Vehicle travel path determination method, device, apparatus, medium and program product

Abstract

This application discloses a method, apparatus, device, medium, and program product for determining vehicle driving paths. The method includes: acquiring the starting point, destination, and a grid map corresponding to the target area for at least two vehicles in the same group within a target area; the grid map comprising i rows and j columns of grids, each grid's size corresponding to the size of the area occupied by each vehicle in the target area, where i and j are positive integers; determining the traffic status of each grid in the grid map at each time step based on target objects present in the target area at each time step; and determining the driving path of each vehicle from the starting point to the destination based on the traffic status of each grid at each time step. This application can avoid collisions during multi-vehicle autonomous driving within a local area and ensures faster arrival at the destination.

Description

Technical Field

[0001] This application relates to the field of battery swapping station technology, and in particular to a method, apparatus, equipment, medium, and program product for determining vehicle travel paths. Background Technology

[0002] A battery swapping station is a facility specifically designed to provide fast battery swapping services for new energy vehicles. To avoid the influence of the external environment, a fixed fence is usually set up around the battery swapping station, with an entrance and an exit. After the driver drives the vehicle capable of automatic battery swapping into the entrance of the battery swapping station, the driver can authorize the battery swapping station to automatically control the vehicle to perform the battery swapping, while the driver can get out of the car and rest.

[0003] Currently, autonomous driving mainly relies on sensors on the vehicle to collect information about the surrounding environment, and then performs path planning based on that information.

[0004] However, due to the limited space at battery swapping stations and the large number of vehicles during peak swapping periods, the current autonomous driving method is prone to problems such as excessively long waiting times for vehicle battery swapping, and even collisions between vehicles, resulting in poor path planning performance. Summary of the Invention

[0005] This application provides a method, apparatus, device, medium, and program product for determining vehicle driving paths, which can avoid collisions during the control of multiple vehicles driving automatically and improve path planning performance.

[0006] Firstly, this application provides a method for determining a vehicle's driving path, including:

[0007] Obtain the starting point, destination, and corresponding grid map of the target area for at least two vehicles in the same group within the target area. The grid map consists of i rows and j columns of grids, and the size of each grid corresponds to the size of the area occupied by each vehicle in the target area. i and j are positive integers.

[0008] Based on the target objects present in the target area at each time, determine the passage status of each grid cell in the grid map at each time.

[0009] Based on the traffic status of each grid at each moment, determine the travel path of each vehicle from the starting point to the destination.

[0010] In this implementation, a grid map of the local area where the battery swapping station is located is constructed. Based on the target objects present in the local area at each time, the traffic status of each grid at different times is obtained. This allows for route planning for each vehicle and control of its movement. This ensures that, during the journey of multiple vehicles from the starting point to the destination in the local area, no two vehicles at the same physical location at any time will collide, improving safety during the battery swapping process.

[0011] In one possible implementation of the first aspect, determining the travel path of each vehicle from the starting point to the destination based on the traffic status of each grid at each time step includes:

[0012] Based on the traffic status of each grid at each moment, the target grid that each vehicle needs to pass through to move from the starting grid to the destination grid in the grid map is determined. The starting grid is the grid corresponding to the starting point in the grid map, and the destination grid is the grid corresponding to the destination in the grid map.

[0013] The travel path of each vehicle from the starting point to the destination is determined based on the target grids that each vehicle needs to pass through to move from the starting grid to the ending grid in the grid map.

[0014] In this implementation, by determining the starting grid corresponding to the starting point of each vehicle in the grid map and the ending grid corresponding to the destination in the grid map, the vehicle's driving path can be planned by searching for the target grid that needs to be traversed from the starting grid to the ending grid. The whole process is more convenient and faster, and can effectively improve the efficiency of path planning.

[0015] In one possible implementation of the first aspect, determining the target grid that each vehicle needs to traverse from the starting grid to the ending grid in the grid map, based on the traffic status of each grid at each time moment, includes:

[0016] Randomly sort the at least two vehicles to obtain at least one sorting order;

[0017] Based on the passage status of each grid at each moment, determine the target grid that each vehicle needs to pass through in the same sequence.

[0018] Based on the target grid that each vehicle in the same arrangement needs to pass through and the preset speed, determine the travel time required for all vehicles in the same arrangement to reach their corresponding destinations.

[0019] Based on the driving time corresponding to different arrangement orders, a target arrangement order and a target grid that each vehicle needs to traverse in the at least one arrangement order are determined.

[0020] In this implementation, by controlling the speed of each vehicle, the stability of the vehicle's driving posture can be ensured. Furthermore, by optimizing the arrangement order and finding the target arrangement order, the maximum time for all vehicles to complete the driving task and reach the destination can be optimized. This can avoid long waiting times at the battery swapping station during peak battery swapping periods and improve battery swapping efficiency.

[0021] In another possible implementation of the first aspect, determining the target grid that each vehicle needs to traverse in the same arrangement order based on the passage status of each grid at each time step includes:

[0022] Based on the passage status of each grid at each time moment, determine the target grid that the first N-1 vehicles in the same arrangement order need to pass through, where N is a positive integer greater than 1 and less than or equal to the total number of vehicles in the group;

[0023] Update the passage status of each grid at each time step based on the target grid that the first N-1 vehicles need to pass through;

[0024] Based on the updated passage status of each grid at each time moment, determine the target grid that the Nth vehicle in the same arrangement order needs to pass through.

[0025] In this implementation, the target grids that each vehicle in the same group needs to pass through are sequentially arranged according to the order of arrangement. The passage status of each grid is updated at each time according to the target grids that the previous N-1 vehicles need to pass through. Then, the target grids that the Nth vehicle needs to pass through are determined step by step. This can avoid multiple vehicles in the same grid at the same time, avoid vehicle collisions, and improve safety.

[0026] In another possible implementation of the first aspect, determining the target grids that each vehicle needs to traverse from the starting grid to the ending grid in the grid map includes:

[0027] Obtain the first grid cell where the vehicle was located at the previous time step and at least one second grid cell adjacent to the first grid cell;

[0028] Based on the passage status of the at least one adjacent second grid, determine the grid in which the vehicle is located at the next moment among the first grid and the at least one second grid;

[0029] Based on the vehicle's starting grid and the grid where the vehicle is located at each moment, determine the target grid that the vehicle needs to pass through to move from the starting grid to the ending grid in the grid map.

[0030] In this implementation, a search algorithm is used to search for the second grid that the vehicle might experience in the next moment, based on the first grid where the vehicle was in the previous moment. This narrows the search range and improves the search efficiency for the target grid.

[0031] Another possible implementation of the first aspect includes:

[0032] Obtain the range of steering angles of the vehicle;

[0033] Based on the vehicle's steerable angle range, determine the movable grid range of the vehicle at the next moment;

[0034] The second grid cells that are not within the range of the movable grid cells in at least one of the adjacent second grid cells are filtered out.

[0035] In this implementation, by utilizing the vehicle's steerable angle range, it is determined which grids the vehicle can actually reach from the surrounding grids, and those grids that the vehicle cannot actually reach are filtered out. This reduces the number of grids that need to be searched during the vehicle's target grid search process, improving the efficiency of single-vehicle path planning while ensuring the feasibility of the calculated path. It also reduces the number of grids that need to be checked, thereby quickly determining the target grid that the vehicle will pass through at the next moment from the remaining grids after filtering, and improving the search efficiency of the target grid.

[0036] In another possible implementation of the first aspect, determining the grid in which the vehicle is located at the next moment among the first grid and the at least one second grid based on the passage status of the adjacent at least one second grid includes:

[0037] Based on the passage status of each second grid and the preset evaluation index, obtain the evaluation value of each second grid;

[0038] Based on the evaluation value, the grid in which the vehicle is located at the next moment is determined among the first grid and the at least one second grid.

[0039] In this implementation, by setting preset evaluation indicators to evaluate each second grid around the vehicle, the optimal second grid can be selected as the target grid that the vehicle needs to experience in the next moment, thereby improving the stability of the vehicle during driving and shortening the vehicle driving time.

[0040] In another possible implementation of the first aspect, obtaining the evaluation value of each second grid cell based on the passage status of each second grid cell and a preset evaluation index includes:

[0041] Based on the traffic status of the second grid, the cost for the vehicle to move to the second grid at the next moment is obtained. The cost includes at least one of the following: the waiting time required to move to the second grid at the next moment, the number of consecutive waiting times required to move to the second grid, the time required to move from the second grid to the destination grid after moving to the second grid, the time required to move from the starting grid to the second grid, the maximum value of the steering angle required to move from the second grid to the destination grid after moving to the second grid, and the steering angle required to move to the second grid.

[0042] The evaluation value of the second grid is determined based on the cost.

[0043] In this implementation, by designing multiple preset evaluation indicators, the method of calculating and sorting the transfer cost of the original classic A-star algorithm is changed, which improves the efficiency of the algorithm search. At the same time, considering the horizontal motion inertia of autonomous vehicles, the maximum turning angle of the line ensures the stability of the vehicle driving along the planned line, further enhancing the driving experience.

[0044] In another possible implementation of the first aspect, determining the accessibility status of each grid cell in the grid map at each time step, based on the target objects present in the target area at each time step, includes:

[0045] If a vehicle is parked in the first area of ​​the target area at the first moment, the grid corresponding to the first area at the first moment is determined to be in a waiting state.

[0046] If there are fixed obstacles in the first area, the grid corresponding to the first area is determined to be impassable at each time.

[0047] If there are no fixed obstacles or vehicles in the first area at the second time, the grid corresponding to the first area at the second time is determined to be passable.

[0048] In this implementation, by configuring different traffic states for the grid, obstacle avoidance operations can be performed in advance during the process of determining the target grid that each vehicle needs to pass through to move from the starting grid to the ending grid in the grid map, thereby reducing the obstacle avoidance time.

[0049] Another possible implementation of the first aspect includes:

[0050] Obtain the length and turning angle range of each vehicle;

[0051] The size of the grid in the grid map is determined based on the length and turning angle range of each vehicle;

[0052] Based on the size of the grid, construct a grid map corresponding to the target area.

[0053] In this implementation, a grid map corresponding to the target area where the battery swapping station is located is established. This minimizes the grid size, thereby further improving the accuracy of vehicle path planning in the target area.

[0054] In another possible implementation of the first aspect, determining the accessibility status of each grid cell in the grid map at each time step, based on the target objects present in the target area at each time step, includes:

[0055] Obtain the location information of each grid cell in the grid map corresponding to the location in the target area and the traffic status of each grid cell at each time.

[0056] At each of the stated times, the target times corresponding to the passable state and the waiting state are obtained;

[0057] Based on the target time and the position information of each grid in the target area, construct a hash table corresponding to each grid.

[0058] Based on the hash table corresponding to each grid cell, the accessibility status of each grid cell in the grid map at each time step is determined.

[0059] In this implementation, a hash table is used to record the traffic status of each grid at all times, which is equivalent to compressing the 3D grid map. This reduces the number of configuration arrays required to record the traffic records of each grid, lowers the storage requirements of computer memory, can be adapted to larger battery swapping sites, can plan the routes of more vehicles at the same time, and facilitates querying and retrieval, quickly finding the traffic status of each grid at each time, thereby further improving the efficiency of route planning.

[0060] In another possible implementation of the first aspect, obtaining at least two vehicles in the same group includes:

[0061] Obtain battery swapping requests initiated by at least two vehicles within the target area;

[0062] The priority of each vehicle is determined based on its battery swapping request.

[0063] Vehicles with the same priority will be grouped together.

[0064] Vehicles with different priorities are grouped into different groups.

[0065] In this implementation, the battery swapping station can group multiple high-priority vehicles together and perform route planning simultaneously, which can meet the needs of drivers and improve battery swapping efficiency.

[0066] In another possible implementation of the first aspect, the starting point of the vehicle in the target area includes any one of the entrance of the target area, the battery swapping location in the target area, and the preset parking space in the target area, and the destination of the vehicle in the target area includes any one of the exit of the target area, the battery swapping location in the target area, and the preset parking space in the target area.

[0067] In this implementation, by setting different starting points and destinations, on the one hand, multiple vehicles in a narrow target area can be diverted, preventing congestion caused by all vehicles heading to the same destination. On the other hand, by treating the battery swapping location in the target area as a necessary central destination, the problem of long algorithm time caused by long-distance path planning can be avoided, enabling rapid planning and control of vehicle paths and improving the response speed of battery swapping requests.

[0068] Another possible implementation of the first aspect includes:

[0069] Obtain the target arrangement order of at least two vehicles in the same group;

[0070] Based on the order of the targets, each vehicle is controlled to travel to its corresponding destination along its designated path.

[0071] In this implementation, each vehicle can travel sequentially along the driving path according to the target arrangement order, avoiding collisions, while also minimizing the time it takes for all these vehicles to reach their destination.

[0072] Secondly, this application provides a vehicle driving path determination device, comprising:

[0073] The acquisition module is used to acquire the starting point, destination and grid map corresponding to the target area for at least two vehicles in the same group within the target area. The grid map includes i rows and j columns of grids, and the size of each grid corresponds to the size of the area occupied by each vehicle in the target area, where i and j are positive integers.

[0074] The status determination module is used to determine the passage status of each grid in the grid map at each time based on the target objects present in the target area at each time.

[0075] The route determination module is used to determine the travel route of each vehicle from the starting point to the destination based on the traffic status of each grid at each time.

[0076] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described above.

[0077] Fourthly, this application provides a readable storage medium storing computer program instructions that, when executed by a processor, implement the method described above.

[0078] Fifthly, this application provides a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the method described above. Attached Figure Description

[0079] The features, advantages, and technical effects of exemplary embodiments of this application will now be described with reference to the accompanying drawings.

[0080] Figure 1 This is a schematic diagram of the layout of a battery swapping station provided in an embodiment of this application;

[0081] Figure 2 This is a schematic flowchart of the vehicle driving path determination method provided in the embodiments of this application;

[0082] Figure 3 This is a schematic diagram of a two-dimensional grid map provided in an embodiment of this application;

[0083] Figure 4 This is a schematic diagram of a three-dimensional raster map provided in an embodiment of this application;

[0084] Figure 5 This is a schematic diagram of the path search algorithm provided in the embodiments of this application;

[0085] Figure 6 This is a schematic flowchart of the target grid determination method provided in the embodiments of this application;

[0086] Figure 7 A schematic flowchart of a target grid determination method for a single vehicle provided in an embodiment of this application;

[0087] Figure 8 This is a schematic diagram illustrating the target raster determination process at different times provided in the embodiments of this application;

[0088] Figure 9 This is a schematic diagram comparing the vehicle's direction of travel provided in an embodiment of this application;

[0089] Figure 10 A schematic diagram of the movable grid range at the next moment provided in an embodiment of this application;

[0090] Figure 11 A schematic diagram illustrating the travel direction of a single vehicle provided in an embodiment of this application;

[0091] Figure 12 This is a schematic diagram of the target grid determination process provided in an embodiment of this application;

[0092] Figure 13 This is a schematic diagram of the battery swapping process at a battery swapping station provided in an embodiment of this application;

[0093] Figure 14 This is a schematic diagram of the multi-vehicle route determination process provided in an embodiment of this application;

[0094] Figure 15 A schematic diagram of the route determination process for a single vehicle provided in an embodiment of this application;

[0095] Figure 16 This is a schematic diagram of the path search algorithm provided in the embodiments of this application;

[0096] Figure 17 This is a schematic diagram of the path provided in the embodiments of this application;

[0097] Figure 18 This is a schematic diagram of the vehicle driving path determination device provided in the embodiments of this application;

[0098] Figure 19 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application.

[0099] The accompanying drawings are not necessarily drawn to scale. Detailed Implementation

[0100] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0101] A battery swapping station is a facility specifically designed to provide rapid battery replacement services for new energy vehicles. After a vehicle enters the station, the station automatically plans the vehicle's route based on the driver's request and controls the vehicle to automatically drive to the battery swapping location. To avoid external environmental influences, fixed electronic fences are set up around the swapping station. During peak swapping periods, vehicle density is typically high, requiring the swapping station to rationally plan the route for each vehicle given its relatively small area and high vehicle density. Current technologies primarily rely on sensors on the vehicle to collect information about its surrounding environment and then plan the route based on this information. However, this method is prone to causing excessively long battery swapping wait times and potential safety risks such as vehicle collisions in swapping station scenarios, resulting in poor route planning performance.

[0102] To address the aforementioned issues, this application provides a method for autonomous driving path planning for multiple vehicles in localized low-speed scenarios. This method enables the control and scheduling of multiple vehicles in such scenarios, ensuring that they can reach their destination as quickly as possible without collisions. Taking the aforementioned battery swapping station as an example, a spatiotemporal grid map of the station is constructed. The two-dimensional grid map is expanded into a three-dimensional grid map with spatiotemporal dimensions. The three-dimensional grid map is used to depict or record the traffic status of each grid, providing a state reference between different vehicles for path planning. This allows for the coordination of other vehicles to avoid obstacles while planning vehicle paths, and also optimizes obstacle avoidance time, shortening the vehicle battery swapping waiting time.

[0103] For example, Figure 1 This is a schematic diagram of the layout of a battery swapping station provided in an embodiment of this application, as shown below. Figure 1 As shown, this battery swapping station can be a semi-enclosed site for automated valet battery swapping. The automated valet battery swapping vehicles only operate within the electronic fence area. When a controlled vehicle crosses the electronic fence, it will immediately apply safety brakes and come to a safe stop. Simultaneously, a safety buffer zone is set up around the perimeter of the electronic fence to ensure the safety of people and the station.

[0104] The automated valet battery swapping site mainly includes an entrance, an exit, an electronic fence (limiting the area where the swapping station can control autonomous driving), a buffer zone (i.e., a physical safety mechanism) located outside the electronic fence, at least one swapping station (multiple swapping stations can be configured in busy areas to meet swapping demand), multiple temporary parking spaces (e.g., 5-8 spaces, with 3-4 redundant spaces planned as needed), one electronic device, such as a battery swapping computing hub, specifically a station-side computer including GPU, CPU, and storage, multiple monocular cameras (mainly installed at the entrance, exit, and front of temporary parking spaces to identify and locate vehicles and request automated valet battery swapping services), multiple binocular cameras (for obstacle recognition, vehicle segmentation, identification, location, and tracking), and multiple ultrasonic radars (to enhance vehicle and environmental perception in image recognition blind spots). Figure 1 The battery swapping process for vehicles at the battery swapping site is as follows:

[0105] 1) When a vehicle enters designated area ①, the battery swapping station uses images captured by cameras to identify whether it is an automatic battery swapping vehicle. The vehicle's infotainment system requests authorization from the user for automatic valet battery swapping and displays the earliest possible battery swapping completion time. The driver can simultaneously schedule a pick-up time (this scheduled pick-up time must be later than the system's estimated earliest possible battery swapping completion time). After authorizing the automatic valet battery swapping service at the battery swapping entrance and setting the pick-up time, the driver can get out of the vehicle and leave the battery swapping area or rest in the vehicle. The battery swapping station calculates the battery swapping task scheduling based on the driver's reservation information and the vehicle information in the station, and completes the vehicle's driving route planning.

[0106] 2) Drivers can choose whether to use the automatic valet battery swap service in area ①. If the driver chooses to accept the service, the battery swap station will take over the vehicle's infotainment system and configure safety procedures for the driver. For example, a safety procedure could be that if the driver presses the brake pedal for an extended period, the driver can immediately take over the vehicle, and the infotainment system will provide an immediate voice prompt. If the driver needs to request the automatic valet battery swap service again later, they need to request it through the vehicle's infotainment app, and the battery swap station will attempt to take over the service again.

[0107] 3) The battery swapping station automatically controls vehicles to enter the station in an orderly manner based on the on-site battery swapping situation (e.g., whether there is a queue or whether a vehicle is currently swapping batteries). The entire process of queuing for entry and driving within the station is monitored by depth cameras and lidar, and the battery swapping station system completes route planning and real-time adjustment of driving strategies.

[0108] 4) The vehicle automatically drives into the battery swapping V-groove, and its attitude is confirmed by sensors such as the station base pressure sensor, binocular camera, proximity switch, and alignment chute. The battery swapping calculation system detects and confirms that the vehicle meets the battery swapping requirements, requests the battery swapping station system to start the swapping process, and then the battery swapping station automatically performs the swapping.

[0109] 5) During the battery swapping process at the station, drivers can monitor the progress via a mobile app or in-vehicle display. After the automatic battery swap is completed, the vehicle follows the station's planned exit route and automatically leaves the battery swapping control panel ⑤. Once the vehicle arrives at area ⑥, it can be routed according to the driver's battery swapping order type (e.g., scheduled pick-up and battery swapping order / unscheduled pick-up and battery swapping order).

[0110] For the pre-booked vehicle pick-up and battery swap order type, (1) if there are enough empty parking spaces in the battery swapping site, the battery swapping calculation system will park the autonomous vehicle in a temporary parking space and notify the driver via SMS that the battery swapping has been completed and please pick up the vehicle as soon as possible; (2) if there are not enough empty parking spaces in the battery swapping site (the pre-booked vehicle pick-up and battery swap order type in the site has reached the upper limit of the pre-booked parking spaces), the battery swapping calculation system will immediately call the driver to pick up the vehicle as soon as possible, and at the same time report to the battery swapping calculation system that it will temporarily no longer accept the pre-booked vehicle pick-up and battery swap order type, and then the autonomous vehicle will be parked in a temporary parking space.

[0111] For non-reservation-based vehicle pick-up and battery swapping orders, the battery swapping system will automatically drive the vehicle to area ⑦, brake safely, hand over control to the driver, and notify the driver that the automatic valet battery swapping service has been completed and to leave the battery swapping service area as soon as possible.

[0112] For pre-booked vehicle pick-up and battery swap orders, once the driver arrives at the battery swap service area ⑦ and confirms arrival via the APP, the battery swap calculation system will automatically wake up the vehicle and drive it to area ⑦. The driver can then wait within the safe area of ​​area ⑦.

[0113] After introducing the battery swapping scenarios and processes described above, the following examples will detail how to perform route planning for multiple vehicles within a battery swapping station. It should be noted that the following specific examples can be combined with each other, and similar concepts or processes may not be elaborated upon in some examples.

[0114] Figure 2 This is a schematic flowchart of a vehicle travel path determination method provided in an embodiment of this application. This method can be applied to the aforementioned battery swapping station, and can be executed by electronic equipment (such as the aforementioned battery swapping calculation system) within the station. Figure 2 As shown, the method may specifically include the following steps:

[0115] Step S210: Obtain the starting point, destination, and corresponding grid map of the target area for at least two vehicles in the same group within the target area.

[0116] The grid map consists of i rows and j columns of grids. The size of each grid corresponds to the size of the area occupied by each vehicle in the target area. i and j are positive integers. The target area includes battery swapping stations.

[0117] In this scenario, when the grid map is drawn to scale according to the target area, the size of each grid cell is the same as or similar to the size of the area occupied by the vehicle (typically, the area occupied by the vehicle is approximately equal to the area of ​​a parking space). For example, in some embodiments, the size of the grid cells in the grid map can be determined based on the length and turning angle range of each vehicle. Then, a grid map corresponding to the target area is constructed based on the grid cell sizes. For instance, a grid cell can be defined as a square with a side length of R. Given that the maximum turning angle of the vehicle is θ (θ can be between 25 and 35 degrees), and L is the vehicle length, the grid cell side length R can be calculated using the minimum turning angle formula R = L / 2 * sin(θ). By using a square with a side length of R as the smallest unit grid cell, a grid map corresponding to the target area where the battery swapping station is located is constructed. This minimizes the grid size, thereby further improving the accuracy of vehicle path planning within the target area.

[0118] In this embodiment, the target area is defined as described above. Figure 1 Taking the automated valet battery swapping site mentioned earlier as an example, there may be multiple vehicles in the target area. Different vehicles can be grouped, for example, according to vehicle size, type, and battery swapping task.

[0119] For example, battery swapping tasks include immediate battery swapping tasks and scheduled battery swapping tasks. An immediate battery swapping task refers to a situation where, after arriving at the entrance of the battery swapping station, the driver expects to quickly complete the battery swap and drive directly out of the station's exit. A scheduled battery swapping task refers to a situation where, after the driver enters the battery swapping station from the entrance, they can park in a temporary parking space, and then the vehicle will depart from the temporary parking space, complete the automatic battery swap, and then return to the original parking space.

[0120] Among them, if the deadline for the scheduled battery swapping task is met, the battery swapping station can prioritize the route planning of vehicles for immediate battery swapping tasks based on the set battery swapping time in each type of battery swapping task, so that vehicles for immediate battery swapping tasks can complete the battery swapping as soon as possible.

[0121] Specifically, when the driver drives the vehicle into Figure 1When designated area ①, drivers can choose different battery swap order types. For example, drivers can choose a scheduled battery swap order (corresponding to a scheduled battery swap task) or an unscheduled battery swap order (corresponding to an on-demand battery swap task). For instance, priority can be assigned to each vehicle based on the set battery swap time in the order type; for example, the earlier the set battery swap time, the higher the priority of the vehicle. Vehicles with the same priority can be grouped together.

[0122] For example, in some other embodiments, after each vehicle enters the target area, the driver can initiate a battery swap request. For instance, the driver can fill in a set battery swap time in the request to inform the battery swap station that the vehicle needs to complete the swap before that time. When the battery swap station receives the request, it can determine the vehicle's priority based on the set swap time (e.g., if the driver requests an immediate swap, the vehicle has the highest priority). To meet the driver's needs and improve swap efficiency, the station can group multiple high-priority vehicles together and perform route planning simultaneously. For example, vehicles with non-reserved battery swap orders can be grouped together. This is because non-reserved battery swap orders typically have strict time requirements, necessitating rapid route planning and battery swapping. Vehicles with reserved battery swap orders only need to complete the swap before the scheduled time.

[0123] In this embodiment, the origin and destination of a vehicle may differ depending on the type of battery swapping order. For example, if a driver wants to swap batteries immediately after entering the battery swapping station and then leave the station immediately after the swap, then the origin of the vehicle is the battery swapping station entrance. Additionally, the vehicle's destination can be divided into two: the first destination is the battery swapping location (after arriving at the location, the vehicle needs to stay for a period of time to swap the battery), and the second destination is the battery swapping station exit.

[0124] For example, after entering the battery swapping station from the entrance, the driver might select a scheduled pickup and battery swap order, such as scheduling to pick up the vehicle in 3 hours. The vehicle can then park in a designated parking space for a period of time, and then drive to the battery swapping location closer to the scheduled time. After the swap is completed, the vehicle can park back in the parking space and wait for the driver to pick it up. In this case, the vehicle's starting point includes the entrance to the battery swapping station, while its destination could be the aforementioned parking space.

[0125] In this embodiment, the grid map includes a number of grids. The more grids there are, the higher the accuracy, ensuring more precise route planning. The size of each grid cell should be at least greater than or equal to the size of the area occupied by the vehicle at the battery swapping station. For example, if a grid map is drawn proportionally based on the area occupied by a local area, then the size of each grid cell in the grid map should be at least equivalent to the size of a parking space.

[0126] Step S220: Determine the accessibility status of each grid cell in the grid map at each time step based on the target objects present in the target area at each time step.

[0127] In this embodiment, the passage status of a grid can be divided into a passable state, an impassable state, and a waiting state. For example, if there is a fixed obstacle (which cannot move autonomously, such as a traffic cone or a boulder) on the corresponding block of the target area, then the grid is in an impassable state at every moment. Conversely, if there is a movable obstacle (which can move autonomously, such as a parked vehicle or pedestrian) on the corresponding block of the target area, then the grid is in a waiting state at that moment. Furthermore, when a movable obstacle moves from the grid to another grid at a future moment, the grid becomes passable at that future moment.

[0128] By constructing a three-dimensional spatiotemporal grid map network, the system depicts the traffic status of each grid at any given time, giving any vehicle the ability to detect other vehicles and avoid obstacles when performing path planning calculations. This ensures that any two vehicles at the same physical location at any given time will not collide.

[0129] For example, taking the first moment as an example, if a vehicle is parked in the first area of ​​the target area at the first moment, the corresponding grid cell in the first area at the first moment is determined to be in a waiting state; if there is a fixed obstacle in the first area, the corresponding grid cell in the first area at each moment is determined to be in an impassable state; if there are no fixed obstacles or vehicles in the first area at the second moment, the corresponding grid cell in the first area at the second moment is determined to be in a passable state. By configuring different passable states for the grid cells, obstacle avoidance operations can be performed in advance during the process of determining the target grid cells that each vehicle needs to pass through to move from the starting grid cell to the ending grid cell in the grid map, thus reducing obstacle avoidance time.

[0130] In this embodiment, as mentioned above, the battery swapping station includes many sensors, such as cameras and radar. The cameras and radar can identify whether a target object in the target area is a fixed obstacle or a movable obstacle. Furthermore, these sensors can also identify the location of the target object within the target area, thereby further determining which grid cell it corresponds to.

[0131] Step S230: Determine the travel path of each vehicle from the origin to the destination based on the traffic status of each grid at each time.

[0132] In this embodiment, since each grid in the grid map has a corresponding position in the target area, determining the target grid to be traversed at each moment is actually performing vehicle path planning.

[0133] Once the traffic status of each grid cell in the raster map is determined at each time point, a three-dimensional raster map can be created. For example, Figure 4 This is a schematic diagram of a three-dimensional raster map provided in an embodiment of this application, such as... Figure 4 As shown, a grid cell in this 3D raster map can be labeled as (X2, Y2, T2), where X2 and Y2 represent the aforementioned... Figure 3 The grid cell in the X2 row and Y2 column represents time T.

[0134] In this embodiment, the passage status of each grid cell in the 3D grid map can be recorded. For example, taking the aforementioned grid cell (X2, Y2, T2) as an example, the passage status of this grid cell can be recorded as a waiting state. The passage status of this grid cell can be represented by a number. For instance, at time T2, if the passage status of this grid cell (X2, Y2, T2) is a waiting state, then the number 1 is used to represent the waiting state. Or, for example, at time T2, if the passage status of this grid cell (X2, Y2, T3) is a passable state, then the number 2 is used to represent the passable state. Referring to the above... Figure 3 It is understandable that when the time dimension is added, the raster XY will be called the raster XYT, where the value of T can vary.

[0135] In this embodiment, by recording the traffic status of each grid in the three-dimensional grid map at each moment, when planning the path for multiple vehicles, it is possible to detect in advance whether the grids around a certain vehicle are passable at the next moment, thereby performing obstacle avoidance planning in advance, optimizing obstacle avoidance time, and preventing vehicles from waiting in a certain grid for a long time.

[0136] In response to the above Figure 3 In a two-dimensional grid map, the A-star path search algorithm can be used to search for the target grid for each vehicle. For example, Figure 5 This is a schematic diagram of the path search algorithm provided in the embodiments of this application, such as... Figure 5 As shown, it includes the following steps:

[0137] Step S510: Define the open list and the closed list.

[0138] The open list stores nodes to be processed, which are the path points the algorithm will explore or consider next. The closed list stores nodes that have already been processed. During each algorithm iteration, the node with the smallest F-value is selected from the open list for expansion and then moved to the closed list.

[0139] Step S520: Calculate the F value in the open list node.

[0140] The evaluation function used in the A-Star algorithm is f(n) = g(n) + h(n). g(n) represents the actual cost function from the starting node to the current node, h(n) represents the estimated cost function from the current node to the destination node, and f(n) represents the total cost function from the starting node through node n to the destination node, i.e., the F-value. When g(n) = 0, the total cost function f(n) only considers the estimated cost from the current node to the destination node. If h(n) = 0, the total cost function f(n) only considers the actual cost from the starting node to the current node.

[0141] Step S530: Find the node with the smallest F value in the open list, add the neighboring nodes of the current node to the open list, and add the previous node of the current node to the closed list.

[0142] Step S540: Determine if the target node exists in the open list.

[0143] Step S550: Obtain the optimal path from the starting node to the target node.

[0144] The A-star algorithm starts from the starting node and expands outwards to its surroundings. It calculates the evaluation value of the surrounding nodes using an evaluation function, selects the node with the minimum cost as the next node to expand, and so on until the destination node is found, thus obtaining the final path.

[0145] However, in 3D raster maps (see above) Figure 4 Therefore, the A-star algorithm needs to be improved to achieve path planning in multi-vehicle autonomous driving. In this embodiment, the A-star algorithm is improved mainly in terms of the dimension of the search space, the node expansion method, the evaluation function, multi-objective optimization, and adaptation to simultaneous planning of multiple vehicles, so as to obtain a heuristic multi-vehicle cooperative path search algorithm, which improves the accuracy of the algorithm, enhances the usability of the path planning results, and reduces the computational load of the algorithm search.

[0146] Specifically, this embodiment uses a 3D grid map (as described above). Figure 4 As shown in the diagram, the X and Y axes represent longitude and latitude, respectively, and the Z axis represents time information. For example, Node... i，j，tLet represent the traffic status of the grid in the i-th row and j-th column at time t. Assuming there are k vehicles in the battery swapping area that need to have their routes planned, then at any time t, based on the traffic status of each grid, we can ensure that the k vehicles do not overlap on the xy-dimensional plane.

[0147] In this process, k vehicles perform path searches sequentially, with each vehicle determining its path based on the Node of the current grid. i，j，t Retrieve the passable grid nodes at time t+1 i，j，t+1 The grid with the best overall evaluation function f(t+1) is selected as the next destination node for transfer.

[0148] Understandably, vehicle path planning is fundamental to the navigation and control of autonomous vehicles. In localized, low-speed environments like battery swapping stations, the relatively small area and high vehicle density during peak swapping periods present challenges such as a large computational workload and high complexity in simultaneously planning paths for multiple vehicles. Furthermore, it's crucial to coordinate multiple vehicles to avoid collisions. Therefore, in this embodiment, a grid map of the local area where the battery swapping station is located is constructed. Based on the target objects present in the local area at each moment, the traffic status of each grid is obtained at different times. Based on the traffic status of each grid, route planning is performed for each vehicle, controlling its movement. This ensures that during the journey from the starting point to the destination of multiple vehicles in the local area, no two vehicles at the same physical location collide, guaranteeing safety during the battery swapping process. Simultaneously, since the traffic status of the grid at the next moment can be known in advance, obstacle avoidance strategies can be generated beforehand when planning the path for a particular vehicle. For example, bypassing impassable grids ahead optimizes obstacle avoidance time, avoids long waiting times, and improves path planning effectiveness.

[0149] Furthermore, in some embodiments, the driving path can be determined through the following steps:

[0150] Step S2301: Based on the traffic status of each grid at each time point, determine the target grid that each vehicle needs to traverse from the starting grid to the destination grid in the grid map. The starting grid is the grid corresponding to the origin in the grid map, and the destination grid is the grid corresponding to the destination in the grid map.

[0151] Step 2302: Determine the travel path of each vehicle from the starting point to the destination based on the target grids that each vehicle needs to pass through to move from the starting grid to the destination grid in the grid map.

[0152] In this embodiment, if the local area and the grid map are proportional, then a small area within the local area corresponds to one grid cell. For example, one parking space corresponds to one grid cell. Figure 3This is a schematic diagram of a two-dimensional grid map provided in an embodiment of this application, such as... Figure 3 As shown, assume the local region is a square region. Figure 3 In this context, X represents longitude and Y represents latitude, so each small square in a local area can be considered a grid.

[0153] For example, when a vehicle is in grid 11, its starting grid is grid 11. If the destination coordinates (X0, Y0) are in grid 12, then the vehicle's ending grid is grid 12.

[0154] In this embodiment, as mentioned above, the raster map is drawn based on local areas, so each raster has a corresponding position in the target area, for example, referring to the above... Figure 3 Grid 11 has a corresponding position in a local area, and grid 12 also has a corresponding position in a local area. By determining the corresponding position of each target grid in the target area, a driving path can be depicted, thereby enabling automatic control of the vehicle.

[0155] In this embodiment, by determining the starting grid corresponding to the starting point of each vehicle in the grid map and the ending grid corresponding to the destination in the grid map, the vehicle's driving path can be planned by searching for the target grid that needs to be traversed from the starting grid to the ending grid. The whole process is more convenient and faster, and can effectively improve the efficiency of path planning.

[0156] When determining the target grid that each vehicle needs to traverse, the arrival time of each vehicle can be optimized in the following ways, allowing all vehicles in the same group to arrive at their destination and complete the battery swap as early as possible. For example, Figure 6 This is a schematic flowchart of the target grid determination method provided in the embodiments of this application, as follows: Figure 6 As shown, it includes the following steps:

[0157] Step S610: Randomly sort at least two vehicles to obtain at least one sorting order.

[0158] As mentioned above, there are multiple vehicles in the same group. This implies that these vehicles are different; their size, model, color, and appearance may vary. Therefore, multiple different arrangement orders can be constructed. For example, with 5 vehicles, the arrangement order could be: Vehicle 1 > Vehicle 2 > Vehicle 3 > Vehicle 4 > Vehicle 5. Another example is: Vehicle 5 > Vehicle 4 > Vehicle 3 > Vehicle 2 > Vehicle 1.

[0159] The order of arrangement can be used to determine the path planning order for each vehicle. For example, if the order is vehicle 1 > vehicle 2 > vehicle 3 > vehicle 4 > vehicle 5, then the path of vehicle 1 will be planned first, followed by the path of vehicle 2, and so on until the paths of all vehicles are planned.

[0160] In this scenario, assuming the grid map has 10 grids, and vehicle 1 prioritizes path planning, if vehicle 1 is in the first grid at time t, then when planning the path for vehicle 2, the passable state of the first grid at time t changes to a waiting state. This demonstrates that different grid arrangements will affect the path planning for different vehicles.

[0161] Step S620: Based on the passage status of each grid at each time moment, determine the target grid that each vehicle needs to pass through in the same arrangement order.

[0162] In this embodiment, continuing with the example of the 5 vehicles mentioned in step S610 above, assuming the arrangement order is vehicle 1 > vehicle 2 > vehicle 3 > vehicle 4 > vehicle 5, then based on the passage status of each grid at each time, it is possible to determine the target grid that all vehicles need to pass through one by one. For example, if vehicle 1 is planned to be in the first grid at time t, then at time t, the first grid is in a waiting state, and vehicle 2 needs to determine whether to continue waiting in place or bypass the first grid.

[0163] Step S630: Based on the target grid that each vehicle in the same sequence needs to pass through and the preset speed, determine the travel time required for all vehicles in the same sequence to reach their corresponding destinations.

[0164] In this embodiment, in order to prevent safety accidents, all vehicles can be configured to a fixed low speed (e.g., less than 10 kilometers per hour) while the vehicles are traveling at the battery swapping station. Alternatively, different vehicles can be configured to have different speeds.

[0165] Once the target grid that each vehicle needs to traverse in the same sequence is determined, the travel path of each vehicle can be determined based on the target grid, and the time required for each vehicle to travel from the starting point to the target point can be analyzed. For example, continuing with the 5 vehicles mentioned above, arranged in the order of vehicle 1>vehicle 2>vehicle 3>vehicle 4>vehicle 5, assuming that the first four vehicles, namely vehicles 1, 2, 3, and 4, each take 20 minutes to reach their destination, while vehicle 5 takes 1 hour, then the actual travel time for all 5 vehicles to reach their destination is 1 hour (that is, taking the latest vehicle to arrive at the destination in the same sequence (e.g., vehicle 5), and the arrival time of vehicle 5 as the travel time corresponding to that sequence).

[0166] Step S640: Based on the driving time corresponding to different arrangement orders, determine the target arrangement order and the target grid that each vehicle in the target arrangement order needs to go through in at least one arrangement order.

[0167] In this embodiment, as mentioned above, there are multiple possible arrangement orders. For example, the arrangement order could be: Vehicle 1 > Vehicle 2 > Vehicle 3 > Vehicle 4 > Vehicle 5. Another example is Vehicle 5 > Vehicle 4 > Vehicle 3 > Vehicle 2 > Vehicle 1. Each arrangement order corresponds to a travel time. For instance, the arrangement order with the shortest travel time can be selected as the target arrangement order. Subsequently, the path for each vehicle is planned sequentially according to this target arrangement order. That is, based on the target arrangement order of at least two vehicles in the group, each vehicle is controlled to travel to its corresponding destination along its corresponding path. This ensures that each vehicle travels sequentially along its path under the target arrangement order, avoiding collisions, and minimizing the time it takes for all vehicles to reach their destination.

[0168] In this embodiment, by controlling the speed of each vehicle, the stability of the vehicle's driving posture can be ensured. Furthermore, by optimizing the arrangement order and finding the target arrangement order, the maximum time for all vehicles to complete the driving task and reach the destination can be optimized. This can avoid long waiting times at the battery swapping station during peak battery swapping periods and improve battery swapping efficiency.

[0169] Furthermore, in some embodiments, the target grid that each vehicle needs to traverse can be determined in the following manner. Figure 7 This is a schematic flowchart of the target grid determination method for a single vehicle provided in an embodiment of this application, as shown below. Figure 7 As shown, it includes the following steps:

[0170] Step S710: Based on the passage status of each grid at each time moment, determine the target grid that the first N-1 vehicles in the same arrangement order need to pass through.

[0171] Where N is a positive integer greater than 1 and less than or equal to the total number of vehicles in the group;

[0172] Step S720: Update the passage status of each grid at each time step based on the target grid that the first N-1 vehicles need to pass through;

[0173] Step S730: Based on the updated passage status of each grid at each time moment, determine the target grid that the Nth vehicle in the same arrangement order needs to pass through.

[0174] In this embodiment, continuing with the example of the 5 vehicles mentioned above, we assume that the order of these 5 vehicles is vehicle 1 > vehicle 2 > vehicle 3 > vehicle 4 > vehicle 5. First, we determine the target grid that vehicle 1 needs to pass through. For example, at time t, vehicle 1 needs to pass through target grid s11, at time t1, vehicle 1 needs to pass through target grid s12, ..., at time tn, vehicle 1 needs to pass through target grid s1n. Thus, we obtain the target grid that vehicle 1 needs to pass through at each time from the starting grid to the ending grid.

[0175] Furthermore, when determining the target grid that vehicle 2 needs to traverse, since vehicle 1 is at target grid s12 at time t1, to prevent a collision between vehicle 1 and vehicle 2, target grid s12 cannot be used as the target grid that vehicle 2 needs to traverse at time t1. For example, vehicle 2 can wait in place or bypass target grid s12 at time t1. That is, after determining the target grid that each vehicle needs to traverse, the passage status of each grid at each time needs to be updated, and then the target grid that the next vehicle needs to traverse can be determined.

[0176] In this embodiment of the application, by sequentially determining the target grids that each vehicle in the same group needs to pass through according to the arrangement order, and updating the passage status of each grid at each moment based on the target grids that the previous N-1 vehicles need to pass through, and then gradually determining the target grids that the Nth vehicle needs to pass through, it is possible to avoid multiple vehicles in the same grid at the same moment, thereby avoiding collisions between vehicles and improving safety.

[0177] Furthermore, determining the target grid that each vehicle needs to traverse at each moment can be achieved through the following steps. Specifically, Figure 8 This is a schematic diagram of the target raster determination process at different times provided in the embodiments of this application, such as... Figure 8 As shown, the method includes the following steps:

[0178] Step S810: Obtain the first grid cell where the vehicle was located at the previous time step and at least one second grid cell adjacent to the first grid cell;

[0179] Step S820: Determine the grid where the vehicle will be located at the next moment from the first grid and at least one second grid, based on the passage status of at least one adjacent second grid.

[0180] Step S830: Based on the vehicle's starting grid and the grid where the vehicle is located at each moment, determine the target grid that the vehicle needs to pass through to move from the starting grid to the ending grid in the grid map.

[0181] In this embodiment, the vehicle actually travels on a two-dimensional plane (refer to the above). Figure 3(This is equivalent to driving on different grids). It is necessary to determine the target grid to be traversed in the next moment from other surrounding grids (i.e., the second grid) or the grid where the vehicle was located in the previous moment, based on the grid where the vehicle was located in the previous moment.

[0182] In the process of searching for surrounding second grids, for example, if the passage status of a certain second grid is passable, then the second grid is used as the target grid, and the vehicle will move from the current grid (i.e., the first grid) to the target grid in the next moment.

[0183] Additionally, if the passage status of the second grid is impassable or waiting, the vehicle can also stay in the current grid. That is, the current grid can also serve as the target grid for the vehicle in the next moment, and the vehicle will continue to stay in the current grid in the next moment.

[0184] In this embodiment of the application, a search algorithm is used to search for a second grid that the vehicle may experience in the next moment from at least one second grid around the vehicle, based on the first grid where the vehicle was located at the previous moment. This can narrow the search range and improve the search efficiency for the target grid.

[0185] Additionally, in some embodiments, due to vehicle limitations, it is necessary to filter the second grid cells surrounding the vehicle. For example, considering eight directions: front, rear, left, right, left front, left rear, right front, and right rear, when the vehicle is in a certain first grid cell, there may be eight second grid cells around the vehicle. However, the vehicle cannot usually directly move to the left or right grid cell, so it is necessary to delete the left and right grid cells. For example, this filtering can be performed through the following steps:

[0186] Step 1: Obtain the vehicle's steering angle range;

[0187] Step 2: Based on the vehicle's steering angle range, determine the movable grid range of the vehicle at the next moment;

[0188] Step 3: Filter out at least one adjacent second grid cell that is not within the movable grid cell range.

[0189] In this embodiment, the vehicle's wheels are typically not swivel wheels, and therefore are subject to constraints such as minimum turning radius, preventing direct lateral horizontal movement. For example, Figure 9 This is a schematic diagram comparing the vehicle's direction of travel provided in the embodiments of this application, such as... Figure 9As shown, the vehicle 90 equipped with casters is not subject to minimum turning radius restrictions, therefore it has eight expansion directions: front, rear, left, right, left front, left rear, right front, and right rear. This means that the grids in these eight directions can all serve as secondary grids. However, in reality, vehicles typically do not have casters installed, for example... Figure 9 In the vehicle 91, the maximum turning angle θ of vehicle 91 is known. θ is generally between 25 and 35 degrees. At this time, vehicle 91 has only 6 possible directions of travel. The grid in these 6 possible directions of travel is the range of movable grids of the vehicle in the next moment.

[0190] To address the limitations imposed on vehicle 91, a seven-directional expansion method (i.e., six drivable expansion directions + one stationary parking direction) is proposed on the latitude and longitude plane. The six drivable expansion directions are as follows: Figure 9 The middle arrows indicate the vehicle's forward movement, deviation to the left of the forward movement by θ degrees, deviation to the right of the forward movement by θ degrees, forward movement in the opposite direction, deviation to the left of the reverse forward movement by θ degrees, and deviation to the right of the reverse forward movement by θ degrees.

[0191] Specifically, Figure 10 A schematic diagram of the movable grid range at the next moment provided in the embodiments of this application is shown below. Figure 10 As shown, it includes 6 vehicle movement extensions occurring in the location space, and 1 parking wait occurring in the spatiotemporal space.

[0192] Figure 11 This is a schematic diagram of the travel direction of a single vehicle provided in an embodiment of this application, such as... Figure 11 As shown, this illustrates the node state changes of vehicle k on the time axis. Vehicle k departs from its starting position at time t0, waits at the starting grid until time t1, and then moves to the left by θ degrees along its direction of travel, continuing this process until it reaches the terminal grid, completing path planning. The vehicle travels from t0 to t... n A total of n units of time of equal length have elapsed.

[0193] In this scheme, the unit time is not the physical duration of 1 second, but rather the time T required for the vehicle to pass through a square grid with side length R at a constant speed. base The unit is seconds. By using a 3D grid map, the algorithm can have more diverse operational options when making path planning decisions. When planning a path, the vehicle uses nodes on the grid... i，j，t Share information to predict movable obstacles.

[0194] In this embodiment, by utilizing the vehicle's steering angle range, it is determined which grids the vehicle can actually reach in the surrounding grids, and those grids that the vehicle cannot actually reach are filtered out. This reduces the number of grids that need to be searched during the vehicle's target grid search process, improving the efficiency of single-vehicle path planning while ensuring the feasibility of the calculated path. It also reduces the number of grids that need to be checked, thereby quickly determining the target grid that the vehicle will pass through at the next moment from the remaining grids after filtering, and improving the search efficiency of the target grid.

[0195] In other embodiments, the target grid where the vehicle will be located at the next moment can be determined through the following method steps. Specifically, Figure 12 This is a schematic diagram of the target grid determination process provided in an embodiment of this application, such as... Figure 12 As shown, the method may specifically include the following steps:

[0196] Step S1210: Obtain the evaluation value of each second grid cell based on the passage status of each second grid cell and the preset evaluation index;

[0197] Step S1220: Based on the evaluation value, determine the grid where the vehicle will be located at the next moment in the first grid and at least one second grid.

[0198] In this embodiment, when multiple second grids exist, each second grid can be evaluated to determine its evaluation value. For example, preset evaluation indicators may include the duration of the waiting state when the second grid is in a waiting state; the longer the waiting state lasts, the higher the evaluation value of the second grid. The second grid with the lowest evaluation value can be selected as the grid where the vehicle is located at the next moment, i.e., the target grid for the next moment.

[0199] Furthermore, an evaluation threshold can be set. When the evaluation value of each second grid is greater than the evaluation threshold, the first grid where the vehicle is currently located can be considered as the target grid for the vehicle at the next moment, meaning that the vehicle will continue to stay in the first grid and wait at the next moment.

[0200] Furthermore, in order to determine the optimal target grid from these second grids, several preset evaluation metrics are proposed in other embodiments to calculate the evaluation value. For example, the evaluation value can be calculated as follows:

[0201] Step A1: Based on the traffic status of the second grid, obtain the cost for the vehicle to move to the second grid at the next moment. The cost includes at least one of the following: the waiting time required to move to the second grid at the next moment, the number of consecutive waiting times required to move to the second grid, the time required to move from the second grid to the destination grid after moving to the second grid, the time required to move from the starting grid to the second grid, the maximum value of the steering angle required to move from the second grid to the destination grid after moving to the second grid, and the steering angle required to move to the second grid.

[0202] Step A2: Determine the evaluation value of the second grid based on the cost.

[0203] In this embodiment, the preset evaluation indicators include: (1) the waiting time required for the vehicle to move to the second grid at the next moment; (2) the number of consecutive waiting times required for the vehicle to move to the second grid; (3) the time required to move from the second grid to the end grid after moving to the second grid; (4) the time required to move from the starting grid to the second grid; (5) the maximum value of the steering angle required to move from the second grid to the end grid after moving to the second grid; and (6) the steering angle required to move to the second grid.

[0204] These preset evaluation indicators can be prioritized, with higher-priority preset evaluation indicators being selected to calculate the evaluation value of each second grid. For example, suppose preset evaluation indicator (1) is selected to calculate the evaluation values ​​of two second grids. If the evaluation values ​​of the two second grids are found to be the same, then preset evaluation indicator (2) is selected to calculate the evaluation values ​​of the two second grids, and the second grid with the smaller evaluation value is selected as the target grid. If preset evaluation indicator (2) calculates the evaluation values ​​of the two second grids to be the same, then the next higher-priority preset evaluation indicator is selected to continue the calculation, and so on.

[0205] For example, as shown in Table 1 below, the priority of each preset evaluation index in Table 1 is determined first. The preset evaluation index with the highest priority is selected to evaluate each second grid in the candidate second grid set, and the evaluation value of each second grid is obtained. The second grid with the smallest evaluation value is selected as the target for the vehicle's transfer at the next moment. The optimization of the planned path is ensured through multi-dimensional evaluation of the transfer status. The number of preset evaluation in Table 1 below can be further expanded, but considering the computational efficiency of the algorithm, the number can be set to within 10.

[0206] Table 1

[0207]

[0208]

[0209] Among them, isWaitTag prioritizes selecting grid cells in a passable state as the target grid cells for the next time step, ensuring that the algorithm finds a path with a shorter time cost.

[0210] The waitCount algorithm searches for the number of consecutive waits, as described above. Figure 3 In the xy-plane, the grid cells with fewer consecutive waits at the same position are given priority. Alternatively, the maximum consecutive wait count (waitCount) can be used to determine priority. max Limit the number of grid cells, for example, by limiting the number of consecutive waits for certain second grid cells to exceed waitCount. max If the result is not found, it will be directly removed, reducing the number of grid cells required for comparison.

[0211] hCost represents the estimated time from the current grid cell to the destination grid cell.

[0212] Additionally, gCost represents the actual time required to travel from the starting grid to the current grid. Here, totalCost = gCost + hCost. The algorithm prioritizes selecting the grid with the lowest totalCost and lowest hCost as the target grid for the next time step, guiding the search towards the target grid at the next next step, thus reducing the total number of target grids the vehicle needs to traverse.

[0213] maxAngle represents the maximum turning angle the vehicle has ever made during its journey.

[0214] travelAngle represents the turning angle required for a vehicle to move from its current grid cell to the target grid cell at the next moment. The maximum angle and travelAngle are used to limit the final driving comfort of the vehicle.

[0215] The calculation method for travelAngle is as follows:

[0216] Let the three most recent target grid cells experienced up to the current time t be:

[0217] A = Node i，j，t-2 B = Node i，j，t-1 C = Node i，j，t

[0218] The turning angle of the vehicle in its current direction of travel is:

[0219]

[0220] The maximum turning angle traversed by the vehicle along its travel path is defined as the maximum turning angle traversed by the vehicle along that travel path up to time t+1. By minimizing the turning angle of the vehicle in its current direction of travel and minimizing the maximum turning angle traversed by the vehicle along its travel path, the vehicle is ensured to prioritize routes with smaller turning angles, thus guaranteeing the stability of the vehicle's driving posture.

[0221] In this embodiment, by setting preset evaluation indicators to evaluate each second grid around the vehicle, the optimal second grid can be selected as the target grid that the vehicle needs to experience in the next moment, thereby improving the stability of the vehicle during driving and shortening the driving time. Furthermore, by designing multiple preset evaluation indicators, the method of calculating and sorting the transfer cost of the original classic A-star algorithm is changed, which improves the efficiency of the algorithm search. At the same time, considering the horizontal motion inertia of autonomous vehicles, the maximum turning angle of the line ensures the smoothness of the vehicle driving along the planned line, further enhancing the driving experience.

[0222] Continue to refer to the above. Figure 4 For a three-dimensional raster map, the raster node i，j，t In the diagram, i represents the i-th row of the raster in the latitude direction, j represents the j-th column of the raster in the longitude direction, and t represents the t-th time series.

[0223] Among them, using Indicates the vehicle is in the grid Node i，j，t The passage status, if This indicates that the grid is passable at time t. This indicates that the grid has a fixed obstacle at any given time, making it impassable. This indicates that the grid cell is occupied by other vehicles at time t and is in a waiting state. Therefore, each grid cell needs to be configured with a corresponding... This is used to record the passage status of the grid. Assume the maximum time for all k vehicles to complete the autonomous driving task is T. max The site for the battery swapping station requires X locations based on latitude and longitude. max and Y max A square grid. Therefore, completing the path planning for k vehicles requires T. max *X max *Y max indivual If T max X max and Y max Larger values ​​require a lot of storage space, resulting in high storage pressure and low query efficiency.

[0224] To address the above issues, in other embodiments, a hash table can be constructed for each grid cell based on its location information within the target area, obstacle information at that location, and vehicle information at that location at each time step. This hash table records the passage status of the grid cell at all times. Subsequently, when querying the passage status of a specific grid cell, the passage status at each time step can be directly retrieved from the hash table, effectively saving time T. max *X max *Y max The array was transformed into a single T array. max *X max Hash tables reduce the amount of data, improve query efficiency, and reduce storage pressure.

[0225] Specifically, the hash table is shown in Table 2 below:

[0226] Table 2

[0227] Fields name Numeric types nodeX Grid latitude String nodeY Grid latitude String timeSet time Hash set isObstacle Fixed obstacle markers Boolean value

[0228] Referring to Table 2 above, assuming vehicle k1 passes through the x1-th row and y1-th column grid at time t1, it is represented as {nodeX:x1, nodeY:y1, timeSet:[t1]}; while vehicle k2 passes through the x1-th row and y1-th column grid at time t2, and t1≠t2, it is represented as {nodeX:x1, nodeY:y1, timeSet:[t1, t2]}; if vehicle k3 decides to stay in the current grid at time t3 (t3 is the next adjacent time of t2), it is represented as {nodeX:x1, nodeY:y1, timeSet:[t1, t2, t3]}.

[0229] In this context, it is determined whether a vehicle can pass through a grid node at time t. i，j The judgment rule is: isObstacle == false && timeSet.contain(t) == false, that is, if the grid is a non-fixed obstacle and timeSet does not contain time t, the current vehicle can safely move to the grid at time t.

[0230] In this embodiment, in order to ensure the efficiency of target grid search and avoid vehicles waiting meaninglessly in a certain grid for a long time, a distinction is made between fixed obstacles (such as stone blocks or boundaries) and movable obstacles (such as vehicles) on the grid. When a vehicle encounters a fixed obstacle, it can only choose to move to other grids around the current node. When a vehicle encounters a movable obstacle, the vehicle can choose to wait in the current grid or move to other grids around the current grid.

[0231] In this embodiment, by using a hash table to record the traffic status of each grid at all times, it is equivalent to compressing the three-dimensional grid map, reducing the number of configuration arrays required to record the traffic records of each grid, reducing the storage requirements of computer memory, adapting to larger battery swapping sites, planning more vehicle routes at the same time, and facilitating query and retrieval to quickly find the traffic status of each grid at each time, thereby further improving the efficiency of route planning.

[0232] In some embodiments, assuming there are k vehicles in the same group within the battery swapping site, continue to refer to the above. Figure 4 When determining the target grid that each vehicle needs to traverse, it is necessary to ensure that at most one vehicle exists on the 3D grid at any given time to prevent collisions between vehicles. Simultaneously, at any time t, there must be k vehicles on the xy-section. Specifically, in some embodiments, the following task conditions can be defined to achieve path planning for multiple vehicles:

[0233] ①At any time t, there is exactly one vehicle at any location within the battery swapping site;

[0234] ② The instant battery swapping tasks for different vehicles are planned according to the order in which the vehicles arrive at the entrance of the battery swapping site. The vehicles that arrive earlier are given priority for battery swapping and will arrive at the exit of the battery swapping site. The starting point of the instant battery swapping task is the entrance of the battery swapping site, and the destination is the exit of the battery swapping site.

[0235] ③ For vehicles undertaking both immediate and scheduled battery swapping tasks, travel routes can be planned simultaneously. Scheduled battery swapping tasks require the vehicle to complete the swap and return to the temporary parking space before the set swapping time. For example, both the starting point and destination of a scheduled battery swapping task can be a temporary parking space.

[0236] ④ Any battery swapping vehicle must pass through the battery swapping location and wait at the location for one battery swapping time T. serive To enable battery swapping;

[0237] ⑤ During route planning, a vehicle may only stop at its current location and wait if it encounters another vehicle blocking its path. The continuous duration of any vehicle's stay at any location shall not exceed the automatic battery swapping time T of the battery swapping station. serive ;

[0238] ⑥ The maximum turning angle that any vehicle passes through on the travel path must be less than or equal to θ. max ;

[0239] ⑦ When multiple vehicles overlap at the same time and location within the battery swapping area, the vehicles will be coordinated to pass through at a constant speed or stop and wait according to the priority of the battery swapping task.

[0240] ⑧ While ensuring the stability of the vehicle's driving posture, optimize the maximum time for all vehicles to complete the automatic driving task.

[0241] As mentioned earlier, vehicles within the same group have the same priority, but different vehicles may have different battery swapping tasks. This results in different vehicles having different starting points and destinations. A vehicle's starting point within the target area includes any one of the following: the entrance to the target area, a battery swapping location within the target area, or a pre-set parking space within the target area. Similarly, a vehicle's destination within the target area includes any one of the following: the exit to the target area, a battery swapping location within the target area, or a pre-set parking space within the target area.

[0242] Referring to conditions ② and ③ above, for an immediate battery swapping task, the vehicle's starting point is the entrance to the battery swapping station. The vehicle's destination is the battery swapping location within the station, where it needs to stay for a specified swapping duration. After the swap, the vehicle continues to use that location as its starting point and the station's exit as its destination, thus completing the path planning for the immediate battery swapping task.

[0243] For scheduled battery swapping tasks, the vehicle's starting point is the entrance to the battery swapping station. The vehicle's initial destination is often a parking space. The vehicle first drives from the station entrance to a parking space within the station. Before the scheduled time arrives, the vehicle departs from the parking space, travels to the battery swapping location, and performs the swap. After the swap, the vehicle continues to use the same location as its starting point and the parking space as its destination. Finally, when the driver returns to retrieve the vehicle, the route continues from the parking space as the starting point and the station's exit as the destination, thus completing the route planning for the scheduled battery swapping task.

[0244] In this embodiment of the application, by setting different starting points and destinations, on the one hand, multiple vehicles in a narrow target area can be diverted to prevent congestion caused by all vehicles heading to the same destination. On the other hand, by taking the battery swapping location in the target area as a necessary central destination, the problem of long algorithm time caused by long-distance path planning can be avoided, realizing rapid planning and control of vehicle paths and improving the response speed of battery swapping requests.

[0245] Furthermore, Figure 13 This is a schematic diagram of the battery swapping process at a battery swapping station provided in an embodiment of this application, as shown below. Figure 13As shown, it includes the following steps: Step 1: The vehicle arrives at the entrance of the battery swapping station; Step 2: Vehicle image is acquired; Step 3: Battery swapping service authorization is pushed; Step 4: Battery swapping service authorization request notification is sent; Step 5: Authorization successful; Step 6: Prepare for battery swapping service; Step 7: Start battery swapping service; Step 8: Battery swapping service completes vehicle takeover; Step 9: Battery swapping service vehicle takeover successful; Step 10: Route planning is performed; Step 11: Autonomous vehicle driving and battery swapping; Step 12: Vehicle arrives at the exit; Step 13: Vehicle safely brakes and vehicle control is returned; Step 14: The driver is notified that the battery swapping service is complete and should leave as soon as possible; Step 15: Site and road information is acquired based on sensors; Step 16: Environmental perception data is transmitted; Step 17: Vehicle, people, and obstacles are monitored. Obstacle identification; Step 18: Decision-making for driving strategy using a pre-trained deep network; Step 19: Decision-making for the route of each vehicle; Step 20: Remote control of the vehicle for autonomous driving; Step 21: Collection of vehicle driving information; Step 22: Transmission of vehicle driving information; Step 23: Tracking vehicle status; Step 24: Remote control of the vehicle to execute the strategy; Step 25: Vehicle braking, notification that the battery swapping service has stopped; Step 26: Battery swapping service has been terminated early; Step 27: Sending a prompt message; Step 28: Authorization failed; Step 29: No remote control of the vehicle; Step 30: Driver drives independently; Step 31: Notification to the driver that the battery swapping service is no longer available, please drive independently; Step 32: No remote control of the vehicle; Step 33: Notification to the driver that the battery swapping service is no longer available, please drive independently.

[0246] in, Figure 14 This is a schematic diagram of the multi-vehicle route determination process provided in the embodiments of this application, such as... Figure 14As shown, it includes the following steps: Step S1410: Construct environmental location information based on the site information of the battery swapping station; Step S1420: Construct a three-dimensional shared grid map; Step S1430: Generate multiple groups according to the vehicle battery swapping task type; Step S1440: Treat multiple vehicles in each group as a corresponding task to form a task list; Step S1450: Check if the task list is empty; Step S1460: Randomly arrange each task; Step S1470: Path planning for multiple vehicles in the same group; Step S1480: If the task conditions are not met; Step S1490: Randomly generate the vehicle arrangement order; Step S14100 Step S14110: All planning is completed; Step S14120: Calculate the time required for multiple vehicles in the same group to reach their destination; Step S14130: Determine if the optimal result has been found; Step S14140: Update the optimal target of the current vehicle and save the arrangement order as the target arrangement order; Step S14150: Prepare for the iteration of the next group; Step S14160: The path planning of multiple vehicles in the same group is completed; Step S14170: Save the path planning results of multiple vehicles in the same group; Step S14180: Path planning results of multiple vehicles in multiple groups.

[0247] Furthermore, in conjunction with the above Figure 1 The battery swapping station scene shown and Figure 13 The battery swapping process shown is as follows: Figure 15 This is a schematic diagram of the route determination process for a single vehicle provided in an embodiment of this application, such as... Figure 15 As shown, it includes the following steps: Step S1510: Obtain the starting point, intermediate points to be passed, and destination of the current vehicle; Step S1520: Obtain the starting point and intermediate points to be passed of the current vehicle; Step S1530: Obtain the intermediate points and destination of the current vehicle; Step S1540: Path planning for a single vehicle with known starting point and destination; Step S1550: Merging two path segments; Step S1560: Calculating vehicle travel time.

[0248] Furthermore, when performing route planning for a single vehicle, the following algorithm can be used: Figure 16 This is a schematic diagram of the path search algorithm provided in the embodiments of this application, such as... Figure 16 As shown, it includes the following steps:

[0249] Step S1610: Define the development list and the shutdown list.

[0250] Step S1620: Add the starting point to the open list.

[0251] Step S1630: Calculate the evaluation value of each grid cell in the open list.

[0252] Step S1640: Based on the evaluation value, find the optimal raster in the open list as the target raster.

[0253] Step S1650: Add the surrounding rasters of the target raster at the current moment to the open list.

[0254] Step S1660: Add the target grid from the previous time step to the closed list.

[0255] Step S1670: Determine if the endpoint grid exists in the open list.

[0256] Step S1680: Obtain the optimal path from the starting grid to the ending grid.

[0257] For example, Figure 17 This is a schematic diagram of the path provided in the embodiments of this application, such as... Figure 17 As shown, vehicle 1 and vehicle 2 start from different starting points and navigate around obstacles ( Figure 17 After passing through the black-filled area, the vehicle will pass through point A for battery swapping. After the battery swapping is completed, it will exit from the battery swapping station.

[0258] In this embodiment, a three-dimensional grid map is constructed by introducing a spatiotemporal dimension and combining latitude and longitude. Expanding from a two-dimensional grid map to a three-dimensional grid map with a spatiotemporal dimension, it depicts / records the transfer states of multiple vehicles, more clearly expressing vehicle start / stop actions. This provides a reference for the traffic status of each grid at different times for path planning, enabling the algorithm to coordinate with other vehicles to complete obstacle avoidance while planning vehicle paths and optimizing obstacle avoidance time. Simultaneously, by sharing the position information between vehicles at each time point through a hash table, the storage consumption required for the three-dimensional grid map is effectively reduced. Furthermore, by using multiple preset evaluation indicators and calculation methods, the evaluation process of the evaluation function is changed, and the algorithm can also support the expansion of more optimization targets. Finally, it supports multiple vehicles simultaneously planning paths for various task types, optimizing the maximum time for all vehicles to complete the autonomous driving task while ensuring the smoothness of the driving path.

[0259] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0260] Figure 18 This is a schematic diagram of the vehicle driving path determination device provided in an embodiment of this application. The vehicle driving path determination device can be integrated into an electronic device, or it can be implemented independently of and in conjunction with an electronic device to achieve this solution. Figure 18 As shown, the vehicle driving path determination device 1800 includes an acquisition module 1810, a status determination module 1820, and a path determination module 1830.

[0261] The acquisition module 1810 is used to acquire the starting point, destination, and grid map corresponding to the target area for at least two vehicles in the same group within the target area.

[0262] The grid map consists of i rows and j columns of grids. The size of each grid corresponds to the size of the area occupied by each vehicle in the target area, where i and j are positive integers.

[0263] The status determination module 1820 is used to determine the passage status of each grid in the grid map at each time based on the target objects present in the target area at each time.

[0264] The route determination module 1830 is used to determine the travel route of each vehicle from the origin to the destination based on the traffic status of each grid at each time.

[0265] Optionally, the path determination module may include a grid determination module, which is used to determine the target grid that each vehicle needs to pass through to move from the starting grid to the ending grid in the grid map based on the traffic status of each grid at each time; and to determine the driving path of each vehicle from the starting point to the destination based on the target grid that each vehicle needs to pass through to move from the starting grid to the ending grid in the grid map.

[0266] The starting grid is the grid cell corresponding to the starting point in the grid map, and the ending grid cell is the grid cell corresponding to the destination in the grid map.

[0267] Optionally, the grid determination module can be used to: randomly sort at least two vehicles to obtain at least one sorting order; determine the target grid that each vehicle in the same sorting order needs to experience based on the traffic status of each grid at each time; determine the travel time required for all vehicles in the same sorting order to reach their corresponding destination based on the target grid that each vehicle in the same sorting order needs to experience and the preset speed; and determine the target sorting order and the target grid that each vehicle in the target sorting order needs to experience in at least one sorting order based on the travel time corresponding to different sorting orders.

[0268] Optionally, the grid determination module can be used to: determine the target grid that the first N-1 vehicles in the same arrangement order need to pass through based on the passage status of each grid at each time; update the passage status of each grid at each time based on the target grid that the first N-1 vehicles need to pass through; and determine the target grid that the Nth vehicle in the same arrangement order needs to pass through based on the updated passage status of each grid at each time.

[0269] Where N is a positive integer greater than 1 and less than or equal to the total number of vehicles in the group.

[0270] Optionally, the grid determination module can be specifically used to: obtain the first grid where the vehicle was located at the previous time and at least one second grid adjacent to the first grid; determine the grid where the vehicle is located at the next time from the first grid and at least one second grid based on the traffic status of the at least one adjacent second grid; and determine the target grid that the vehicle needs to pass through to move from the starting grid to the ending grid in the grid map based on the vehicle's starting grid and the grid where the vehicle is located at each time.

[0271] Optionally, a filtering module is also included, for obtaining the vehicle's steering angle range; determining the vehicle's movable grid range at the next moment based on the vehicle's steering angle range; and filtering out at least one adjacent second grid that is not within the movable grid range.

[0272] Optionally, the grid determination module can be used to: obtain the evaluation value of each second grid based on the traffic status of each second grid and a preset evaluation index; and determine the grid where the vehicle is located at the next moment in the first grid and at least one second grid based on the evaluation value.

[0273] Optionally, the grid determination module can be used to: obtain the cost of a vehicle moving to the second grid at the next moment based on the traffic status of the second grid; and determine the evaluation value of the second grid based on the cost.

[0274] The cost includes at least one of the following: the waiting time required to move to the second grid at the next moment, the number of consecutive waiting times required to move to the second grid, the time required to move from the second grid to the end grid after moving to the second grid, the time required to move from the starting grid to the second grid, the maximum value of the turning angle required to move from the second grid to the end grid after moving to the second grid, and the turning angle required to move to the second grid.

[0275] Optionally, the state determination module can be used to: determine that the grid corresponding to the first area of ​​the target area is in a waiting state when there is a vehicle parked in the first area at the first time; determine that the grid corresponding to the first area is in an impassable state when there is a fixed obstacle in the first area; and determine that the grid corresponding to the first area is in a passable state when there is no fixed obstacle or vehicle in the first area at the second time.

[0276] Optionally, it also includes a map building module for obtaining the length and turning angle range of each vehicle; determining the size of the grid in the grid map based on the length and turning angle range of each vehicle; and constructing a grid map corresponding to the target area based on the grid size.

[0277] Optionally, the grid determination module can be used to: obtain the location information of each grid in the grid map corresponding to the location in the target area and the passage status of each grid at each time; obtain the target time corresponding to the passable status and waiting status at each time; construct a hash table corresponding to each grid based on the target time and the location information of each grid corresponding to the location in the target area; and determine the passage status of each grid in the grid map at each time based on the hash table corresponding to each grid.

[0278] Optionally, the acquisition module can be used to: acquire battery swapping requests initiated by at least two vehicles within the target area; determine the priority of each vehicle based on its battery swapping request; group vehicles with the same priority into the same group; and group vehicles with different priorities into different groups.

[0279] Optionally, the starting point of the vehicle in the target area includes any one of the entrance of the target area, the battery swapping location in the target area, and the preset parking space in the target area, and the destination of the vehicle in the target area includes any one of the exit of the target area, the battery swapping location in the target area, and the preset parking space in the target area.

[0280] Optionally, a control module is also included, which is used to obtain the target arrangement order of at least two vehicles in the same group; according to the target arrangement order, each vehicle is controlled to travel to the corresponding destination according to the corresponding driving path.

[0281] The apparatus provided in this application embodiment can be used to execute the methods in the above embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0282] This application also provides a battery swapping system, which includes a control device and at least one sensor. The sensor is used to acquire vehicle information of each vehicle in a target area, and the target area includes multiple vehicles. The control device is used to acquire vehicle information and execute the above-described method.

[0283] Furthermore, the sensors include image sensors and radar sensors. Image sensors are used to acquire image information about the vehicle; radar sensors are used to acquire the vehicle's location information.

[0284] Furthermore, at least one battery swapping station is set up in the target area, and the control equipment is also used to control the vehicle to drive to the battery swapping station for battery swapping based on the vehicle's vehicle information.

[0285] Furthermore, the target area is also equipped with at least one parking space, at least one entrance, and at least one exit;

[0286] Furthermore, the control equipment can determine the origin and destination from at least one parking space, at least one entrance, at least one exit, and at least one battery swapping station based on the vehicle's information, and control the vehicle to travel from the origin to the destination.

[0287] Furthermore, sensors are installed at entrances, exits, and parking spaces.

[0288] Figure 19 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. Figure 19 As shown, the electronic device 1900 may include a processor 1901 and a memory 1902 storing computer program instructions.

[0289] Specifically, the processor 1901 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0290] Memory 1902 may include mass storage for data or instructions. For example, and not as a limitation, memory 1902 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these.

[0291] Where appropriate, memory 1902 may include removable or non-removable (or fixed) media. Where appropriate, memory 1902 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 1902 is a non-volatile solid-state memory.

[0292] Memory 1902 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory 1902 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any of the methods described in the above embodiments. Processor 1901 implements any of the methods in the above embodiments by reading and executing computer program instructions stored in memory 1902.

[0293] In one example, the electronic device 1900 may also include a communication interface 1903 and a bus 1904. For example... Figure 19 As shown, the processor 1901, memory 1902, and communication interface 1903 are connected via bus 1904 and communicate with each other.

[0294] The communication interface 1903 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0295] Bus 1904 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 1904 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0296] Furthermore, in conjunction with the methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement the methods in the above embodiments.

[0297] This application also provides a computer program product, including a computer program, which, when executed, implements any of the methods described in the above embodiments.

[0298] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0299] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0300] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0301] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0302] Unless otherwise specified, all embodiments and optional embodiments of this application can be combined to form new technical solutions.

[0303] Unless otherwise specified, all technical features and optional technical features of this application may be combined to form new technical solutions.

[0304] Unless otherwise specified, all steps of this application may be performed sequentially or randomly, preferably sequentially. For example, if the method includes steps (a) and (b), it means that the method may include steps (a) and (b) performed sequentially, or it may include steps (b) and (a) performed sequentially. For example, if the method may also include step (c), it means that step (c) may be added to the method in any order. For example, the method may include steps (a), (b), and (c), or it may include steps (a), (c), and (b), or it may include steps (c), (a), and (b), etc.

[0305] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for determining a vehicle's driving path, characterized in that, include: Obtain the starting point, destination, and corresponding grid map of the target area for at least two vehicles in the same group within the target area. The grid map consists of i rows and j columns of grids, and the size of each grid corresponds to the size of the area occupied by each vehicle in the target area. i and j are positive integers. Based on the target objects present in the target area at each time, determine the passage status of each grid cell in the grid map at each time. Based on the traffic status of each grid at each moment, determine the travel path of each vehicle from the starting point to the destination.

2. The method according to claim 1, characterized in that, The step of determining the travel path of each vehicle from the starting point to the destination based on the traffic status of each grid at each time includes: Based on the traffic status of each grid at each moment, the target grid that each vehicle needs to pass through to move from the starting grid to the destination grid in the grid map is determined. The starting grid is the grid corresponding to the starting point in the grid map, and the destination grid is the grid corresponding to the destination in the grid map. The travel path of each vehicle from the starting point to the destination is determined based on the target grids that each vehicle needs to pass through to move from the starting grid to the ending grid in the grid map.

3. The method according to claim 2, characterized in that, The step of determining the target grids that each vehicle needs to traverse from the starting grid to the ending grid in the grid map, based on the traffic status of each grid at each time moment, includes: Randomly sort the at least two vehicles to obtain at least one sorting order; Based on the passage status of each grid at each moment, determine the target grid that each vehicle needs to pass through in the same sequence. Based on the target grid that each vehicle in the same arrangement needs to pass through and the preset speed, determine the travel time required for all vehicles in the same arrangement to reach their corresponding destinations. Based on the driving time corresponding to different arrangement orders, a target arrangement order and a target grid that each vehicle needs to traverse in the at least one arrangement order are determined.

4. The method according to claim 3, characterized in that, The step of determining the target grid that each vehicle needs to traverse in the same sequence based on the traffic status of each grid at each time includes: Based on the passage status of each grid at each time moment, determine the target grid that the first N-1 vehicles in the same arrangement order need to pass through, where N is a positive integer greater than 1 and less than or equal to the total number of vehicles in the group; Update the passage status of each grid at each time step based on the target grid that the first N-1 vehicles need to pass through; Based on the updated passage status of each grid at each time moment, determine the target grid that the Nth vehicle in the same arrangement order needs to pass through.

5. The method according to claim 2, characterized in that, Determining the target grids that each vehicle needs to traverse from the starting grid to the ending grid in the grid map includes: Obtain the first grid cell where the vehicle was located at the previous time step and at least one second grid cell adjacent to the first grid cell; Based on the passage status of the at least one adjacent second grid, determine the grid in which the vehicle is located at the next moment among the first grid and the at least one second grid; Based on the vehicle's starting grid and the grid where the vehicle is located at each moment, determine the target grid that the vehicle needs to pass through to move from the starting grid to the ending grid in the grid map.

6. The method according to claim 5, characterized in that, Also includes: Obtain the range of steering angles of the vehicle; Based on the vehicle's steerable angle range, determine the movable grid range of the vehicle at the next moment; The second grid cells that are not within the range of the movable grid cells in at least one of the adjacent second grid cells are filtered out.

7. The method according to claim 5, characterized in that, Determining the grid where the vehicle is located at the next moment among the first grid and the at least one second grid based on the traffic status of the adjacent at least one second grid includes: Based on the passage status of each second grid and the preset evaluation index, obtain the evaluation value of each second grid; Based on the evaluation value, the grid in which the vehicle is located at the next moment is determined among the first grid and the at least one second grid.

8. The method according to claim 7, characterized in that, The step of obtaining the evaluation value of each second grid cell based on the passage status of each second grid cell and the preset evaluation index includes: Based on the traffic status of the second grid, the cost for the vehicle to move to the second grid at the next moment is obtained. The cost includes at least one of the following: the waiting time required to move to the second grid at the next moment, the number of consecutive waiting times required to move to the second grid, the time required to move from the second grid to the destination grid after moving to the second grid, the time required to move from the starting grid to the second grid, the maximum value of the steering angle required to move from the second grid to the destination grid after moving to the second grid, and the steering angle required to move to the second grid. The evaluation value of the second grid is determined based on the cost.

9. The method according to any one of claims 1-8, characterized in that, The step of determining the accessibility status of each grid cell in the grid map at each time step, based on the target objects present in the target area at each time step, includes: If a vehicle is parked in the first area of ​​the target area at the first moment, the grid corresponding to the first area at the first moment is determined to be in a waiting state. If there are fixed obstacles in the first area, the grid corresponding to the first area is determined to be impassable at each time. If there are no fixed obstacles or vehicles in the first area at the second time, the grid corresponding to the first area at the second time is determined to be passable.

10. The method according to any one of claims 1-8, characterized in that, Also includes: Obtain the length and turning angle range of each vehicle; The size of the grid in the grid map is determined based on the length and turning angle range of each vehicle; Based on the size of the grid, construct a grid map corresponding to the target area.

11. The method according to any one of claims 1-8, characterized in that, The step of determining the accessibility status of each grid cell in the grid map at each time step, based on the target objects present in the target area at each time step, includes: Obtain the location information of each grid cell in the grid map corresponding to the location in the target area and the traffic status of each grid cell at each time. At each of the stated times, the target times corresponding to the passable state and the waiting state are obtained; Based on the target time and the position information of each grid in the target area, construct a hash table corresponding to each grid. Based on the hash table corresponding to each grid cell, the accessibility status of each grid cell in the grid map at each time step is determined.

12. The method according to claim 1, characterized in that, The acquisition of at least two vehicles in the same group includes: Obtain battery swapping requests initiated by at least two vehicles within the target area; The priority of each vehicle is determined based on its battery swapping request. Vehicles with the same priority will be grouped together. Vehicles with different priorities are grouped into different groups.

13. The method according to claim 1, characterized in that, The starting point of the vehicle in the target area includes any one of the entrance of the target area, the battery swapping location in the target area, and the preset parking space in the target area. The destination of the vehicle in the target area includes any one of the exit of the target area, the battery swapping location in the target area, and the preset parking space in the target area.

14. The method according to claim 1, characterized in that, Also includes: Obtain the target arrangement order of at least two vehicles in the same group; Based on the order of the targets, each vehicle is controlled to travel to its corresponding destination along its designated path.

15. A vehicle travel path determination device, characterized in that, include: The acquisition module is used to acquire the starting point, destination and grid map corresponding to the target area for at least two vehicles in the same group within the target area. The grid map includes i rows and j columns of grids, and the size of each grid corresponds to the size of the area occupied by each vehicle in the target area, where i and j are positive integers. The status determination module is used to determine the passage status of each grid in the grid map at each time based on the target objects present in the target area at each time. The route determination module is used to determine the travel route of each vehicle from the starting point to the destination based on the traffic status of each grid at each time.

16. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-14.

17. A readable storage medium, characterized in that, The readable storage medium stores computer program instructions that, when executed by a processor, implement the method as described in any one of claims 1-14.

18. A computer program product, characterized in that, When the instructions in a computer program product are executed by the processor of an electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1-14.

Images