Path planning method, vehicle and electronic equipment

Abstract

The present invention discloses a path planning method, vehicle, and electronic device. The method includes: obtaining entrance and exit information of a work area, as well as spatial orientation information of multiple work positions; generating multiple candidate paths based on the entrance and exit information and spatial orientation information; determining a first-type main road based on the first-type candidate lanes in the multiple candidate paths, and determining a second-type main road based on the second-type candidate lanes in the multiple candidate paths; merging at least a portion of the first-type candidate lanes in each candidate path into the first-type main road, and merging at least a portion of the second-type candidate lanes in each candidate path into the second-type main road, to generate a target path; and sending the target path to a target vehicle. The present invention solves the technical problem of poor path planning effectiveness in related technologies.

Description

Technical Field

[0001] The present invention relates to the fields of vehicles and path planning, and in particular to a path planning method, a vehicle, and electronic equipment. Background Art

[0002] With the development of intelligent driving technology, path planning is key to ensuring efficient and safe vehicle operation. This is especially true in industrial automation environments such as open-pit mines, where the large number of vehicles in the operating area, limited space, and complex obstacles create frequent vehicle operations. This places higher demands on the real-time, accurate, and safe nature of path planning.

[0003] In related technologies, path planning decisions are made through mutual communication between vehicles to prompt vehicles to avoid or detour in a timely manner. However, this planning method has limited ability to cope with complex driving scenarios. As the number of vehicles increases, paths are prone to intersecting, making it difficult for vehicles to drive according to the planned path. It can also lead to congestion, insecurity, and other situations, resulting in poor path planning results.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] Embodiments of the present invention provide a path planning method, a vehicle, and an electronic device to at least solve the technical problem of poor path planning effect in related technologies.

[0006] According to one aspect of an embodiment of the present invention, a path planning method is provided, comprising: obtaining entrance and exit information of a work area, and spatial orientation information of a plurality of work positions, wherein the entrance and exit information includes an entrance position and an exit position of the work area; generating a plurality of candidate paths based on the entrance and exit information and the spatial orientation information, wherein each candidate path comprises a first type candidate lane for connecting the corresponding work position with the entrance position and a second type candidate lane for connecting the corresponding work position with the exit position; determining a first type main road based on the first type candidate lanes in the plurality of candidate paths, and determining a second type main road based on the second type candidate lanes in the plurality of candidate paths; merging at least a portion of the first type candidate lanes in each candidate path into the first type main road, and merging at least a portion of the second type candidate lanes in each candidate path into the second type main road, to generate a target path; and sending the target path to a target vehicle.

[0007] According to another aspect of an embodiment of the present invention, a path planning method is also provided, including: receiving a target path, wherein the target path is generated by merging at least part of a first type candidate lane in each candidate path among multiple candidate paths into a first type main road, and merging at least part of a second type candidate lane in each candidate path into a second type main road, the first type main road is determined based on the first type candidate lanes in the multiple candidate paths, the second type main road is determined based on the second type candidate lanes in the multiple candidate paths, the multiple candidate paths are generated based on entrance and exit information of the work area and spatial orientation information of multiple work positions, the entrance and exit information includes the entrance position and exit position of the work area, each candidate path includes a first type candidate lane for connecting the corresponding work position with the entrance position and a second type candidate lane for connecting the corresponding work position with the exit position; driving according to the target path.

[0008] According to another aspect of an embodiment of the present invention, a vehicle is also provided, including: a communication unit for communicating with a cloud server or a target vehicle; a memory storing an executable program; and a processor for running the program, wherein the method of each embodiment of the present invention is executed when the program is running.

[0009] According to another aspect of an embodiment of the present invention, an electronic device is provided, including: a communication unit for communicating with a target vehicle; a memory storing an executable program; and a processor for running the program, wherein the method of each embodiment of the present invention is executed when the program is running.

[0010] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0011] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0012] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0013] According to another aspect of an embodiment of the present invention, a computer program is provided. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0014] In an embodiment of the present invention, entrance and exit information of a work area and spatial orientation information of a plurality of work positions are obtained; a plurality of candidate paths are generated based on the entrance and exit information and the spatial orientation information; a first type of main road is determined based on the first type of candidate lanes in the plurality of candidate paths, and a second type of main road is determined based on the second type of candidate lanes in the plurality of candidate paths; at least a portion of the first type of candidate lanes in each candidate path is merged into the first type of main road, and at least a portion of the second type of candidate lanes in each candidate path is merged into the second type of main road to generate a target path; and the target path is sent to a target vehicle. It is easy to notice that two types of candidate lanes are generated through entrance and exit information and spatial orientation information to cover the complete path from the entrance to the work position and from the work position back to the exit, and in the scenario of multiple work positions, a path planning method that merges the main road and the lane is introduced. By planning and defining a main road, the path can be planned with the main road as the core, and then at least part of the candidate lane is merged into the main road to generate the target path, achieving the purpose of orderly planning the path, thereby realizing the technical effect of improving the driving effect of path planning, and then solving the technical problem of poor path planning effect in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0016] Figure 1 is a flow chart of a path planning method according to an embodiment of the present invention;

[0017] Figure 2 is a schematic diagram of an optional driving according to a planned path according to an embodiment of the present invention;

[0018] Figure 3 is a flow chart of an optional path planning method according to an embodiment of the present invention;

[0019] Figure 4 is a schematic diagram of an optional path planning device according to an embodiment of the present invention;

[0020] Figure 5 is a schematic diagram of an optional path planning device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to an embodiment of the present invention, a method embodiment of a path planning method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] Figure 1 is a flow chart of a path planning method according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0025] Step S102: obtaining the entrance and exit information of the working area and the spatial orientation information of multiple working positions.

[0026] The entrance and exit information includes the entrance and exit locations of the work area.

[0027] The above-mentioned working area can be a loading area for loading operations. The working area can be in an open-pit mine or in a tunnel. The location of the working area is not limited here and can be determined as needed. The working area can include multiple loading points so that vehicles such as mining trucks can leave the working area for transportation activities after completing loading at the loading point. The working area can be rectangular, irregular polygonal or other shapes. The shape of the working area is not limited and can be determined as needed. This depends on the terrain and operation layout of the mine. The working area can also be divided into multiple sub-areas, each sub-area corresponding to one or more excavators for operation. The working area defines the boundaries and scope of the operation, which helps to understand the specific environment of vehicle path planning and multi-vehicle collaborative operation, and provides a clear geographic spatial framework for the path planning method.

[0028] The aforementioned workstations are specific locations within the work area where loading operations are performed. In a multi-excavator scenario, each excavator has one or more corresponding workstations, allowing them to operate independently without interfering with each other. Mining trucks and other vehicles must accurately access these workstations for loading. Workstations can be static, meaning the excavator is fixed in position, or dynamic, meaning the excavator moves within the work area based on operational needs. In this case, mining trucks and other vehicles must track the excavator's position in real time. Workstations are defined by position coordinates (X, Y, Z) and an orientation angle (θ). Workstations can also be determined by preconfigured codes. Workstations serve as the endpoints and starting points of path planning, ensuring that mining trucks can efficiently and safely reach the loading station for loading. Once loading is complete, they can depart along the adapted path to avoid conflicts with other mining trucks or equipment.

[0029] The aforementioned entrance and exit information can include the entrance and exit locations of the work area. Entrance and exit information can be the channels through which mining trucks enter and exit the work area. Entrances and exits can be one-way, with separate entrances and exits, allowing mining trucks and other vehicles to enter and exit only through the entrances. Entrances and exits can also be bidirectional, meaning the same location can serve as both an entrance and an exit. Entrance and exit information is crucial for route planning. It determines the initial and final routes for mining trucks and other vehicles, helping to design conflict-free traffic flow routes and improve operational efficiency and safety in the work area.

[0030] The above-mentioned spatial orientation information may refer to the relative position and orientation angle of the working area. Spatial orientation information may include but is not limited to position, orientation, lane layout, obstacle distribution, etc. The content of the spatial orientation information is not limited here and can be determined as needed. Spatial orientation information can be static, such as a fixed road layout; spatial orientation information can also be dynamic, such as the real-time position information and relative angle of mining trucks and excavators. Spatial orientation information is the basis for realizing collaborative path planning of mining trucks. It helps to understand the relative position relationship of each element in the working area and design a path to avoid collisions and improve efficiency. In addition, dynamic spatial orientation information also supports real-time scheduling and path adjustment between mining trucks and excavators to cope with changes in the working environment.

[0031] In an optional embodiment, the Global Positioning System (GPS) and LiDAR can be used to obtain entrance and exit information for the work area and the spatial orientation information of multiple workstations. Vehicles can be equipped with GPS receivers to record their location information in real time. GPS reference points are also set at the entrances and exits of the work area and at each workstation to determine the precise coordinates of these entrances and exits and workstations. The vehicle's LiDAR can then periodically scan the surrounding environment, including the entrances and exits and the terrain features near the workstations. By analyzing the LiDAR data, a three-dimensional map of the work area can be constructed, thereby determining the exact spatial relationship between the entrances and exits and the workstations. Furthermore, the GPS data and terrain feature data from the LiDAR scans can be fed into a computing platform for fusion processing to generate a digital map of the work area, clearly marking the entrance and exit information and the spatial orientation information of each workstation.

[0032] In another optional embodiment, entrance and exit information, as well as the spatial orientation information of multiple workstations, can also be obtained from data recorded by drones. The drone is equipped with a camera and can fly over the work area according to a pre-set flight path, capturing images of every corner of the work area, particularly near entrances and exits and workstations. The images captured by the drone are processed by image recognition software to automatically identify the specific locations of entrances and exits, as well as the spatial orientation information of each workstation. Furthermore, through in-depth analysis of the images, detailed data on the topography of the work area can be obtained. The image data and analysis results recorded by the drone can be integrated into a database and transmitted in real time to the vehicle's autonomous driving system, so that the actual layout of entrances and exits and workstations can be considered during route planning.

[0033] In another optional embodiment, entrance and exit information and the spatial orientation information of multiple workstations can be obtained from a pre-planned and configured data information management system. Satellite remote sensing and drone aerial photography can be used to obtain a three-dimensional terrain model of the work area. This three-dimensional terrain model includes, but is not limited to, information such as surface relief, vegetation cover, and geological structure. Then, combined with topographic mapping data, the locations of entrances and exits within the work area are planned to ensure accessibility and safety. Simultaneously, multiple workstations are rationally arranged. Positioning markers, such as radio frequency identification (RFID) tags, QR codes, and GPS beacons, are installed at the planned entrances and exits and workstations. These positioning markers provide precise geographic coordinate information. These positioning markers and corresponding information are then entered into the data information management system for easy access when needed. However, given that the work area may change due to temporary work requirements, equipment maintenance, weather conditions, and other factors, data and information in the data information management system can be updated by on-site staff using handheld devices, or by using automated equipment (such as drones) for real-time scanning and confirmation, with automatic synchronization to the data information management system.

[0034] Step S104: Generate multiple candidate paths based on the entrance and exit information and the spatial orientation information.

[0035] Each candidate path includes a first type candidate lane for connecting the corresponding work position and the entrance position and a second type candidate lane for connecting the corresponding work position and the exit position.

[0036] The candidate paths described above may include first-type candidate lanes and second-type candidate lanes. A candidate path can be a possible route option planned for a vehicle in an autonomous driving or intelligent transportation system. In collaborative path planning for mining trucks in the loading area of an open-pit mine, candidate paths can include empty and loaded lanes corresponding to the excavator. The generation and function of candidate paths are particularly critical, as they not only affect the operating efficiency of mining trucks but also directly affect the safety of the work area. Candidate paths can be determined based on entrance and exit information and spatial orientation information to guide vehicles from the entrance to the work area, or from the work area to the exit.

[0037] The aforementioned first-type candidate lanes can be used to connect workstations with entrances. First-type candidate lanes may have different attributes, such as lane width, slope, turning radius, and load capacity. These attributes are not specified here and can be determined as needed, depending on the specific topography and transportation requirements of the work area. Furthermore, depending on the layout and number of workstations, lane types can be linear, circular, or branched. These lane types are not specified here and can be determined as needed. Generating first-type candidate lanes can reduce the time and energy consumption required for vehicles to enter workstations, avoid unnecessary travel while searching for workstations, and ensure safe driving when entering the work area, reducing the possibility of accidents. The generation of first-type candidate lanes typically considers factors such as the spatial orientation of the entrance and workstations, as well as the minimum turning radius and sufficient safety distance, ultimately forming a lane layout suitable for accessing the workstations. Furthermore, actual lane availability must be verified through on-site surveys to ensure consistency with the planning model.

[0038] The aforementioned second-type candidate lanes can be used to connect the work area with the exit. In contrast to the first-type lanes, the second-type candidate lanes are used to plan routes for vehicles leaving the work area after completing their work. The selection of the second-type candidate lanes must take into account the vehicle's load status when leaving the work area, the distribution of exits from the work area, and the expected traffic flow. This ensures a smooth, unobstructed path for vehicles like mining trucks leaving the work area, avoiding congestion and collisions. Generating the second-type candidate lanes improves the efficiency of mining trucks' post-operation evacuation, reducing waiting and dwell time. It also ensures orderly and safe traffic flow at the work area exit, avoiding the tail effect, whereby mining trucks remain in the work area for extended periods after completing their work, leading to exit congestion. Similar to the first-type candidate lanes, the second-type candidate lanes can be determined based on exit information and spatial orientation information. These can be designed using traffic engineering software and adjusted based on actual site conditions. Of particular note, since mining trucks may be fully loaded when leaving the work area, lane design must also consider the impact of the vehicle's center of gravity shift on driving stability to ensure the road's load capacity and safety.

[0039] In an alternative embodiment, the work area is viewed as a graph, where nodes represent key locations such as entrances and exits and workstations, and edges represent paths connecting these locations. Each edge is assigned a specific weight (e.g., distance, time required, energy consumption, etc.). A graph search algorithm, such as Dijkstra's algorithm or depth-first search, is used to explore paths from any entrance or exit to one or more workstations. The Dijkstra algorithm works by finding the shortest path from one vertex to all other vertices in a weighted graph.

[0040] In another optional embodiment, a machine learning model, such as a neural network or reinforcement learning, can be trained to identify the spatial orientation of entrances, exits, and workstations and predict multiple possible candidate paths. The machine learning model can be trained using a large amount of historical driving data and path planning so that it can learn effective paths. By learning from historical behavior patterns and environmental characteristics, the machine learning model can generate candidate paths that better meet actual needs. Reinforcement learning can continuously adjust the path selection strategy to adapt to dynamic changes in the environment, such as changes in traffic flow or temporary adjustments to workstations.

[0041] In another alternative embodiment, virtual reality or augmented reality technology can be combined with physical world entrance and exit information and spatial orientation information to create a virtual work area model, which can be used to generate and visualize multiple candidate paths in real time. This allows users to intuitively see the effects of each candidate path in the virtual environment and adjust or select it based on actual needs.

[0042] Step S106 : determining a first type of main road based on the first type of candidate lanes in the plurality of candidate paths, and determining a second type of main road based on the second type of candidate lanes in the plurality of candidate paths.

[0043] The aforementioned first-type main roads can be used to guide vehicles from the entrance to the work area. A first-type main road can be the only way for vehicles to enter the work area. In specific applications, a first-type main road can be an unloaded lane before the excavator's turning lane. It is typically a common section of road from the entrance to multiple work areas. This first-type main road can provide a standardized driving path, reducing uncertainty for unloaded mining trucks entering the work area and searching for their work area, thereby shortening the time it takes to reach the work area. Furthermore, planning this first-type main road can avoid potential traffic conflicts and improve traffic safety within the work area.

[0044] The aforementioned second-type main roads can be used to guide vehicles from work stations to exits. These roads can be the only way vehicles must travel from a work station to an exit. Specifically, they can be heavy-load lanes preceding excavator turn lanes. These roads are typically common sections of road leading from multiple work stations to exits. These second-type main roads provide a standardized driving path, reducing uncertainty for heavy-loaded mining trucks when leaving work stations and thus shortening departure times. Furthermore, planning these second-type main roads can avoid potential traffic conflicts and improve traffic safety within the work area.

[0045] In an optional embodiment, a first type of main road is determined based on a first type of candidate lane in a plurality of candidate paths by a first preset rule. The first preset rule may be a priority for evaluating lanes. The preset rule may be manually set. The first type of main road is determined by the first preset rule, such as lane length, preference for straight sections, avoidance of continuous turns, and ensuring lane width. Furthermore, a second type of main road may also be determined based on a second type of candidate lane in a plurality of candidate paths by a second preset rule. The second type of main road is determined by the second preset rule, such as lane length, preference for straight sections, avoidance of continuous turns, and ensuring lane width.

[0046] In another optional embodiment, a cluster analysis can be performed on all first-type candidate lanes to identify those parts that are often shared by multiple paths. Based on these shared parts, a center point or a center path is determined as a first-type main road. For the first-type candidate lanes, a clustering algorithm can be used to group them and identify frequently used sections. From the clustering results, one or several center points are determined, and these points are connected to form the first-type candidate lanes. In addition, a cluster analysis can be performed on all second-type candidate lanes to identify those parts that are often shared by multiple paths. Based on these shared parts, a center point or a center path is determined as a second-type main road. For the second-type candidate lanes, a clustering algorithm can be used to group them and identify frequently used sections. From the clustering results, one or several center points are determined, and these points are connected to form the second-type candidate lanes.

[0047] In another optional embodiment, experts can determine the first type of main road from the first type of candidate lanes and the second type of main road from the second type of candidate lanes based on their experience. Expert planning can integrate expertise in fields such as mine operations, safety management, and vehicle engineering to improve the overall quality of path planning. Faced with the ever-changing mining operating environment, expert planning can respond promptly and adjust path planning strategies to meet new challenges. Expert planning can also identify potential safety risks, allowing preventive measures to be taken during path planning to reduce the incidence of accidents.

[0048] Step S108 : Merge at least a portion of the first type candidate lanes in each candidate path into the first type main road, and merge at least a portion of the second type candidate lanes in each candidate path into the second type main road, to generate a target path.

[0049] The target path described above can refer to the route determined for a target vehicle in a multi-lane, multi-station layout. This path is designed to ensure that vehicles can efficiently and safely travel from the entrance to the station and back to the exit. By avoiding congestion and obstacles and adjusting turning radius, the target path reduces vehicle travel time and energy consumption, thereby improving operational efficiency. By generating a target path, vehicles can adhere to safety regulations during movement, reducing the risk of accidents. In multi-vehicle environments, the target path helps avoid head-on collisions, i.e., conflicts between vehicle paths, and ensures smooth traffic flow.

[0050] In an optional embodiment, artificial intelligence technologies such as deep learning or genetic algorithms can be used to intelligently analyze first-type candidate lanes and automatically merge them into first-type main roads, as well as second-type candidate lanes and automatically merge them into second-type main roads, to generate a target path. Specifically, a deep learning model is trained using historical driving data, lane geometry information, and vehicle performance data to understand the impact of different candidate lanes on the target path. The deep learning model analyzes the candidate lanes and predicts the performance indicators of the merged main road (such as overall travel time and energy consumption). This determines which first-type candidate lanes in each candidate path should be merged into the first-type main road, and which second-type candidate lanes in each candidate path should be merged into the second-type main road. The lane merging solutions recommended by the deep learning model are verified in a virtual simulation environment, and manual adjustments are made as needed to ultimately determine the target path.

[0051] In another optional embodiment, a multi-objective algorithm can be used to transform the lane merging problem into a mathematical problem that incorporates multiple objectives (e.g., time, energy consumption, and safety) to generate a target path. For the first type of candidate lanes, a feature matrix is generated that contains their attributes (length, width, slope, turning radius, etc.) and their corresponding performance indicators (e.g., travel time, expected energy consumption). A multi-objective function is established: multiple objectives are set, such as minimizing total travel time, reducing energy consumption, maximizing safety, etc., and these objectives are converted into mathematical expressions. The multi-objective algorithm is applied to solve a first type candidate lane solution that can simultaneously meet or balance multiple objectives. Similarly, a second type candidate lane solution is solved that can simultaneously meet or balance multiple objectives. Then, the first and second type candidate lane solutions are combined to obtain the target path.

[0052] In another optional embodiment, an adaptive lane allocation and merging algorithm can be used to dynamically evaluate and merge first- and second-type candidate lanes based on real-time traffic flow and road conditions to generate a target path. Traffic flow, speed, road condition, and other information for each first- and second-type candidate lane can be collected in real time through onboard sensors and vehicle-to-vehicle (V2V) communication. Based on this real-time information, each first- and second-type candidate lane is scored, taking into account its current driving efficiency, safety, and contribution to the overall operational process. Based on the lane score and vehicle type (empty or loaded), the first- and second-type candidate lanes are dynamically selected for merging to determine the target path.

[0053] Step S110: sending the target path to the target vehicle.

[0054] The target vehicles mentioned above can be vehicles traveling along the target route to complete a task. In cloud platform applications, the target vehicles can be all vehicles performing a task, a single vehicle, or multiple vehicles performing tasks. There is no limit on the number of target vehicles. In other words, unified task allocation can be achieved through the cloud platform's associated target vehicles. The cloud platform analyzes the task execution status of all vehicles and distributes the respective routes to the corresponding vehicles. Target vehicles can be either unloaded or fully loaded, and their status influences route planning decisions. An unloaded target vehicle can be a mining truck that has completed unloading or is awaiting loading. A fully loaded target vehicle can be a mining truck that has completed loading and is preparing to return to the unloading point or exit. By monitoring the location and status of target vehicles in real time, their route planning can be dynamically adjusted to respond to emergencies or adjust the overall operational process.

[0055] In an optional embodiment, the target path can be transmitted to the target vehicle via a wireless communication network. Specifically, the target path can be converted into a digital code or coordinate sequence for easy network transmission. To prevent data interception or tampering by third parties, the digital code or coordinate sequence can be encrypted and securely transmitted to the target vehicle via the wireless network. After receiving the encrypted data, the target vehicle uses the corresponding key to decode it and display the target path to the driver assistance system or automated navigation system.

[0056] In another optional embodiment, radio frequency identification technology and a global positioning system can be combined to arrange RFID readers at key locations. When a vehicle passes by, the identification information stored on the vehicle's RFID tag is automatically read, and the vehicle's position is determined through GPS positioning, and the target path is then sent to the vehicle.

[0057] In another optional embodiment, vehicle-to-vehicle communication technology can be used to enable the target vehicle to receive its target path from the nearest known vehicle or base station. This is particularly suitable for operating areas with poor network signals. This requires that each vehicle be equipped with a V2V communication module that can automatically establish a communication link with surrounding vehicles. The target path is first transmitted to the vehicle closest to the target vehicle, which then transmits the data to the target vehicle step by step via the V2V network. During the path information transmission process, if there are temporary environmental changes (such as obstacles or temporarily closed road sections), the V2V network can provide rapid feedback, allowing the target vehicle to adjust its route immediately.

[0058] Furthermore, the target path can be sent to the target vehicle through map data. The generated target path can be structured in advance to obtain map data so that the vehicle can navigate according to the map data.

[0059] Through the above steps, the low driving efficiency and safety issues caused by path conflicts in traditional path planning can be effectively solved. Specifically, by comprehensively analyzing the entrance and exit information and spatial orientation information, the generated candidate paths can ensure the smooth driving of vehicles in the operating area, avoiding unnecessary collisions and waiting time, thereby improving operating efficiency. In addition, the strategy of merging candidate lanes into the main road not only adjusts the path structure, but also reduces the number of vehicle turns, further improving driving efficiency. This technical solution is applicable to various operating environments, including but not limited to mining areas, warehouses, factories, logistics centers, etc., and can be flexibly adjusted according to the specific needs of different scenarios, and has a wide range of application scenarios.

[0060] In an embodiment of the present invention, entrance and exit information of a work area and spatial orientation information of a plurality of work positions are obtained; a plurality of candidate paths are generated based on the entrance and exit information and the spatial orientation information; a first type of main road is determined based on the first type of candidate lanes in the plurality of candidate paths, and a second type of main road is determined based on the second type of candidate lanes in the plurality of candidate paths; at least a portion of the first type of candidate lanes in each candidate path is merged into the first type of main road, and at least a portion of the second type of candidate lanes in each candidate path is merged into the second type of main road to generate a target path; and the target path is sent to a target vehicle. It is easy to notice that two types of candidate lanes are generated through entrance and exit information and spatial orientation information to cover the complete path from the entrance to the work position and from the work position back to the exit, and in the scenario of multiple work positions, a path planning method that merges the main road and the lane is introduced. By planning and defining a main road, the path can be planned with the main road as the core, and then at least part of the candidate lane is merged into the main road to generate the target path, achieving the purpose of orderly planning the path, thereby realizing the technical effect of improving the driving effect of path planning, and then solving the technical problem of poor path planning effect in related technologies.

[0061] Furthermore, based on the entrance and exit information and the spatial orientation information, multiple candidate paths are generated, including: based on the entrance and exit information, the spatial orientation information and the kinematic characteristics of the work vehicle, multiple initial paths are generated, wherein each initial path includes a first type of initial lane for connecting the corresponding work position with the entrance position and a second type of initial lane for connecting the corresponding work position with the exit position; when there is a conflict area between any two paths in the multiple initial paths, the multiple initial paths are adjusted to obtain multiple candidate paths; when there is no conflict area between any two paths in the multiple initial paths, the multiple initial paths are determined to be multiple candidate paths; wherein the conflict area is an area where different work vehicles conflict when traveling on any two paths.

[0062] The initial path may include a first type initial lane and a second type initial lane. The initial path may be a path initially generated based on the entrance and exit information, spatial orientation information, and kinematic characteristics of the work vehicle, without considering the driving conditions of other vehicles.

[0063] The first type of initial lane mentioned above can be used to connect the work position and the entrance position. The first type of initial lane can be a path initially generated based on the entrance and exit information, spatial orientation information and the kinematic characteristics of the work vehicle, without considering the driving conditions of other vehicles.

[0064] The second type of initial lane can be used to connect the work position and the exit position. The second type of initial lane can be a path initially generated based on the entrance and exit information, spatial orientation information and the kinematic characteristics of the work vehicle, without considering the driving conditions of other vehicles.

[0065] In an optional embodiment, a machine learning model, such as a neural network or reinforcement learning model, can be used to analyze access information, spatial orientation information, and the kinematic characteristics of the work vehicle to predict multiple initial paths. Alternatively, a virtual model can be constructed based on the access information, spatial orientation information, and the kinematic characteristics of the work vehicle to generate and visualize multiple initial paths in real time. This allows users to visually visualize the effects of each initial path in a virtual environment and adjust or select them based on actual needs.

[0066] Next, a determination is made as to whether any two of the multiple initial paths have conflicting regions. A conflicting region is an area where different work vehicles might collide while traveling on any two paths. Specifically, the geometry and spatial positions of the paths can be analyzed to determine whether the two paths intersect or are too close to each other. Alternatively, dynamic analysis of the vehicles' movements can be performed, using a model to simulate their driving states and predict their actual positions along the initial paths. By comparing the predicted behaviors of the vehicles on any two initial paths, a conflict exists if the predicted positions of the vehicles are too close or overlap at a specific time point. This helps identify and adjust the paths before the vehicles actually reach the conflicting region. Alternatively, conflict detection can be performed using a spatiotemporal network. Based on the vehicle's speed and path, the spatiotemporal grids it is likely to occupy at each time point can be predicted. The algorithm then checks whether any two paths simultaneously occupy the same grid at the same time point; if so, a conflict exists. If a conflicting region exists, the multiple initial paths need to be adjusted to generate multiple candidate paths. If a conflicting region does not exist, the multiple initial paths can be identified as candidate paths to further generate the target path.

[0067] Kinematic characteristics may refer to the physical limitations of a vehicle during driving, such as turning radius, maximum speed, vehicle length and width, and safety bounding box. By considering the kinematic characteristics of the vehicle, the generated initial path can ensure the safe driving of the vehicle within the operating area, avoiding the problem of infeasible paths due to physical limitations. In addition, by identifying conflict areas, it can ensure that multiple paths do not interfere with each other, avoiding possible collisions of vehicles during driving, and improving operational safety. This technical solution is not only applicable to a single type of operating vehicle, but can also be applied to complex environments where multiple types of vehicles coexist, including but not limited to forklifts, drones, etc., and can adjust paths according to the characteristics of different types of vehicles.

[0068] Furthermore, multiple initial paths are adjusted to obtain multiple candidate paths, including: matching any two initial paths among the multiple initial paths to determine at least one first conflicting path combination among the multiple initial paths, wherein a conflicting area exists between two paths in the same first conflicting path combination; adjusting at least one first conflicting path combination to obtain multiple adjusted paths; if a conflicting area exists between any two paths among the multiple adjusted paths and the number of iterations has not reached a preset number, matching any two initial paths among the multiple adjusted paths to determine at least one second conflicting path combination among the multiple adjusted paths, adjusting the at least one second conflicting path combination to obtain a path in the next adjustment process; if no conflicting area exists between any two paths among the multiple adjusted paths or the number of iterations has reached a preset number, using the multiple adjusted paths as multiple candidate paths.

[0069] The above-mentioned first conflicting path combination can be a combination of two initial paths. If there is a conflict between the two initial paths, the two initial paths can be matched to obtain the first conflicting path combination. The first conflicting path combination can be one group or multiple groups. By identifying the first conflicting path combination, measures can be taken in advance to avoid the risk of collision between vehicles and ensure the safe operation of the work area. By adjusting the path determined to be the first conflicting path combination, the conflict area can be reduced and the overall feasibility and efficiency of the path can be improved. Identifying conflicting paths also helps to adjust the order and speed of vehicle driving, adjust the traffic flow in the work area, and rationally allocate work resources.

[0070] The above-mentioned second conflicting path combination can be used to characterize the situation where, after adjustments are made to the paths with conflicting areas, there are still conflicting areas between any paths. The second conflicting path combination can be one group or multiple groups. By identifying and processing the second conflicting path combination, the path planning algorithm can continuously adjust the path in multiple iterations until all path combinations do not interfere with each other in space, achieving a global solution. As the number of iterations increases, the accuracy of path planning also improves accordingly, and it can more accurately handle subtle conflicts that may occur in complex scenarios, thereby improving the level of refinement in vehicle scheduling in the operating area. In an environment where multiple vehicles work together, by continuously identifying and reducing conflicts, not only safety is improved and manual intervention is reduced, but also waiting and scheduling delays for vehicles such as mining trucks can be avoided to the greatest extent, thereby improving operating efficiency.

[0071] In an optional embodiment, path adjustment can be based on a local conflict adjustment strategy. By identifying and locally adjusting the conflict points in the initial path, the conflict area is gradually reduced, and finally a candidate path is generated. The space-time grid technology can be used to identify any two paths in the initial path that have a conflict area to form a first conflict path combination. For each first conflict path combination, a smoothing algorithm is used to adjust the path to avoid the conflict area, and multiple adjusted paths are obtained. Then, the adjusted path is checked to see if there is a new conflict area. If so, the conflict path is determined to be the second conflict path combination. The adjustment steps are repeated until there is no more conflict area or the preset number of iterations is reached. Finally, the conflict-free path is used as the candidate path.

[0072] In another optional embodiment, the interaction of paths can be analyzed from a global perspective, and the paths can be adjusted in a collaborative manner to reduce conflict areas. Each initial path can be regarded as an edge in the graph, and a network graph containing all paths can be established. On the network graph, all conflicting path segments are marked to form a conflict area network. Then, graph theory algorithms are used, such as the shortest path algorithm, minimum spanning tree, etc. The graph theory algorithms are not limited here and can be determined as needed. Next, the network graph is replanned to ensure that all paths do not conflict at the global level. Check whether there is a conflict in the replanned global path. If there is, continue to adjust until the conflict-free condition is met or the number of iterations reaches the upper limit. The final conflict-free path is the candidate path.

[0073] In another optional embodiment, path conflict prediction and adjustment can be based on deep learning. A deep learning model is used to predict path conflicts, and the path is adjusted accordingly to generate candidate paths. The deep learning model can be a convolutional neural network, a recurrent neural network, etc. The deep learning model is not limited here and can be determined as needed. For each initial path, the possibility of conflict with other paths is predicted by the deep learning model, and the first conflicting path combination is identified. Based on the conflict prediction results, the first conflicting path combination is adjusted, such as changing the path curve, changing the driving order, or adjusting the speed. The deep learning model can perform iterative learning based on the adjusted path feedback to continuously improve the prediction accuracy. After multiple iterations, the path with a conflict prediction result lower than the threshold is used as a candidate path, or when the preset number of iterations is reached, the adjustment process is stopped and the current path set is used as a candidate path.

[0074] By adjusting individual conflict combinations, the algorithm then traverses and analyzes any two initial paths with conflicting areas until no conflicts are found or the maximum number of iterations set by the algorithm is reached. This allows for gradual adjustments to the path structure, reducing conflict areas and improving the efficiency and safety of vehicles within the work area. Furthermore, by setting an upper limit on the number of iterations, infinite adjustments are avoided, ensuring efficient path planning.

[0075] In the scenario of collaborative mining truck path planning within the loading area of an open-pit mine, multiple initial paths for each excavator can be generated based on the excavator's position and orientation, using a two-lane path planning algorithm. These initial paths can include a turning lane for entering the work area and an opposing lane for exiting the work area. If multiple excavators are in the work area, the initial paths of different excavators are checked for conflicting areas. Initial paths with conflicting areas are then paired to generate the first conflicting path combination.

[0076] Furthermore, at least one first conflict path combination is adjusted to obtain multiple adjusted paths, including: obtaining a target conflict path combination based on the conflict path combination corresponding to the maximum conflict area in at least one first conflict path combination; adjusting two paths in the target conflict path combination respectively to obtain two initial adjustment results; determining a target adjustment result from the two initial adjustment results based on evaluation indicators of the two initial adjustment results; and adjusting the two paths in the target conflict path combination based on the target adjustment result to obtain multiple adjusted paths.

[0077] In an optional embodiment, the path adjustment can be performed based on the density of the conflict area. By analyzing the density of the conflict area, the path combination with the highest conflict density is adjusted preferentially. For each first conflict path combination, the vehicle density per unit area of the conflict area is calculated, and the target conflict path combination with the highest conflict density is determined. The two paths in the target conflict path combination are adjusted separately, for example, by changing the path curve, adjusting the driving direction or driving speed, to obtain two initial adjustment results. Then, an evaluation index is used, such as path length, estimated driving time, energy consumption, etc. The evaluation index is not limited here and can be determined as needed. Then, the two initial adjustment results are evaluated, and the result that reduces the conflict area the most or has the highest path performance can be selected as the target adjustment result. Based on the target adjustment result, the two paths in the target conflict path combination are modified to generate adjusted paths, and these paths are integrated into the entire path planning.

[0078] In another optional embodiment, virtual simulation can be used to predict the collision probability under different path adjustment schemes, and the scheme that can most effectively reduce the collision risk can be selected for path adjustment. First, a virtual simulation environment is established to construct a virtual environment similar to the actual operation area, including terrain, lane layout, vehicle characteristics, etc. In the virtual environment, the target conflict path combination is simulated multiple times, and different adjustment schemes are tried, such as by fine-tuning the path curvature, changing the driving order, etc. A collision risk prediction analysis is performed on each adjustment scheme, and the initial adjustment result with the lowest collision probability is identified as the target adjustment result, which is applied to the actual path planning to achieve effective adjustment of the conflict path combination and generate multiple adjusted paths.

[0079] Furthermore, the evaluation index can be a performance indicator used to evaluate the results of path adjustment, such as path length, travel time, number of turns, etc. For example, when adjusting two conflicting paths, the adjustment effect can be evaluated by calculating the length and number of turns of the adjusted path. By adjusting the target conflict path combination based on the largest conflict area, this technical solution can prioritize solving the most serious path conflict problems and improve the efficiency of path planning. In addition, by introducing evaluation indicators, it is possible to ensure the improvement of path adjustment results and avoid the decline in path traffic efficiency caused by blind adjustment.

[0080] Furthermore, the two paths in the target conflict path combination are adjusted separately to obtain two initial adjustment results, including: for any one path, adjusting the path according to multiple adjustment steps to obtain multiple candidate adjustment results; determining the conflict area between different candidate adjustment results and another path; and obtaining the initial adjustment result based on the candidate adjustment result corresponding to the minimum conflict area among the multiple candidate adjustment results.

[0081] In an optional embodiment, a perturbation-based path adjustment technique can be used to adjust the path, yielding two initial adjustment results. By applying small perturbations to the path, specifically adjusting the path partially or entirely with varying step sizes, the conflict area can be reduced. A path in the target conflict path combination can be selected, and a series of adjustment step sizes (e.g., 1 meter, 2 meters, 3 meters) can be set. Small displacements are then made at key points along the path (such as the starting point, midpoint, end point, or near the conflict point), generating multiple candidate adjustment results. The numerical values used here are provided for illustrative purposes only. Each candidate adjustment result is then analyzed for its conflict area with the other path, which can be analyzed using a space-time grid technique. Based on the size of the conflict area, the candidate adjustment result with the smallest conflict area is selected to ensure minimal interference between the adjusted path and the other path. This determines the initial adjustment result. The above steps are repeated for the other path in the target conflict path combination, ultimately yielding the initial adjustment result.

[0082] In another optional embodiment, the principles of a genetic algorithm can be applied to search for path adjustment solutions through operations such as crossover and mutation over multiple generations of evolution. An initial population containing multiple adjustment solutions is generated for each path, with each solution representing a candidate adjustment result. An evaluation function is defined to calculate the size of the conflict region between each path adjustment solution and another path, using this as the basis for selecting the evolutionary direction. Based on the evaluation function, the population is evolved through selection, crossover, and mutation operations in the genetic algorithm to search for the path adjustment solution with the smallest conflict region. After multiple generations of evolution, the solution with the smallest conflict region is selected as the initial adjustment result. This strategy is then applied to the two paths, yielding two initial adjustment results.

[0083] The adjustment step size can refer to the incremental length of the path during each adjustment. For example, when adjusting a path, the adjustment step size can be set to 1 meter, and the path can be adjusted incrementally until the adjustment result with the minimum conflict area is found. The values here are for example only. By adjusting the path according to multiple adjustment steps, this technical solution can fine-tune each path, reduce the conflict area, and improve the efficiency and safety of work vehicles within the work area. In addition, by determining the initial adjustment result with the minimum conflict area, the path adjustment result can be guaranteed and the expansion of the conflict area can be avoided.

[0084] In the case of specific application to mining trucks, the evaluation index can be the sum of the distances from the reversing completion point to the excavator. The smaller the value, the better the solution. Select the combination with the largest conflict area from the first conflict path combination, that is, move the first conflict path combination along the direction of the reversing completion point, upward, left, and right. The step distance is generally set to 1 meter, and the maximum moving distance is generally set to 5 meters. The values here are only for example. Keep the moving result with the smallest conflict area with the other first conflict path combination, and calculate the evaluation index at this time: Then, do the same process for another first conflict path combination to get the evaluation index ,contrast and , take the shift result corresponding to the minimum value as the adjustment plan.

[0085] Furthermore, the first type of candidate lanes include driving lanes and turning lanes. Based on the first type candidate lanes in multiple candidate paths, a first type of main road is determined, and based on the second type candidate lanes in multiple candidate paths, a second type of main road is determined, including: determining the longest driving lane from the driving lanes included in the multiple candidate paths as the first type of main road; and determining the longest candidate lane from the second type candidate lanes included in the multiple candidate paths as the second type of main road.

[0086] The first type of candidate lanes mentioned above can include driving lanes and turning lanes. Driving lanes can be straight routes from the entry point to the work area. In particular, driving lanes can be unloaded lanes, which refer to the routes that mining trucks take from the starting point to the work area when not loaded with ore or other materials. Unloaded lanes correspond to loaded lanes (i.e., the routes that mining trucks take after loading). Unloaded lanes focus on the driving requirements of unloaded mining trucks, including but not limited to route directness, driving speed, and safe distance. Driving lane planning must consider factors such as the mine's topography, spatial layout, mining truck size, driving speed, and operational efficiency. The design goal is to enable mining trucks to complete their driving tasks in the shortest possible time, with minimal energy consumption, while avoiding collisions with other vehicles or obstacles. Turning lanes can be lanes used by vehicles to turn, make U-turns, or change direction. For example, in the working area of an open-pit mine, mining trucks need to turn near the excavator for loading operations, while in the unloading area, mining trucks need to turn for safe exit. The design of turn lanes must take into account the vehicle's turning radius, safe spacing, and space constraints within the loading area. This ensures that trucks avoid conflicts with other vehicles or fixed obstacles when changing direction, while minimizing the time and space required for changes and improving operational efficiency. By distinguishing between driving lanes and turn lanes, rational path planning can be ensured, avoiding unnecessary turns and waiting time.

[0087] In an optional embodiment, lane lengths can be sorted, with the longest lane among the lanes selected as the first-type arterial road, and the longest candidate lane among the second-type candidate lanes selected as the second-type arterial road. Specifically, the lanes are sorted by length, and the longest lane is selected as the first-type arterial road. The second-type candidate lanes are sorted by length, and the longest candidate lane is selected as the second-type arterial road.

[0088] In another alternative embodiment, the shortest path algorithm from graph theory can be used to transform the problem into the longest path problem. By constructing a lane network graph, the longest path from the starting point to the end point is found. The lanes of all candidate paths are considered edges in the graph, and the connecting points of adjacent lanes are considered nodes, forming a complete lane network graph. Each lane (edge) is assigned a weight, which can be the negative length of the lane. This transforms the longest lane into the graph theory shortest path problem: finding the longest path from the starting node to the ending node. The lanes included in this path are the selected first-type main roads. Similarly, for the second-type candidate lanes, a lane network graph is constructed to find the longest path from the starting point to the end point. All second-type candidate lanes of the candidate paths are considered edges in the graph, and the connecting points of adjacent lanes are considered nodes, forming a complete lane network graph. Each lane (edge) is assigned a weight, which can be the negative length of the lane. This transforms the longest lane into the graph theory shortest path problem: finding the longest path from the starting node to the ending node. The lanes included in this path are the selected second-type main roads.

[0089] By determining the longest driving lane and candidate lanes as the main road, this technical solution can construct a more efficient driving path within the work area, reduce vehicle driving distance, and improve work efficiency.

[0090] Furthermore, at least part of the first type candidate lane in each candidate path is merged into the first type main road, and at least part of the second type candidate lane in each candidate path is merged into the second type main road to generate a target path, including: determining a first bifurcation point between the first type candidate lane and the first type main road, and determining a second bifurcation point between the second type candidate lane and the second type main road; sampling the first type candidate lane to generate a first connecting path between the first bifurcation point and the first type candidate lane, and sampling the second type candidate lane to generate a second connecting path between the second bifurcation point and the first type candidate lane, wherein the first connecting path and the first type candidate lane are connected. The intersection of the first connecting path and the second type candidate lane is the first target sampling point, and the intersection of the second connecting path and the second type candidate lane is the second target sampling point; the section of the first type main road before the first bifurcation point, the first connecting path, and the section of the first type candidate lane after the first target sampling point are spliced together to generate a first type target lane; the section of the second type main road before the second bifurcation point, the second connecting path, and the section of the second type candidate lane after the second target sampling point are spliced together to generate a second type target lane, wherein the first type target lane and the second type target lane meet preset conditions; and a target path is obtained based on the first type target lane and the second type target lane.

[0091] In an optional embodiment, a first bifurcation point can be determined based on the relative position and orientation of the first-type candidate lane and the first-type main road. The first-type candidate lane can be a branch road, so that each branch road can be merged into the main road. The first bifurcation point can be manually annotated or predicted through reinforcement learning. Similarly, the second bifurcation point between the second-type candidate lane and the second-type main road can be predicted by manually annotating or through reinforcement learning.

[0092] Then, the first type of candidate lanes are sampled to generate a first connecting path from the first bifurcation point to the first type of candidate lanes. The intersection of the first connecting path and the first type of candidate lanes is the first target sampling point. Starting from the first bifurcation point, the first type of candidate lanes can be sampled at regular intervals or according to safety distance conditions to determine multiple first target sampling points. Then, a path planning algorithm is used to generate the first connecting path. Similarly, the second type of candidate lanes can be sampled at regular intervals or according to safety distance conditions to determine second target sampling points. Then, a path planning algorithm is used to generate a second connecting path from the second bifurcation point to the first type of candidate lanes.

[0093] After obtaining the first and second connecting paths, linear interpolation can be used to create a smooth transition between the endpoints of the first-type main road segment before the first bifurcation point, the first connecting path, and the segment after the first target sampling point in the first-type candidate lane, thereby creating the first-type target lane. Alternatively, smooth curve fitting can be used to connect the endpoints of the three segments and adjust the curve parameters to create the first-type target lane. Smooth curve fitting can be performed using a discrete point smoothing method or a Gaussian process regression algorithm. Alternatively, it can be performed using spline curve fitting, i.e., polynomial segment fitting. The objective function used in smooth curve fitting can be the sum of smoothness cost, length cost, and origin point offset cost. Similarly, linear interpolation or smooth curve fitting can be used to connect the segment before the second bifurcation point in the second-type main road segment, the second connecting path, and the segment after the second target sampling point in the second-type candidate lane, thereby creating the second-type target lane. The generated first-type target lane and second-type target lane meet the preset conditions. Specifically, through the above splicing process, the first-type target lane and the second-type target lane meet the position constraint, curvature constraint, and start and end point orientation constraint conditions.

[0094] Finally, a target path can be derived based on the first and second target lanes. By integrating the first and second target lanes based on lane priorities, the target path is obtained. Alternatively, a mixed integer linear programming approach can be used to solve constraints on the first and second target lanes to obtain the target path. Alternatively, a multi-agent system can be used to simulate the behavior of vehicles traveling in the first and second target lanes, using a coordination algorithm to generate the target path.

[0095] A bifurcation point is the connection point between a main road and a branch road. Sampling refers to selecting multiple points along a path to generate a path. By determining bifurcation points and connecting paths, this technical solution ensures the consistency and rationality of vehicle paths within the operating area, avoiding unnecessary turns and waiting time, and improving operational efficiency. Furthermore, by splicing paths based on target lanes that meet preset conditions, the efficiency of path planning is ensured, preventing degradation in path performance.

[0096] Furthermore, a first bifurcation point between a first type candidate lane and a first type main road is determined, and a second bifurcation point between a second type candidate lane and a second type main road is determined, including: constructing a first buffer area corresponding to the first type candidate lane and a second buffer area corresponding to the second type candidate lane based on the type of the working vehicle; determining at least one first intersection between the first type main road and the first buffer area, and at least one second intersection between the second type main road and the second buffer area; determining a first bifurcation point from at least one first intersection, and determining a second bifurcation point from at least one second intersection, wherein a distance between the first bifurcation point and the first type candidate lane is greater than a distance between an intersection other than the first bifurcation point and the first type candidate lane, and a distance between the second bifurcation point and the second type candidate lane is greater than a distance between an intersection other than the second bifurcation point and the second type candidate lane.

[0097] The buffer area mentioned above refers to the minimum safe distance area set in path planning to avoid collisions between vehicles. The buffer area can be a rectangular area around the lane lines. For example, in a warehouse environment, the buffer area may be the minimum safe distance between shelves. By constructing the first buffer area and the second buffer area, this technical solution can ensure the safety of the vehicle's driving path within the working area and avoid collisions between vehicles. In addition, by determining the intersection between the bifurcation point and the buffer area, the rationality of the path planning can be ensured and blind spots in the path planning can be avoided.

[0098] In an optional embodiment, a first buffer area corresponding to the first type of candidate lane and a second buffer area corresponding to the second type of candidate lane can be constructed based on the type of the work vehicle. Different types of work vehicles will have different buffer areas. The size information of the vehicle, such as width, length and safety margin, can be determined by the type of work vehicle. Then, the center lines of the first type candidate lane and the second type candidate lane can be used as references, and half the vehicle width plus the safety margin can be extended to the left and right to construct the corresponding first buffer area and second buffer area. Alternatively, based on the type of vehicle, the vehicle's motion characteristics such as braking distance and turning radius can be determined. The first buffer area and the second buffer area are determined by analyzing the motion characteristics.

[0099] Then, a first intersection point and a second intersection point are predicted through human analysis or reinforcement learning. A first bifurcation point is then determined from the at least one first intersection point, ensuring that the distance between the first bifurcation point and the first type candidate lane is greater than the distance between the first type candidate lane and the intersection points other than the first bifurcation point. And a second bifurcation point is determined from the at least one second intersection point, ensuring that the distance between the second bifurcation point and the second type candidate lane is greater than the distance between the second type candidate lane and the intersection points other than the second bifurcation point.

[0100] Specifically, the distance between each first intersection and the first type candidate lane can be calculated, and the intersection farthest from the first type candidate lane among the first intersections between the first buffer area and the first type candidate lane can be selected as the first bifurcation point to reduce the risk of collision when vehicles enter or leave the candidate lane. Alternatively, by setting a safety distance threshold based on the type and driving speed of the operating vehicle, all first intersections can be analyzed to evaluate whether the path from the first intersection to the first type candidate lane meets the set safety distance requirement. From the intersections that meet the safety assessment, the intersection farthest from the first type candidate lane and providing a better view can be selected as the first bifurcation point to improve the safety and smoothness of vehicle driving. Similarly, the distance between each second intersection and the second type candidate lane can be calculated, and the intersection farthest from the second type candidate lane can be selected as the second bifurcation point.

[0101] Specifically, the buffer area can be determined using the following formula:

[0102] F= ;

[0103] Where F represents the expansion parameter of the buffer area, in meters. Indicates the width of the vehicle, represents the safe bounding box, Indicates the error value.

[0104] Furthermore, sampling the first type candidate lane to generate a first connecting path between the first bifurcation point and the first type candidate lane, and sampling the second type candidate lane to generate a second connecting path between the second bifurcation point and the first type candidate lane, including: determining a first target path point in the first type candidate lane that is closest to the first bifurcation point, and a second target path point in the second type candidate lane that is closest to the second bifurcation point; sampling the first type candidate lane starting from the first target path point to obtain a plurality of first sampling points, and sampling the second type candidate lane starting from the second target path point to obtain a plurality of second sampling points; based on the kinematic characteristics of the vehicle, sequentially connecting the first sampling points with the first bifurcation point to obtain a plurality of first reference paths, and sequentially connecting the second sampling points with the second bifurcation point to obtain a plurality of second reference paths; obtaining a first connecting path based on at least the shortest path among the plurality of first reference paths, and obtaining a second connecting path based on the shortest path among the plurality of second reference paths.

[0105] In an optional embodiment, a first target pathpoint closest to the first bifurcation point in the first type of candidate lanes and a second target pathpoint closest to the second bifurcation point in the second type of candidate lanes can be manually determined. The first type of candidate lanes herein may be a branch road. Alternatively, the first target pathpoint with the shortest distance to the first bifurcation point can be calculated from the first type of candidate lanes using Euclidean distance, and the second target pathpoint closest to the second bifurcation point can be obtained from the second type of candidate lanes.

[0106] Then, sampling can be performed on the first type of candidate lane starting from the first target path point based on a fixed distance or a sampling frequency determined by the vehicle's kinematic characteristics to obtain multiple first sampling points. Similarly, sampling can be performed on the second type of candidate lane starting from the second target path point based on a fixed distance or a sampling frequency determined by the vehicle's kinematic characteristics to obtain multiple second sampling points.

[0107] Next, based on the vehicle's kinematic characteristics, the first sampling point and the first bifurcation point can be sequentially connected to obtain multiple first reference paths. The vehicle's kinematic characteristics can be used to define the calculation parameters of a path planning algorithm, and the path planning algorithm can be used to select a first reference path that connects the first sampling point and the first bifurcation point. Alternatively, a vehicle dynamics model can be constructed based on the vehicle's kinematic characteristics. Starting from the first bifurcation point, a path connecting the first bifurcation point to the first sampling point is predicted to obtain multiple first reference paths. Similarly, a path planning algorithm or a vehicle dynamics model can be used to sequentially connect the second sampling point and the second bifurcation point to obtain multiple second reference paths.

[0108] Finally, the shortest path among the first reference paths can be determined as the first connecting path using straight-line distance, or the shortest path among multiple first reference paths can be determined as the first connecting path using a graph theory shortest path algorithm. Similarly, the shortest path among multiple second reference paths can be determined as the second connecting path using a distance comparison method or a graph theory shortest path algorithm.

[0109] The target path point can be the closest intersection to the bifurcation point. The reference path is a path generated based on the sampling points and bifurcation points. By determining the target path point and generating the reference path, this technical solution ensures the consistency and rationality of the vehicle's driving path within the work area, avoiding unnecessary turns and waiting time, and improving work efficiency. Furthermore, by connecting paths based on the vehicle's kinematic characteristics, the feasibility of path planning is ensured, avoiding path infeasibility issues caused by physical limitations.

[0110] The technical solution proposed in this application is described below in conjunction with an optional embodiment, which involves a method for generating a target path.

[0111] The closest point to the first bifurcation point on the first type candidate lane can be obtained. Starting from the closest point, samples are taken every 5 meters, with a maximum sampling distance of 30 meters, to obtain a first set of sampling points. The values here are for example only. The first sampling points are traversed sequentially, and a curve smoothing algorithm is used to connect the first bifurcation point to the first sampling point to obtain a first reference path set. The shortest path in the reference path set is selected to obtain a first connecting path. Similarly, the closest point to the second bifurcation point on the second type candidate lane can be obtained. Starting from the closest point, a second set of sampling points is obtained. The second sampling points are traversed sequentially, and a curve smoothing algorithm is used to connect the second bifurcation point to the second sampling point to obtain a second set of reference paths. The shortest path in the reference path set is selected to obtain a second connecting path.

[0112] Next, the first-type main road section before the first bifurcation point, the first connecting path, and the first-type candidate lane section after the first target sampling point are concatenated to generate the first-type target lane. The second-type main road section before the second bifurcation point, the second connecting path, and the second-type candidate lane section after the second target sampling point are concatenated to generate the second-type target lane. A smoothing method is then used to obtain a first-type target lane and a second-type target lane that maintain a constant endpoint position and satisfy curvature constraints. Finally, the first-type target lane and the second-type target lane are merged to obtain the target path. Furthermore, if the first-type candidate lane is a driving lane, the first-type candidate lane and the turning lane are concatenated to obtain the merged first-type target lane.

[0113] The above embodiment introduces different types of main roads and, through lane merging path planning, pre-plans and defines a main road in a multi-excavator operation scenario. The mining truck path is then planned around this main road. Paths leading to different excavators are then branched off from the main road, ensuring the orderliness and coordination of the overall path. The adjustment and separation of switching paths for multiple excavators are also considered. When generating switching paths, the spatial factors of the work area and path interference between multiple excavators are fully considered. An algorithm is used to pre-separate the switching paths of different excavators to ensure that the paths do not interfere with each other and avoid vehicle conflicts caused by path intersections. Global collaborative path planning avoids head-on collisions. During path planning, the driving requirements of all excavators and mining trucks are comprehensively considered, and reasonable main roads and branching paths are defined in advance to avoid path conflicts during mining truck operation. By pre-planning paths, multi-vehicle collaborative operation is achieved, avoiding post-processing of path conflicts and vehicle waiting, and improving the operating efficiency of mining trucks and other vehicles within the work area.

[0114] like Figure 2 As shown, it shows the situation of driving according to the planned path. Figure 2 The system includes two workstations 202, two first-type candidate lanes 2061, two second-type candidate lanes 2062, and two first-type main roads 208. There is a first intersection 2001 between the two first-type candidate lanes, and a second intersection 2002 between the two second-type candidate lanes.

[0115] According to an embodiment of the present invention, a method embodiment of an optional path planning method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0116] Figure 3 is a flow chart of an optional path planning method according to an embodiment of the present invention, such as Figure 3 As shown, the method includes the following steps:

[0117] Step S302: Receive the target path.

[0118] Among them, the target path is generated by merging at least part of the first type candidate lane in each candidate path among multiple candidate paths into the first type main road, and merging at least part of the second type candidate lane in each candidate path into the second type main road. The first type main road is determined based on the first type candidate lanes in multiple candidate paths, and the second type main road is determined based on the second type candidate lanes in multiple candidate paths. The multiple candidate paths are generated based on the entrance and exit information of the work area and the spatial orientation information of multiple work positions. The entrance and exit information includes the entrance position and exit position of the work area. Each candidate path includes a first type candidate lane for connecting the corresponding work position with the entrance position and a second type candidate lane for connecting the corresponding work position with the exit position.

[0119] In an optional embodiment, the vehicle may receive the target path via vehicle-to-vehicle communication technology. Alternatively, the vehicle may utilize onboard visual sensors and simultaneous localization and mapping technology to autonomously identify and understand the target path without receiving path information via wireless communication.

[0120] The target path can be generated by merging at least a portion of the first type candidate lane in each of the multiple candidate paths into the first type main road, and merging at least a portion of the second type candidate lane in each of the multiple candidate paths into the second type main road. The target path can be generated using the method described in the above embodiment.

[0121] The first type of main road is determined based on the first type of candidate lanes among the multiple candidate paths. The first type of main road can be determined using the method described in the above embodiment. The second type of main road can be determined based on the second type of candidate lanes among the multiple candidate paths. The second type of main road can be determined using the method described in the above embodiment.

[0122] Multiple candidate paths can be generated based on the entrance and exit information of the work area and the spatial orientation information of multiple workstations. The candidate paths can be generated using the method described in the above embodiment. The entrance and exit information can include the entrance and exit locations of the work area. Each candidate path can include a first-type candidate lane connecting the corresponding workstation with the entrance location and a second-type candidate lane connecting the corresponding workstation with the exit location.

[0123] Step S304: driving along the target route.

[0124] In an optional embodiment, a controller can generate control signals to control the vehicle to follow the target path. Alternatively, Model Predictive Control (MPC) can be used to predict future driving states using a vehicle dynamics model and minimize deviations from the target path through a control sequence.

[0125] In this embodiment, at least a portion of the first-type candidate lanes from multiple candidate paths can be merged into a first-type main road, and at least a portion of the second-type candidate lanes can be merged into a second-type main road. This merging strategy can effectively reduce path conflicts and improve the overall smoothness and efficiency of vehicle travel. Main roads are determined based on information from all first-type candidate lanes, while branch lanes are paths separated from the main roads and can be used for direct travel to specific work locations. This differentiation helps improve the path hierarchy and facilitates vehicle operation scheduling. Candidate paths are generated using information about the entrances and exits of the work area and the spatial orientation of multiple work locations. This method ensures the rationality of path planning and enables the generated paths to adapt to the actual layout and needs of the work environment. By merging paths and distinguishing between main roads and branch lanes, path conflicts within the work area are effectively avoided, reducing the risk of vehicle collisions and improving operational safety. During path merging, the actual needs of the work location and the convenience of vehicle entry and exit are taken into consideration, making path planning more flexible and able to quickly adapt to changing work conditions, improving vehicle travel efficiency and operational productivity in the work area.

[0126] According to an embodiment of the present invention, a device embodiment of a path planning device is provided. It should be noted that the device can be used to execute the above-mentioned path planning method.

[0127] Figure 4 is a schematic diagram of an optional path planning device according to an embodiment of the present invention, such as Figure 4 As shown, the device includes:

[0128] The acquisition module 40 is used to acquire the entrance and exit information of the working area and the spatial orientation information of multiple working positions, wherein the entrance and exit information includes the entrance position and exit position of the working area.

[0129] The generation module 42 is used to generate multiple candidate paths based on the entrance and exit information and the spatial orientation information, wherein each candidate path includes a first type candidate lane for connecting the corresponding work position with the entrance position and a second type candidate lane for connecting the corresponding work position with the exit position.

[0130] a determination module 44 for determining a first-type main road based on the first-type candidate lanes in the plurality of candidate paths, and determining a second-type main road based on the second-type candidate lanes in the plurality of candidate paths;

[0131] The merging module 46 is configured to merge at least a portion of the first type candidate lanes in each candidate path into the first type main road, and merge at least a portion of the second type candidate lanes in each candidate path into the second type main road, to generate a target path.

[0132] The sending module 48 is configured to send the target path to the target vehicle.

[0133] Furthermore, the generation module 42 is also used to generate multiple initial paths based on the entrance and exit information, spatial orientation information and kinematic characteristics of the work vehicle, wherein each initial path includes a first type of initial lane for connecting the corresponding work position with the entrance position and a second type of initial lane for connecting the corresponding work position with the exit position; when there is a conflict area between any two paths in the multiple initial paths, the multiple initial paths are adjusted to obtain multiple candidate paths; when there is no conflict area between any two paths in the multiple initial paths, the multiple initial paths are determined to be multiple candidate paths; wherein the conflict area is an area where different work vehicles conflict when traveling on any two paths.

[0134] Furthermore, the generation module 42 is also used to match any two initial paths among the multiple initial paths, determine at least one first conflicting path combination among the multiple initial paths, wherein a conflicting area exists between two paths in the same first conflicting path combination; adjust at least one first conflicting path combination to obtain multiple adjusted paths; if a conflicting area exists between any two paths among the multiple adjusted paths and the number of iterations does not reach a preset number, match any two initial paths among the multiple adjusted paths, determine at least one second conflicting path combination among the multiple adjusted paths, adjust at least one second conflicting path combination to obtain a path in the next adjustment process; if no conflicting area exists between any two paths among the multiple adjusted paths, or the number of iterations reaches a preset number, use the multiple adjusted paths as multiple candidate paths.

[0135] Furthermore, the generation module 42 is also used to obtain a target conflict path combination based on the conflict path combination corresponding to the maximum conflict area in at least one first conflict path combination; adjust the two paths in the target conflict path combination respectively to obtain two initial adjustment results; determine the target adjustment result from the two initial adjustment results based on the evaluation indicators of the two initial adjustment results; adjust the two paths in the target conflict path combination based on the target adjustment result to obtain multiple adjusted paths.

[0136] Furthermore, the generation module 42 is also used to adjust any path according to multiple adjustment steps to obtain multiple candidate adjustment results; determine the conflict area between different candidate adjustment results and another path; and obtain the initial adjustment result based on the candidate adjustment result corresponding to the minimum conflict area among the multiple candidate adjustment results.

[0137] Furthermore, the first type candidate lanes include driving lanes and turning lanes. The determination module 44 is further used to determine that the longest driving lane is the first type main road from the driving lanes included in the multiple candidate paths; and to determine that the longest candidate lane is the second type main road from the second type candidate lanes included in the multiple candidate paths.

[0138] Furthermore, the merging module 46 is further configured to determine a first bifurcation point between the first type candidate lane and the first type main road, and a second bifurcation point between the second type candidate lane and the second type main road; sample the first type candidate lane to generate a first connecting path from the first bifurcation point to the first type candidate lane, and sample the second type candidate lane to generate a second connecting path from the second bifurcation point to the first type candidate lane, wherein the intersection point between the first connecting path and the first type candidate lane is a first target sampling point, and the intersection point between the second connecting path and the second type candidate lane is a second target sampling point; concatenate the section of the first type main road before the first bifurcation point, the first connecting path, and the section of the first type candidate lane after the first target sampling point to generate the first type target lane; concatenate the section of the second type main road before the second bifurcation point, the second connecting path, and the section of the second type candidate lane after the second target sampling point to generate the second type target lane, wherein the first type target lane and the second type target lane meet preset conditions; and obtain a target path based on the first type target lane and the second type target lane.

[0139] Furthermore, the merging module 46 is also used to construct a first buffer area corresponding to the first type of candidate lane and a second buffer area corresponding to the second type of candidate lane based on the type of the working vehicle; determine at least one first intersection between the first type of main road and the first buffer area, and at least one second intersection between the second type of main road and the second buffer area; determine a first bifurcation point from at least one first intersection, and determine a second bifurcation point from at least one second intersection, wherein the distance between the first bifurcation point and the first type candidate lane is greater than the distance between the intersection other than the first bifurcation point and the first type candidate lane, and the distance between the second bifurcation point and the second type candidate lane is greater than the distance between the intersection other than the second bifurcation point and the second type candidate lane.

[0140] Furthermore, the merging module 46 is further configured to determine a first target path point in the first type candidate lane that is closest to the first bifurcation point, and a second target path point in the second type candidate lane that is closest to the second bifurcation point; perform sampling on the first type candidate lane starting from the first target path point to obtain a plurality of first sampling points, and perform sampling on the second type candidate lane starting from the second target path point to obtain a plurality of second sampling points; based on the kinematic characteristics of the vehicle, sequentially connect the first sampling points with the first bifurcation point to obtain a plurality of first reference paths, and sequentially connect the second sampling points with the second bifurcation point to obtain a plurality of second reference paths; obtain a first connecting path based on at least the shortest path among the plurality of first reference paths, and obtain a second connecting path based on the shortest path among the plurality of second reference paths.

[0141] According to an embodiment of the present invention, an optional device embodiment of a path planning device is provided. It should be noted that the device can be used to execute the above-mentioned path planning method.

[0142] Figure 5 is a schematic diagram of an optional path planning device according to an embodiment of the present invention, such as Figure 5 As shown, the device includes:

[0143] a receiving module 50 for receiving a target path, wherein the target path is generated by merging at least a portion of a first-type candidate lane in each of the multiple candidate paths into a first-type main road, and merging at least a portion of a second-type candidate lane in each of the candidate paths into a second-type main road, the first-type main road being determined based on the first-type candidate lanes in the multiple candidate paths, the second-type main road being determined based on the second-type candidate lanes in the multiple candidate paths, the multiple candidate paths being generated based on entrance and exit information of a work area and spatial orientation information of multiple work positions, the entrance and exit information including an entrance location and an exit location of the work area, and each candidate path including a first-type candidate lane for connecting a corresponding work position with the entrance location and a second-type candidate lane for connecting the corresponding work position with the exit location;

[0144] The driving module 52 is configured to drive along a target path.

[0145] According to another aspect of an embodiment of the present invention, a vehicle is also provided, including: a communication unit for communicating with a cloud server or a target vehicle; a memory storing an executable program; and a processor for running the program, wherein the method of each embodiment of the present invention is executed when the program is running.

[0146] The above-mentioned communication unit can be used to ensure that data is effectively and reliably transmitted between the vehicle executing the path planning method proposed in this application and the cloud server or the target vehicle. For example, when the above-mentioned path planning method proposed in this application is executed by a vehicle, the vehicle may include the above-mentioned communication unit, and then the vehicle can communicate with the target vehicle based on the above-mentioned communication unit, and send the generated target path to the target vehicle, etc.; when the above-mentioned vehicle serves as a target vehicle, it can also receive the target path sent by the cloud server or other vehicles.

[0147] The above-mentioned memory may refer to a device inside a computer for storing data and programs, and may include memory, hard disk, etc., wherein the memory may be used to temporarily store running programs and data, the hard disk may be used to store programs and data for a long time, and the memory may be used to enable the computer to read and write data, as well as execute programs; the above-mentioned processor may be responsible for executing instructions in computer programs and performing data processing, and may be responsible for controlling and executing various operations, including arithmetic operations, logical operations, data transmission, etc.

[0148] An embodiment of the present application further provides an electronic device, comprising: a communication unit for communicating with a target vehicle; a memory storing an executable program; and a processor for running the program, wherein the method of each embodiment of the present invention is executed when the program is running.

[0149] The above-mentioned communication unit can be a basic module or component for transmitting, receiving and processing information, and can be a hardware module, a software module, or a combination of a hardware module and a software module, used to ensure that data is effectively and reliably transmitted between the platform or vehicle executing the path planning method proposed in this application and the target vehicle. For example, when the above-mentioned path planning method proposed in this application is executed by a platform, the platform may include the above-mentioned electronic device, and then the platform can communicate with the target vehicle based on the above-mentioned communication unit, and send the generated target path to the target vehicle, etc.; for example, when the above-mentioned path planning method proposed in this application is executed by a vehicle, the vehicle may include the above-mentioned electronic device, and then the vehicle can communicate with the target vehicle based on the above-mentioned communication unit, and send the generated target path to the target vehicle, etc.; the above-mentioned communication unit may include modules such as a transmitter, a receiver, a modulator, a demodulator, an encoder, and a decoder. The specific structure of the communication unit can be determined according to actual needs and is not limited here.

[0150] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0151] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0152] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0153] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0154] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0156] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0157] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0158] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), a mobile hard drive, a magnetic disk, or an optical disk.

[0159] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A path planning method, characterized in that: include: Acquire entrance and exit information of the work area and spatial orientation information of multiple work positions, wherein the entrance and exit information includes the entrance position and exit position of the work area; Based on the entrance and exit information and the spatial orientation information, a plurality of candidate paths are generated, wherein each candidate path includes a first type candidate lane for connecting a corresponding work position with the entrance position and a second type candidate lane for connecting the corresponding work position with the exit position; Determining a first-type main road based on the first-type candidate lanes in the plurality of candidate paths, and determining a second-type main road based on the second-type candidate lanes in the plurality of candidate paths; Merging at least a portion of the first type candidate lane in each candidate path into the first type main road, and merging at least a portion of the second type candidate lane in each candidate path into the second type main road, to generate a target path; sending the target path to a target vehicle; The step of merging at least a portion of the first type candidate lanes in each candidate path into the first type main road, and merging at least a portion of the second type candidate lanes in each candidate path into the second type main road, to generate a target path includes: Determining a first bifurcation point between the first type candidate lane and the first type main road, and determining a second bifurcation point between the second type candidate lane and the second type main road; Sampling the first type of candidate lane to generate a first connecting path from the first bifurcation point to the first type of candidate lane, and sampling the second type of candidate lane to generate a second connecting path from the second bifurcation point to the first type of candidate lane, wherein the intersection of the first connecting path and the first type of candidate lane is a first target sampling point, and the intersection of the second connecting path and the second type of candidate lane is a second target sampling point; Splicing the road section of the first-type main road before the first bifurcation point, the first connecting path, and the road section of the first-type candidate lane after the first target sampling point to generate a first-type target lane; splicing the road section of the second-type main road before the second bifurcation point, the second connecting path, and the road section of the second-type candidate lane after the second target sampling point to generate a second-type target lane, wherein the first-type target lane and the second-type target lane meet preset conditions; The target path is obtained based on the first type target lane and the second type target lane.

2. The method according to claim 1, characterized in that The generating of multiple candidate paths based on the entrance and exit information and the spatial orientation information includes: Based on the entrance and exit information, the spatial orientation information, and the kinematic characteristics of the work vehicle, a plurality of initial paths are generated, wherein each initial path includes a first type of initial lane for connecting a corresponding work position with the entrance position and a second type of initial lane for connecting the corresponding work position with the exit position; In the case where there is a conflict area between any two paths among the multiple initial paths, adjusting the multiple initial paths to obtain the multiple candidate paths; In a case where no conflicting area exists between any two paths among the multiple initial paths, determining the multiple initial paths as the multiple candidate paths; The conflict area is an area where different working vehicles conflict when traveling on any two paths.

3. The method according to claim 2, characterized in that The adjusting the multiple initial paths to obtain the multiple candidate paths includes: Matching any two of the multiple initial paths to determine at least one first conflicting path combination among the multiple initial paths, wherein a conflicting region exists between two paths in the same first conflicting path combination; Adjusting the at least one first conflicting path combination to obtain a plurality of adjusted paths; If a conflicting region exists between any two of the multiple adjusted paths and the number of iterations has not reached a preset number, matching any two initial paths among the multiple adjusted paths, determining at least one second conflicting path combination among the multiple adjusted paths, and adjusting the at least one second conflicting path combination to obtain a path for a next adjustment process; If there is no conflicting area between any two paths among the plurality of adjusted paths, or the number of iterations reaches the preset number, the plurality of adjusted paths are used as the plurality of candidate paths.

4. The method according to claim 3, characterized in that The adjusting the at least one first conflicting path combination to obtain a plurality of adjusted paths includes: Obtaining a target conflicting path combination according to the conflicting path combination corresponding to the largest conflicting area in the at least one first conflicting path combination; Adjusting the two paths in the target conflicting path combination respectively to obtain two initial adjustment results; determining a target adjustment result from the two initial adjustment results based on evaluation indicators of the two initial adjustment results; Two paths in the target conflict path combination are adjusted based on the target adjustment result to obtain the multiple adjusted paths.

5. The method according to claim 4, characterized in that The two paths in the target conflicting path combination are adjusted respectively to obtain two initial adjustment results, including: For any path, adjusting the path according to multiple adjustment steps to obtain multiple candidate adjustment results; Determine the conflict areas between different candidate adjustment results and another path; The initial adjustment result is obtained according to the candidate adjustment result corresponding to the minimum conflicting area among the multiple candidate adjustment results.

6. The method according to any one of claims 1 to 5, characterized in that The first-type candidate lanes include driving lanes and turning lanes. The determining of a first-type main road based on the first-type candidate lanes in the plurality of candidate paths and the determining of a second-type main road based on the second-type candidate lanes in the plurality of candidate paths include: Determining, from the driving lanes included in the plurality of candidate paths, the longest driving lane as the first type of main road; From the second-type candidate lanes included in the plurality of candidate paths, determine the candidate lane with the longest length as the second-type main road.

7. The method according to claim 6, characterized in that The determining of a first bifurcation point between the first type candidate lane and the first type main road, and determining a second bifurcation point between the second type candidate lane and the second type main road, includes: Based on the type of the working vehicle, construct a first buffer area corresponding to the first type candidate lane and a second buffer area corresponding to the second type candidate lane; Determining at least one first intersection point between the first type of main road and the first buffer area, and at least one second intersection point between the second type of main road and the second buffer area; The first bifurcation point is determined from the at least one first intersection, and the second bifurcation point is determined from the at least one second intersection, wherein the distance between the first bifurcation point and the first type of candidate lane is greater than the distance between the first type of candidate lane and the intersection other than the first bifurcation point, and the distance between the second bifurcation point and the second type of candidate lane is greater than the distance between the second type of candidate lane and the intersection other than the second bifurcation point.

8. The method according to claim 6, characterized in that The sampling of the first type candidate lane to generate a first connecting path between the first bifurcation point and the first type candidate lane, and the sampling of the second type candidate lane to generate a second connecting path between the second bifurcation point and the first type candidate lane include: Determine a first target pathpoint in the first type candidate lane that is closest to the first bifurcation point, and a second target pathpoint in the second type candidate lane that is closest to the second bifurcation point; Sampling the first type of candidate lane starting from the first target path point to obtain a plurality of first sampling points, and sampling the second type of candidate lane starting from the second target path point to obtain a plurality of second sampling points; Based on the kinematic characteristics of the vehicle, sequentially connecting the first sampling point and the first bifurcation point to obtain a plurality of first reference paths, and sequentially connecting the second sampling point and the second bifurcation point to obtain a plurality of second reference paths; The first concatenated path is obtained at least according to the shortest path among the plurality of first reference paths, and the second concatenated path is obtained according to the shortest path among the plurality of second reference paths.

9. A path planning method, characterized in that: include: receiving a target path, wherein the target path is generated by merging at least a portion of a first type candidate lane in each candidate path among a plurality of candidate paths into a first type main road, and merging at least a portion of a second type candidate lane in each candidate path into a second type main road, the first type main road being determined based on the first type candidate lanes in the plurality of candidate paths, the second type main road being determined based on the second type candidate lanes in the plurality of candidate paths, the plurality of candidate paths being generated based on entrance and exit information of a work area and spatial orientation information of a plurality of work positions, the entrance and exit information including an entrance position and an exit position of the work area, each candidate path including a first type candidate lane for connecting a corresponding work position with the entrance position, and a second type candidate lane for connecting the corresponding work position with the exit position; Follow the target path as described; The target path is generated by merging at least part of a first type candidate lane in each candidate path among multiple candidate paths into a first type main road, and merging at least part of a second type candidate lane in each candidate path into a second type main road, including: determining a first bifurcation point between the first type candidate lane and the first type main road, and determining a second bifurcation point between the second type candidate lane and the second type main road; sampling the first type candidate lane to generate a first connecting path between the first bifurcation point and the first type candidate lane, and sampling the second type candidate lane to generate a second connecting path between the second bifurcation point and the first type candidate lane, wherein the first connecting path is connected to the first type candidate lane. as a first target sampling point, and the intersection of the second connecting path and the second type candidate lane is a second target sampling point; the section of the first type main road before the first bifurcation point, the first connecting path, and the section of the first type candidate lane after the first target sampling point are spliced together to generate a first type target lane; the section of the second type main road before the second bifurcation point, the second connecting path, and the section of the second type candidate lane after the second target sampling point are spliced together to generate a second type target lane, wherein the first type target lane and the second type target lane meet preset conditions; and the target path is obtained based on the first type target lane and the second type target lane.

10. A vehicle, characterized in that: include: a communication unit, for communicating with a cloud server or a target vehicle; a memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 9 when running.

11. An electronic device, characterized in that: include: a communication unit for communicating with a target vehicle; a memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 8 when running.

Images