present application also provides a computer program product, which stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the vehicle path planning method shown in the above embodiments.

[0229] In some embodiments, the computer program product involved in the embodiments of the present application can be deployed and executed on a vehicle-mounted terminal, or on multiple vehicle-mounted terminals located at one location, or on multiple vehicle-mounted terminals distributed at multiple locations and interconnected through a communication network. Multiple vehicle-mounted terminals distributed at multiple locations and interconnected through a communication network can constitute a blockchain system.

[0230] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0231] The above description is only for the purpose of facilitating those skilled in the art to understand the technical solution of this application and is not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included in the scope of protection of this application.

Claims

1. A vehicle path planning method, characterized in that: The method comprises: Determine the path starting point, path ending point, and multiple candidate path nodes of the autonomous vehicle; Combining the path endpoint and the plurality of candidate path nodes into a node set; Taking the starting point of the path as a reference node; Determine a first target node from the node set based on the reference node, and delete the first target node from the node set, where the first target node is the node closest to the reference node; Based on the first target node, determining a plurality of neighbor nodes of the first target node from the node set; Determining the distance between the reference node and each neighbor node respectively; Determine a target neighbor node based on the distance between the reference node and each of the neighbor nodes, and use the target neighbor node as a predecessor node of the first target node; Taking the target neighbor node as a reference node, and then performing the step of determining a first target node from the node set based on the reference node until the node set is empty or the first target node is the end point of the path; Starting from the end point of the path, tracing back along the predecessor node to the starting point of the path, a driving path from the starting point of the path to the end point of the path is obtained.

2. The method according to claim 1, characterized in that The determining the target neighbor node based on the distance between the reference node and each neighbor node includes: For a first neighbor node, the distance between the starting point of the path and the first neighbor node is used as the target distance, and the first neighbor node is used as the target neighbor node; For the next neighbor node, if the distance between the starting point of the path and the next neighbor node is less than the target distance, the target distance is updated to the distance between the starting point of the path and the next neighbor node, and the target neighbor node is updated to the next neighbor node, and so on, until the multiple neighbor nodes are determined and the target neighbor node is obtained.

3. The method according to claim 1, characterized in that The determining the target neighbor node based on the distance between the reference node and each neighbor node includes: For a first neighbor node, determining a first quality parameter value based on a distance between the starting point of the path and the first neighbor node and a time required for the autonomous vehicle to travel the distance, the first quality parameter value being used to indicate a quality of the first neighbor node as a path node, the first quality parameter value being used as a target quality parameter value, and the first neighbor node being used as the target neighbor node; For the next neighbor node, a second quality parameter value is determined based on the distance between the starting point of the path and the next neighbor node and the time required for the autonomous driving vehicle to travel the distance. The second quality parameter value is used to represent the quality of using the next neighbor node as a path node. When the second quality parameter value is greater than the target quality parameter value, the target quality parameter value is updated to the second quality parameter value, and the target neighbor node is updated to the next neighbor node. This process is repeated until the multiple neighbor nodes are determined and the target neighbor node is obtained.

4. The method according to claim 1, wherein The determining the target neighbor node based on the distance between the reference node and each neighbor node includes: For a first neighbor node, based on the distance between the starting point of the path and the first neighbor node and the safety factor of the autonomous vehicle passing through the first neighbor node, determining a third quality parameter value, the third quality parameter value being used to indicate the quality of the first neighbor node as a path node, using the third quality parameter value as a target quality parameter value, and using the first neighbor node as the target neighbor node; For the next neighbor node, a fourth quality parameter value is determined based on the distance between the starting point of the path and the next neighbor node and the safety factor of the autonomous driving vehicle passing through the next neighbor node. The fourth quality parameter value is used to represent the quality of the next neighbor node as a path node. When the fourth quality parameter value is greater than the target quality parameter value, the target quality parameter value is updated to the fourth quality parameter value, and the target neighbor node is updated to the next neighbor node, and so on, until the multiple neighbor nodes are determined and the target neighbor node is obtained.

5. The method according to claim 1, wherein The process of determining the endpoint of the autonomous vehicle's path includes: Activating the endpoint recognition function of the autonomous vehicle; While the driver is driving the autonomous vehicle, the body sensor of the autonomous vehicle is activated by the endpoint recognition function; Acquiring first environmental data of the autonomous driving vehicle through the vehicle body sensor; Based on the first environmental data, the parking end point of the autonomous driving vehicle is determined, and the parking end point is used as the path end point of the autonomous driving vehicle.

6. The method according to claim 1, characterized in that The determining, based on the first target node, a plurality of neighbor nodes of the first target node from the node set includes: Acquire second environment data of the first target node; When the second environmental data indicates that an obstacle exists around the first target node, determining an obstacle direction of the obstacle at the first target node based on the second environmental data; Determining a pathfinding direction of the autonomous vehicle based on the obstacle direction; Based on the routing direction, a plurality of neighbor nodes of the first target node are determined from the node set, where the plurality of neighbor nodes are located in the routing direction of the first target node.

7. A vehicle path planning device, characterized in that: The device comprises: A first determination module is used to determine a path starting point, a path ending point, and a plurality of candidate path nodes of the autonomous driving vehicle; a composition module, configured to combine the path endpoint and the plurality of candidate path nodes into a node set; As a module, used to take the starting point of the path as a reference node; A second determining module is configured to determine a first target node from the node set based on the reference node, and delete the first target node from the node set, wherein the first target node is the node closest to the reference node; A third determining module is configured to determine, based on the first target node, a plurality of neighboring nodes of the first target node from the node set; a fourth determining module, configured to respectively determine the distance between the reference node and each neighboring node; a fifth determining module, configured to determine a target neighboring node based on a distance between the reference node and each of the neighboring nodes, and use the target neighboring node as a predecessor node of the first target node; The module is further configured to use the target neighbor node as a reference node; The second determining module is further configured to determine a first target node from the node set based on the reference node until the node set is empty or the first target node is a path end point; The backtracking module is used to start from the end point of the path and backtrack along the predecessor node to the starting point of the path to obtain the driving path from the starting point of the path to the end point of the path.

8. A vehicle-mounted terminal, characterized in that: The vehicle-mounted terminal includes a processor and a memory, wherein the memory stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the vehicle path planning method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The storage medium stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the vehicle path planning method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The product stores at least one program code, and the at least one program code is used to be executed by a processor to implement the vehicle path planning method according to any one of claims 1 to 6.

Images