Path planning method and device

Abstract

The invention provides a path planning method and device, and the method comprises the steps: constructing a sixteen-way tree based on a preset four-dimensional space range, and mapping obstacle information to nodes in the sixteen-way tree; performing time dimension and / or space dimension expansion processing on the obstacle information in the sixteen-way tree to obtain an expanded sixteen-way tree; and based on the starting point and the terminal point of the target aircraft, performing path search in the sixteen-way tree after the obstacle area expansion, and determining the optimal path of the target aircraft. By introducing the time dimension, the target aircraft not only can avoid obstacles in space, but also can process changes of the obstacles in different time periods based on the planned path, so that the comprehensiveness and safety of path planning are improved. By performing expansion processing of time and space dimensions on the obstacle information, the path planning algorithm can consider the influence of the obstacle in a larger range, and the safety and effectiveness of path planning are further improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of path planning, in particular to a path planning method and device. BACKGROUND

[0002] When a flight vehicle such as a UAV performs a flight path planning, the existing method generally searches for a path in a three-dimensional space by avoiding static obstacles, and determines a flight path of the flight vehicle.

[0003] The existing flight vehicle path planning process of directly searching for a path in a three-dimensional space may, in a scenario of dense flight of UAVs in a low-altitude airspace, cause the planned flight path to intersect with the flight path of other UAVs or obstacles in a specific time period, thereby increasing the flight risk. Therefore, how to improve the safety of UAV path planning is an important issue to be solved in the industry at present. SUMMARY

[0004] The present application provides a path planning method and device to improve the safety of flight vehicle path planning.

[0005] The present application provides a path planning method, comprising the following steps: Based on a preset four-dimensional space range, a sixteen-ary tree is constructed, and obstacle information in the four-dimensional space range is mapped to nodes in the sixteen-ary tree; Based on a preset expansion range, the obstacle information in the sixteen-ary tree is subjected to inflation processing in the time dimension and / or the space dimension to obtain a sixteen-ary tree after expansion of an obstacle region; Based on a starting point and an ending point of a target flight vehicle, a path search is performed in the sixteen-ary tree after expansion of the obstacle region to determine an optimal path of the target flight vehicle.

[0006] According to the path planning method provided by the present application, the inflation processing of the obstacle information in the sixteen-ary tree in the time dimension and / or the space dimension comprises: The obstacle information in the sixteen-ary tree is extended in a time window, and / or the obstacle information in the sixteen-ary tree is expanded in a spatial geometric volume.

[0007] According to the path planning method provided by the present application, the sixteen-ary tree is constructed based on a preset four-dimensional space range, comprising: A root node representing the four-dimensional space range is created; Starting from the root node, each node is recursively divided into sixteen child nodes until a preset resolution is reached; Sixteen child nodes of each node are determined based on eight spatial sub-regions obtained by spatial dimension division and two time periods obtained by time dimension division.

[0008] According to the path planning method provided in the application, the optimal path of the target aircraft is determined by searching the expanded sixteen-ary tree after the obstacle region. The optimal path of the target aircraft avoiding the obstacle is determined by searching the expanded sixteen-ary tree after the obstacle region based on the A-star search algorithm.

[0009] According to the path planning method provided in the application, the optimal path of the target aircraft avoiding the obstacle is determined by searching the expanded sixteen-ary tree after the obstacle region based on the A-star search algorithm, which comprises: The four-tuple of each node is constructed based on the position information and time information of each node in the expanded sixteen-ary tree after the obstacle region. The four-tuple corresponding to each node is evaluated based on the path cost and heuristic function value to determine the optimal path of the target aircraft avoiding the obstacle.

[0010] According to the path planning method provided in the application, the path cost between adjacent nodes is determined based on the flight distance of the aircraft in the space of adjacent nodes, the flight time of the aircraft in adjacent nodes and the dynamic constraint of the aircraft. The dynamic constraint of the aircraft comprises one or more of the speed of the target aircraft, the acceleration of the target aircraft and the turning radius of the target aircraft.

[0011] According to the path planning method provided in the application, after the optimal path of the target aircraft is determined, the method further comprises: The optimal path is interpolated based on the Bezier curve or the spline curve to obtain a smoothed flight path. The smoothed flight path is adjusted based on the time dimension constraint, the dynamic constraint of the aircraft and the obtained real-time obstacle information to obtain an adjusted flight path.

[0012] According to the path planning method provided in the application, after the optimal path of the target aircraft is determined, the method further comprises: During the movement of the target aircraft along the optimal path, real-time obstacle change information in the four-dimensional space range is obtained. Based on the real-time obstacle change information, the expanded sixteen-ary tree after the obstacle region is updated, and the flight path of the target aircraft is adjusted based on the updated sixteen-ary tree.

[0013] According to the path planning method provided in the application, the preset expansion range is determined based on size information of the obstacle and an influence range of the obstacle on the target aircraft.

[0014] The application further provides a path planning device, comprising the following modules: A hexa-tree construction module is configured to construct a hexa-tree based on a preset four-dimensional space range, and map obstacle information in the four-dimensional space range to nodes in the hexa-tree. An expansion module is configured to perform inflation processing on the obstacle information in the hexa-tree in the time dimension and / or the space dimension based on a preset expansion range, to obtain a hexa-tree after expansion of an obstacle region. A path planning module is configured to perform path searching in the hexa-tree after expansion of the obstacle region based on a starting point and an ending point of the target aircraft, to determine an optimal path of the target aircraft.

[0015] The application further provides an aircraft comprising the path planning device described above.

[0016] The application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the path planning method of any of the above when executing the program.

[0017] The application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the path planning method of any of the above.

[0018] The application further provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the path planning method of any of the above.

[0019] The path planning method and device provided by the application can effectively divide and manage the four-dimensional space in which the target aircraft flies, by constructing a hexa-tree based on a four-dimensional space range and mapping obstacle information to nodes in the hexa-tree. The introduction of the time dimension enables the subsequent path planning to comprehensively consider dynamic obstacles in time, so that the target aircraft can not only avoid obstacles in space based on the planned path, but also handle changes in obstacles in different time periods, thereby improving the comprehensiveness and safety of path planning. At the same time, by performing inflation processing on the obstacle information in the time and space dimensions, and performing path searching in the inflated hexa-tree based on a path searching algorithm, the path planning algorithm can consider the influence of obstacles in a larger range, thereby further improving the safety of the planned path. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort based on these drawings.

[0021] Figure 1 is a flowchart of the path planning method provided by the present application.

[0022] Figure 2 is a flowchart of the path planning method provided by the present application.

[0023] Figure 3 is a structural diagram of the path planning device provided by the present application.

[0024] Figure 4 is a structural diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely in the following with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort belong to the scope of protection of the present application.

[0026] In the related method, the aircraft path planning is realized based on a three-dimensional path planning algorithm. When processing the aircraft path planning, the three-dimensional path planning algorithm cannot fully consider the complexity brought by the time dimension.

[0027] Specifically, the path planning method of the related method usually only focuses on static obstacles in space, and ignores the case that the position of the obstacle may change in different time periods by simply searching for a path in three-dimensional space. This method is easy to cause path conflict or flight insecurity, especially in the scene of dense flight of aircraft in low-altitude airspace. The planned route may intersect with the route of other aircraft in a specific time period, thereby increasing the flight risk.

[0028] Further, three-dimensional path planning algorithms have difficulty in accurately handling time-dependent dynamic obstacles. In low-altitude airspace, the flight path of an aircraft is not only limited by fixed obstacles in space, but also affected by the dynamic routes of other aircraft. Three-dimensional path planning methods fail to effectively address these time-dependent obstacle problems, and cannot guarantee that the generated route is safe throughout the entire flight process. This limitation directly affects the accuracy and practicality of path planning, limiting the ability of aircraft to autonomously fly in complex airspace.

[0029] Due to the lack of comprehensive consideration of the time dimension, related methods have great limitations in flight path planning in low-altitude airspace, and are difficult to adapt to the complex airspace management needs of future low-altitude economy. The three-dimensional path planning algorithm in related methods cannot dynamically adjust and optimize in the time dimension, resulting in the planned route may encounter unforeseen obstacles or flight conflicts during actual execution, increasing the complexity and risk of flight tasks.

[0030] In summary, the three-dimensional path planning method in related methods only considers obstacles in space and does not adequately consider the dynamic nature of the time dimension, which can easily lead to path conflicts or flight risks in the complex environment of low-altitude airspace. Moreover, the three-dimensional path planning method is difficult to cope with dynamic airspace management requirements and cannot flexibly avoid the routes of other aircraft in the time dimension.

[0031] To overcome the shortcomings of related methods, the present application provides a path planning method, Figure 1 is a flowchart of the path planning method provided by the present application, as Figure 1 shown, the method comprises the following steps: Step 110, based on a preset four-dimensional space range, a sixteen-ary tree is constructed, and obstacle information in the four-dimensional space range is mapped to nodes in the sixteen-ary tree; Step 120, based on a preset expansion range, the obstacle information in the sixteen-ary tree is processed in the time dimension and / or the space dimension to obtain a sixteen-ary tree after expansion of the obstacle region; Step 130, based on the starting point and the ending point of the target aircraft, path searching is performed in the sixteen-ary tree after expansion of the obstacle region to determine the optimal path of the target aircraft.

[0032] The execution subject of the path planning method provided in the application can be an electronic device, a component in the electronic device, an integrated circuit, or a chip. The electronic device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a notebook computer, a palm computer, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), and the non-mobile electronic device can be a server, a network attached storage (NAS), or a personal computer (PC), which are not limited in the application.

[0033] The technical solution of the application will be described in detail below with the server executing the path planning method provided in the application as an example.

[0034] In step 110, a sixteen-ary tree corresponding to the preset four-dimensional space range is constructed based on the preset four-dimensional space range.

[0035] It should be noted that the preset four-dimensional space range can be a range supported by the set target aircraft during flight, which specifically includes a three-dimensional space (x, y, z) and a time dimension (t). By determining the preset four-dimensional space range, the boundary box of the flight space of the target aircraft and the start and end range of time are defined.

[0036] The sixteen-ary tree is a kind of multi-ary tree data structure, and each node can have sixteen child nodes. In the four-dimensional space, the sixteen-ary tree can more finely divide the space. The four-dimensional space can be recursively partitioned according to certain rules, and each partitioning divides the current space region into sixteen smaller sub-regions. For example, in a three-dimensional space, the x, y, and z directions can be bisected respectively to obtain eight sub-cubes; and in combination with the time dimension, each sub-cube is bisected on the time axis to obtain sixteen sub-four-dimensional space regions. Each sub-region corresponds to a child node in the sixteen-ary tree, and the root node represents the entire preset four-dimensional space range.

[0037] Optionally, the specific process of constructing the sixteen-ary tree corresponding to the four-dimensional space range can be as follows: The hexa-tree is initialized by creating an empty root node representing the entire four-dimensional space range. Then, starting from the root node, each node is recursively divided into sixteen child nodes. Each child node is one-eighth of the volume of its parent node in space and is divided into a time period in the time dimension. Specifically, for each child node, in the three-dimensional space, each spatial dimension (x, y, z) is evenly divided into two parts, thereby dividing the entire space into eight equal-volume subspaces, forming eight spatial eighths, and in the time dimension, the time range is divided into two parts, thereby forming sixteen child nodes for each spatial eighth. For each child node, the specific range of space and time is recorded, and each node contains information about the space and time range it is responsible for.

[0038] After the basic structure of the hexa-tree is constructed, the spatial position information and time information in the obstacle information are assigned to the corresponding child nodes. If the obstacle spans the space or time range of multiple nodes, it is mapped to these nodes.

[0039] It can be understood that the obstacle information can be determined based on the time information and spatial position information of multiple obstacles in the preset four-dimensional space range. For each obstacle, its spatial position information and time information in the four-dimensional space are determined. Then, starting from the root node of the hexa-tree, the minimum child node that can completely contain the obstacle is found by layer-by-layer downward search according to the division rule, and the related information of the obstacle is stored in the node. If the obstacle spans multiple child nodes, the obstacle information needs to be stored in multiple child nodes involved. In this way, the hexa-tree can accurately record the distribution of obstacles in the four-dimensional space.

[0040] Optionally, during the flight of the aircraft, the hexa-tree can be updated regularly as the environment changes to ensure that it reflects the latest obstacle information and the state of the four-dimensional space. This includes handling the addition, deletion, or movement of obstacles. Through the above steps, a detailed hexa-tree can be constructed for efficient path planning and obstacle avoidance analysis in the four-dimensional space.

[0041] In step 120, based on the preset expansion range, the obstacle information in the hexa-tree is expanded in the time dimension and / or the space dimension to obtain the hexa-tree after the expansion of the obstacle region.

[0042] It should be noted that in actual application, the target aircraft needs to maintain a certain safety distance from the obstacles to avoid collision. Therefore, the obstacle information in the hexagonal tree can be dilated to expand the influence range of the obstacles in time and space. The preset expansion range can be determined by comprehensively considering factors such as the size of the target aircraft, the size of the obstacle, the flight speed, the kinematics and dynamics limitations of the aircraft, safety requirements, and the like.

[0043] When performing hexagonal tree dilation, the main purpose is to expand the obstacle region so that the actual influence range of the obstacle can be better considered during path planning. Starting from each node of the constructed hexagonal tree, the obstacle information recorded in the node is checked. For each obstacle in the node, its expansion range in space and time dimensions is determined, which can be referred to as the dilation range. The expansion in space can be set based on the actual size of the obstacle and its potential impact on the aircraft, and is usually expanded by a certain radius or volume; the expansion in time considers the time window of the existence of the obstacle, and reflects the possible changes of the obstacle in the time dimension by extending the time period.

[0044] In the specific expansion operation, the influence range of the obstacle can be expanded within the spatial range of each node, and the expanded obstacle region is marked in the corresponding child node. At the same time, for the expansion in time dimension, the start and end times of the obstacle influence time window are extended to cover the possible time change range. In this way, the original obstacle region is expanded in space and time to form a larger dilated region.

[0045] During the dilation process of the hexagonal tree, it is necessary to ensure that the dilated obstacle region does not overlap or miss the surrounding nodes, so as to ensure the accuracy and integrity of the path planning. After completing the dilation operation, the obstacle information of each node will include the expanded region, which will be used for subsequent path planning and optimization to avoid possible collision or interference. Through hexagonal tree dilation, the path planning process can consider the influence of obstacles in a larger range, improving the safety and effectiveness of the planned path.

[0046] In step 130, based on the starting point and the end point of the target aircraft, a path search is performed in the hexagonal tree after the expansion of the obstacle region to determine the optimal path of the target aircraft.

[0047] In the path planning phase, the A-star algorithm can be used to calculate the optimal path from the start point to the end point on the constructed and inflated sixteen-ary tree. First, the A-star algorithm defines each node in the four-dimensional space as a four-tuple, including the position (x, y, z) and time (t). These nodes are evaluated by path cost and heuristic function value to calculate the optimal path from the start point to the end point. The heuristic function is usually selected according to the actual application, such as Euclidean distance or Manhattan distance, to estimate the cost from the current node to the target node.

[0048] In the A-star algorithm, it is particularly necessary to handle the kinematic and dynamic constraints between adjacent nodes. Specifically, the algorithm needs to consider the physical limitations of the aircraft's speed, acceleration, and flight attitude when expanding nodes. This means that when calculating the path cost between adjacent nodes, not only the spatial distance needs to be considered, but also the time change needs to be considered. Each pair of adjacent nodes (position, time) must satisfy these dynamic constraints to ensure the actual feasibility of the path. By detecting the kinematic constraints between adjacent nodes, the algorithm ensures that the aircraft will not exceed its physical capabilities when moving, such as turning radius or speed limits.

[0049] In the path planning process, the A-star algorithm evaluates all adjacent nodes of each node and calculates the actual cost and heuristic cost of these adjacent nodes. The actual cost includes the spatial and temporal consumption from the current node to the adjacent node, while considering the inflated obstacle information to avoid collisions. The heuristic cost estimates the cost from the adjacent node to the end point. Through such evaluation, the algorithm can select the optimal path while considering all dynamic constraints.

[0050] The path planning method provided by the present application can effectively divide and manage the four-dimensional space of the target aircraft flight by constructing a sixteen-ary tree in a four-dimensional space range and mapping obstacle information to nodes in the sixteen-ary tree. The introduction of the time dimension allows the subsequent path planning to consider dynamic obstacles in time, so that the target aircraft based on the planned path can not only avoid obstacles in space, but also handle changes in obstacles in different time periods, improving the comprehensiveness and safety of path planning. At the same time, by performing time and space dimension inflation processing on the obstacle information and performing path search in the inflated sixteen-ary tree based on the path search algorithm, the path planning algorithm can consider the influence of obstacles in a larger range, further improving the safety and effectiveness of the planned path.

[0051] In one embodiment, the inflation processing of the obstacle information in the sixteen-ary tree in the time dimension and / or the space dimension includes: lengthening the obstacle information in the sixteen-ary tree in the time window, and / or expanding the obstacle information in the sixteen-ary tree in the spatial geometric volume.

[0052] For the expansion of the obstacle information in the hexa-tree, inflation processing can be performed from the time dimension, from the space dimension, or from both the time dimension and the space dimension.

[0053] It should be noted that the obstacle information specifically includes time information of the obstacle and spatial position information of the obstacle.

[0054] The time dimension inflation processing is to extend the time window in the obstacle information in the hexa-tree, which considers that the duration of the influence of the obstacle may exceed the actual existence time, or reserves a certain safety time margin for path planning and the like.

[0055] According to the actual application scenario and safety requirements, a suitable time window extension value can be set. The selection of the extension value can comprehensively consider various factors, such as the motion characteristics of the obstacle (for a moving obstacle), the response time, and the accuracy requirement of path planning.

[0056] The space dimension inflation processing is to expand the spatial geometric volume of the obstacle information in the hexa-tree, which considers that there may be a safety area around the obstacle or the influence of the physical characteristics (such as the collision radius of the object) of the obstacle itself on the surrounding space.

[0057] The specific implementation process of expanding the spatial geometric volume can be implemented by taking the geometric center of the obstacle as a reference and expanding a fixed distance in each direction.

[0058] The path planning method provided by the embodiments of the present application can significantly improve the accuracy of environment modeling and the safety of path planning by performing time dimension and / or space dimension inflation processing on the obstacle information in the hexa-tree based on reasonable time window extension and spatial geometric volume expansion implementation.

[0059] In one embodiment, based on a preset four-dimensional space range, a hexa-tree is constructed, including: creating a root node representing the four-dimensional space range; starting from the root node, recursively dividing each node into sixteen child nodes until a preset resolution is reached; wherein the sixteen child nodes of each node are determined based on eight spatial sub-regions obtained by spatial dimension division and two time periods obtained by time dimension division.

[0060] Specifically, the construction process of the hexa-tree can include: First, a root node is created, which represents the entire given four-dimensional space range.

[0061] Starting from the root node, recursively divide, in the spatial dimension, the space region represented by the current node into eight sub-regions, and in the time dimension, divide the corresponding time interval into two time periods. The combination of the division in the spatial and time dimensions causes each node to generate sixteen child nodes.

[0062] Continue the process recursively until the child nodes reach a preset resolution, at which time the construction of the hexa-tree is completed. It should be noted that the preset resolution can be the size of the smallest space unit and time unit that the hexa-tree can distinguish. The preset resolution can be set according to the needs of node division.

[0063] The path planning method provided by the embodiments of the present application can more finely divide the four-dimensional space by constructing a hexa-tree in a four-dimensional space range, so that the path search in a complex environment is more efficient and accurate. The hierarchical structure of the hexa-tree supports dynamic obstacle processing and path optimization, and is more adaptable.

[0064] In one embodiment, the path search in the hexa-tree after the expansion of the obstacle region determines the optimal path of the target aircraft, including: based on the A-star search algorithm, performing path search in the hexa-tree after the expansion of the obstacle region to determine the optimal path of the target aircraft to avoid obstacles.

[0065] The A-star search algorithm is used to determine the optimal obstacle avoidance path of the target aircraft in the hexa-tree after the expansion of the obstacle region. The A-star algorithm takes the starting node as the starting point and comprehensively considers the actual cost from the starting point to the current node and the heuristic estimated cost from the current node to the target node.

[0066] In the hexa-tree, the A-star algorithm searches node by node, and judges whether the node is passable with the help of the expanded obstacle information. When the target node is reached, the path is traced back, and the optimal path that can make the target aircraft successfully avoid obstacles and has the minimum cost is obtained.

[0067] In one embodiment, based on the A-star search algorithm, the path search in the hexa-tree after the expansion of the obstacle region determines the optimal path of the target aircraft to avoid obstacles, including: based on the position information and time information of each node in the hexa-tree after the expansion of the obstacle region, constructing a four-tuple of each node; based on the path cost and the heuristic function value, evaluating the four-tuple corresponding to each node to determine the optimal path of the target aircraft to avoid obstacles.

[0068] The A-star search algorithm is used to calculate the optimal path from the starting point to the end point on the constructed and inflated hexa-tree. First, the A-star search algorithm defines each node in the four-dimensional space as a four-tuple, including the position (x, y, z) and the time (t).

[0069] Each node in the hexa-tree is evaluated by a path cost and a heuristic function value to calculate the optimal path from the start to the end. The heuristic function is usually chosen according to the actual application, such as Euclidean distance or Manhattan distance, to estimate the cost from the current node to the target node.

[0070] In one embodiment, the path cost between adjacent nodes is determined based on the flight distance of the aircraft in the adjacent node space, the flight time of the aircraft at the adjacent node, and the dynamic constraints of the aircraft, including one or more of the speed of the target aircraft, the acceleration of the target aircraft, and the turning radius of the target aircraft.

[0071] It should be noted that in the A* search algorithm, it is particularly necessary to handle the kinematic and dynamic constraints between adjacent nodes. Specifically, the algorithm needs to consider the physical limitations of the target aircraft's speed, acceleration, turning radius, etc. when expanding nodes. This means that when calculating the path cost between adjacent nodes, not only the flight distance of the aircraft in the adjacent node space needs to be considered, but also the flight time of the aircraft at the adjacent node needs to be considered. Each pair of adjacent nodes (position, time) must satisfy these dynamic constraints to ensure the actual feasibility of the path. By detecting the kinematic constraints between adjacent nodes, the algorithm ensures that the aircraft will not exceed its physical capabilities, such as turning radius or speed limits, when moving.

[0072] In the path planning process, the A* search algorithm evaluates all adjacent nodes of each node and calculates the actual cost and heuristic cost of these adjacent nodes. The actual cost includes the consumption of space and time from the current node to the adjacent node, while considering the inflated obstacle information to avoid collisions. The heuristic cost estimates the cost from the adjacent node to the end. Through such evaluation, the algorithm can select the optimal path while considering all dynamic constraints.

[0073] The final result is a path that meets all kinematic and dynamic constraints, which can effectively guide the aircraft to fly in a complex four-dimensional space.

[0074] In one embodiment, after determining the optimal path of the target aircraft, it further includes: interpolating the optimal path based on a Bezier curve or a spline curve to obtain a smoothed flight path; adjusting the smoothed flight path based on the time dimension constraints, the dynamic constraints of the aircraft, and the obtained real-time obstacle information to obtain an adjusted flight path.

[0075] The optimal path can be further optimized to improve the optimal path generated by the A* algorithm, making it smoother, more efficient, and meeting the actual flight requirements. In this stage, the optimization goals can include reducing path length, avoiding unnecessary sharp turns, and optimizing the smoothness of the flight trajectory, thereby improving the flight efficiency and safety of the aircraft.

[0076] The optimization process first involves a detailed analysis of the optimal path generated by the A* algorithm to identify and correct potential path problems. This includes checking each node in the path and evaluating the connections between its adjacent nodes. The path optimization algorithm takes into account the actual flight characteristics of the aircraft, such as minimum turning radius, maximum acceleration, and flight attitude restrictions, ensuring that the optimized path meets these dynamic constraints.

[0077] To achieve the smoothing and optimization of the path, curve smoothing algorithms and path resampling can be used. For example, a Bezier curve or a spline curve can be used to interpolate the path, generating a smoother trajectory. By reducing sharp turns and unnecessary bends in the path, the optimization algorithm can significantly improve the flight stability and comfort of the aircraft.

[0078] In the process of path optimization, time constraints also need to be considered. That is, optimization not only focuses on spatial smoothness, but also ensures the reasonableness of time. For example, the time interval on the path must match the flight speed and acceleration of the aircraft to avoid excessive speed or slow speed in actual flight.

[0079] In addition, the optimization stage also needs to recheck the obstacle information based on the obtained real-time obstacle information, ensuring that the optimized path still avoids all spatial and temporal obstacles. If new obstacles or path problems are found during the optimization process, the algorithm will recalculate the path to ensure that the final generated path is safe and feasible in actual flight.

[0080] Finally, the optimized path will be saved as the flight plan of the aircraft, guiding the aircraft to fly along the optimized trajectory in actual flight. By balancing the length, smoothness, and flight safety of the path, an optimal flight solution that meets actual requirements is provided.

[0081] In one embodiment, after determining the optimal path of the target aircraft, it further includes: obtaining real-time obstacle change information in the four-dimensional space range during the movement of the target aircraft along the optimal path; updating the sixteen-cubic tree after the expansion of the obstacle region based on the real-time obstacle change information, and adjusting the flight path of the target aircraft based on the updated sixteen-cubic tree.

[0082] After determining the optimal path, the optimal path can be dynamically updated, and the specific dynamic updating process can include: The dynamic updating and replanning phase ensures that the aircraft can adapt to environmental changes during actual flight, especially when obstacle information changes. The main task of this phase is to monitor the dynamic changes of obstacles in real time during the flight of the aircraft along the determined path, obtain real-time obstacle change information, and adjust the flight path based on the obtained real-time obstacle change information to maintain the safety and effectiveness of the flight.

[0083] During flight, the nodes of the hexa-tree are continuously updated based on real-time obstacle change information obtained from real-time sensor data. Real-time obstacle change information includes the appearance and disappearance of obstacles in the environment, the position changes of obstacles, and changes in the time dimension. Real-time analysis of this data and updating of obstacle information in the hexa-tree ensures that the obstacle data in the tree structure is always up-to-date.

[0084] When changes in obstacles on the path are detected, the safety of the path will be re-evaluated based on the dynamic updating algorithm. If it is found that the original path is no longer feasible or has safety risks under the new obstacle distribution, the algorithm will trigger the replanning process. The goal of replanning is to recalculate the path based on new obstacle information and find a new, effective flight trajectory.

[0085] During the replanning process, the A-star algorithm will perform path search on the updated hexa-tree. Since the adjacent nodes may have changed, the A-star algorithm needs to consider the new spatial and temporal constraints between nodes, including the kinematics and dynamics constraints of the aircraft. Ensure that the flight speed, acceleration, and other dynamic constraints of the aircraft are considered when replanning the path.

[0086] To improve the efficiency of replanning, local path correction techniques can also be combined, which means adjusting the path locally near the original path rather than recalculating the entire path. This method can significantly shorten the replanning time and improve the response speed of the system.

[0087] Finally, the path after dynamic updating and replanning will be applied to the flight control system of the aircraft to ensure that the aircraft can safely avoid new obstacles and successfully complete the flight mission. This process guarantees the adaptability and flight safety of the aircraft in a dynamic environment.

[0088] In one embodiment, the preset expansion range is determined based on size information of the obstacle and an influence range of the obstacle on the target aircraft.

[0089] In practical applications, the target aircraft needs to maintain a certain safety distance from the obstacles to avoid collision. Therefore, the obstacle information in the hexoctree needs to be inflated to expand the influence range of the obstacles in time and space. The preset expansion range can be determined according to the size information of the obstacles and the influence range of the obstacles on the target aircraft.

[0090] It can be understood that different obstacles have different sizes, and the target aircraft needs to avoid obstacles during flight in the path. At this time, the size of the obstacle needs to be considered. In addition, for the case where the obstacle is an aircraft, the influence caused by the airflow generated during the flight of the obstacle also needs to be considered, so the influence range of the obstacle on the target aircraft needs to be determined.

[0091] Among them, based on the expansion according to the size information of the obstacle and the influence range of the obstacle on the target aircraft, the expansion can be realized based on a certain radius or volume.

[0092] The application also provides an implementation process of the path planning method provided by the application, such as Figure 2 The flowchart of the path planning method provided by the application is shown.

[0093] Step 210, hexoctree construction: according to a given four-dimensional space range, a hexoctree is constructed, space and time nodes are divided, and obstacle information is mapped into corresponding nodes.

[0094] Step 220, hexoctree inflation: each obstacle is inflated in space and time dimensions to form a three-dimensional space and time safety area.

[0095] Step 230, initial path planning: an A-star algorithm is used to perform initial path planning on the hexoctree to generate an optimal path from the starting point to the ending point, avoiding all known spatial and temporal obstacles.

[0096] Step 240, path optimization: the initially planned path is optimized to make it more consistent with the actual needs of the unmanned aerial vehicle flight.

[0097] Step 250, dynamic updating and re-planning: during flight, the changes of obstacles are monitored in real time, and the hexoctree nodes are dynamically updated according to the new information. If it is found that the obstacles on the path have changed in time, the algorithm will recalculate the path to ensure flight safety.

[0098] Through the implementation process, compared with the three-dimensional path planning method in the related method which only considers static obstacles in space, the application introduces the time dimension, so that the path planning can consider dynamic obstacles in time. In this way, not only obstacles in space are avoided, but also changes of obstacles in different time periods are processed, improving the comprehensiveness and safety of path planning.

[0099] The path planning method in the related method usually uses a simple grid or graph structure for spatial division, while the sixteen-ary tree data structure used in the application can more finely divide the four-dimensional space, making the path search in complex environment more efficient and accurate. The hierarchical structure of the sixteen-ary tree supports dynamic obstacle processing and path optimization, and is more adaptable.

[0100] The unique time dimension expansion method of the application integrates the changes of dynamic obstacles in time into path planning, avoiding the limitations of related methods that ignore changes in the time dimension. This innovation can better cope with complex situations of intensive unmanned aerial vehicle flight in practical applications, effectively reducing flight risks.

[0101] In addition, by comprehensively considering four-dimensional space information and dynamic obstacles, the application solves the limitations of related methods in complex dynamic environment path planning, meeting the high requirements of future low-altitude economy for unmanned aerial vehicle autonomous flight. This makes the unmanned aerial vehicle more efficient and safe in complex airspace to complete the task.

[0102] The path planning device provided by the application is described below. The path planning device described below can be referred to in conjunction with the path planning method described above.

[0103] As shown in the following description, the device includes: Figure 3 A sixteen-ary tree construction module 310 is configured to construct a sixteen-ary tree based on a preset four-dimensional space range, and map obstacle information in the four-dimensional space range to nodes in the sixteen-ary tree. An expansion module 320 is configured to perform inflation processing on the obstacle information in the sixteen-ary tree in the time dimension and / or the space dimension based on a preset expansion range, to obtain a sixteen-ary tree after expansion of the obstacle region. A path planning module 330 is configured to perform path search in the sixteen-ary tree after expansion of the obstacle region based on the starting point and the ending point of the target aircraft, to determine the optimal path of the target aircraft.

[0104] ​The path planning device provided in the application can effectively divide and manage the four-dimensional space in which the target aircraft flies by constructing a sixteen-ary tree in a four-dimensional space range and mapping obstacle information to nodes in the sixteen-ary tree. The introduction of the time dimension enables the subsequent path planning to comprehensively consider dynamic obstacles in time, so that the target aircraft can not only avoid obstacles in space based on the planned path, but also process changes in obstacles in different time periods, thereby improving the comprehensiveness and safety of path planning. At the same time, by performing inflation processing on the obstacle information in the time and space dimensions and performing path search in the sixteen-ary tree after inflation based on a path search algorithm, the path planning algorithm can consider the influence of obstacles in a larger range, thereby further improving the safety and effectiveness of the planned path.

[0105] In one embodiment, the expansion module 320 is specifically configured to: The inflation processing on the obstacle information in the sixteen-ary tree in the time dimension and / or the space dimension includes: The extension of the obstacle information in the sixteen-ary tree in the time window and / or the expansion of the obstacle information in the sixteen-ary tree in the space geometric volume.

[0106] In one embodiment, the sixteen-ary tree construction module 310 is specifically configured to: The construction of the sixteen-ary tree based on the preset four-dimensional space range includes: creating a root node representing the four-dimensional space range; recursively dividing each node into sixteen child nodes until a preset resolution is reached, starting from the root node; wherein the sixteen child nodes of each node are determined based on eight spatial sub-regions obtained by dividing in the spatial dimension and two time periods obtained by dividing in the time dimension.

[0107] In one embodiment, the path planning module 330 is specifically configured to: The path search in the sixteen-ary tree after expansion of the obstacle region to determine the optimal path of the target aircraft includes: performing path search in the sixteen-ary tree after expansion of the obstacle region based on an A-star search algorithm to determine the optimal path of the target aircraft to avoid obstacles.

[0108] In one embodiment, the path planning module 330 is further specifically configured to: The path search in the sixteen-ary tree after expansion of the obstacle region based on the A-star search algorithm to determine the optimal path of the target aircraft to avoid obstacles includes: construct a quadruple for each node based on the position information and the time information of each node in the extended sixteen-ary tree; evaluate the quadruple corresponding to each node based on the path cost and the heuristic function value, and determine an optimal path for the target aircraft to avoid the obstacle.

[0109] In one embodiment, the path planning module 330 is further specifically configured to: The path cost between adjacent nodes is determined based on the flight distance of the aircraft in the space of adjacent nodes, the flight time of the aircraft at adjacent nodes, and the dynamic constraint of the aircraft. The dynamic constraint of the aircraft includes one or more of the speed of the target aircraft, the acceleration of the target aircraft, and the turning radius of the target aircraft.

[0110] In one embodiment, the path planning module 330 is further specifically configured to: After determining the optimal path for the target aircraft, the method further includes: interpolating the optimal path based on a Bezier curve or a spline curve to obtain a smoothed flight path; adjusting the smoothed flight path based on the time dimension constraint, the dynamic constraint of the aircraft, and the obtained real-time obstacle information to obtain an adjusted flight path.

[0111] In one embodiment, the path planning module 330 is further specifically configured to: After determining the optimal path for the target aircraft, the method further includes: obtaining real-time obstacle change information in the four-dimensional space range during movement of the target aircraft along the optimal path; updating the extended sixteen-ary tree based on the real-time obstacle change information, and adjusting the flight path of the target aircraft based on the updated sixteen-ary tree.

[0112] In one embodiment, the extension module 320 is further specifically configured to: The preset extension range is determined based on the size information of the obstacle and the influence range of the obstacle on the target aircraft.

[0113] Figure 4 An example of a schematic diagram of the physical structure of an electronic device is shown in FIG. 1. Figure 4As shown, the electronic device can include a processor 410, a communications interface 420, a memory 430, and a communications bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other through the communications bus 440. The processor 410 can invoke a logical instruction in the memory 430 to execute a path planning method, which includes: based on a preset four-dimensional space range, constructing a sixteen-ary tree, and mapping obstacle information in the four-dimensional space range to a node in the sixteen-ary tree; Based on a preset expansion range, performing inflation processing on the obstacle information in the sixteen-ary tree in the time dimension and / or the space dimension to obtain a sixteen-ary tree after expansion of an obstacle region; Based on a starting point and an ending point of a target aircraft, performing path searching in the sixteen-ary tree after expansion of the obstacle region to determine an optimal path of the target aircraft.

[0114] In addition, the logical instruction in the memory 430 described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0115] On the other hand, the present application also provides a computer program product, which includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the path planning method provided by the above-mentioned methods, which includes: based on a preset four-dimensional space range, constructing a sixteen-ary tree, and mapping obstacle information in the four-dimensional space range to a node in the sixteen-ary tree; Based on a preset expansion range, performing inflation processing on the obstacle information in the sixteen-ary tree in the time dimension and / or the space dimension to obtain a sixteen-ary tree after expansion of an obstacle region; Based on the start point and the end point of the target aircraft, a path search is performed in the sixteen-ary tree after expansion of the obstacle region, and an optimal path of the target aircraft is determined.

[0116] In another aspect, the application also provides a non-transitory computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the path planning method provided by the above method, the method comprising: based on a preset four-dimensional space range, constructing a sixteen-ary tree, and mapping obstacle information in the four-dimensional space range to nodes in the sixteen-ary tree; Based on a preset expansion range, performing inflation processing on the obstacle information in the sixteen-ary tree in the time dimension and / or the space dimension to obtain a sixteen-ary tree after expansion of the obstacle region; Based on the start point and the end point of the target aircraft, a path search is performed in the sixteen-ary tree after expansion of the obstacle region, and an optimal path of the target aircraft is determined.

[0117] The device embodiments described above are only schematic, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment. Those skilled in the art can understand and implement without creative labor.

[0118] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software plus necessary general hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0119] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A path planning method, characterized in that, include: Based on a preset four-dimensional space range, a hexadecimal tree is constructed, and obstacle information within the four-dimensional space range is mapped to nodes in the hexadecimal tree; Based on a preset expansion range, the obstacle information in the hexadecimal tree is expanded in terms of time and / or space to obtain a hexadecimal tree with expanded obstacle region. Based on the starting point and ending point of the target aircraft, a path search is performed in the hexadecimal tree after the obstacle area is expanded to determine the optimal path of the target aircraft.

2. The path planning method according to claim 1, characterized in that, The process of dilating the obstacle information in the hexadecimal tree in terms of time and / or space dimensions includes: The obstacle information in the hexadecimal tree is extended in terms of time window, and / or the obstacle information in the hexadecimal tree is expanded in terms of spatial geometric volume.

3. The path planning method according to claim 1, characterized in that, The construction of a hexadecimal tree based on a preset four-dimensional spatial range includes: Create a root node representing the range of the four-dimensional space; Starting from the root node, each node is recursively divided into sixteen child nodes until the preset resolution is reached; The sixteen child nodes of each node are determined based on eight spatial sub-regions obtained by dividing the space dimension and two time periods divided by the time dimension.

4. The path planning method according to claim 1, characterized in that, The path search performed in the expanded hexadecimal tree of the obstacle region to determine the optimal path for the target aircraft includes: Based on the A-Star search algorithm, a path search is performed in the expanded hexadecimal tree of the obstacle region to determine the optimal path for the target aircraft to avoid the obstacles.

5. The path planning method according to claim 4, characterized in that, The A-Star search algorithm performs path search in the expanded hexadecimal tree of the obstacle region to determine the optimal path for the target aircraft to avoid the obstacles, including: Based on the position and time information of each node in the expanded hexadecimal tree of the obstacle region, construct a quadruple for each node; Based on path cost and heuristic function value, the quadruples corresponding to each node are evaluated to determine the optimal path for the target aircraft to avoid obstacles.

6. The path planning method according to claim 5, characterized in that, The path cost between adjacent nodes is determined based on the flight distance of the aircraft in the adjacent node space, the flight time of the aircraft in the adjacent node, and the dynamic constraints of the aircraft. The dynamic constraints of the aircraft include one or more of the target aircraft's velocity, target aircraft's acceleration, and target aircraft's turning radius.

7. The path planning method according to claim 1, characterized in that, After determining the optimal path for the target aircraft, the process also includes: The optimal path is interpolated based on Bézier curves or spline curves to obtain a smoothed flight path. Based on time constraints, aircraft dynamic constraints, and acquired real-time obstacle information, the smoothed flight path is adjusted to obtain the adjusted flight path.

8. The path planning method according to claim 1, characterized in that, After determining the optimal path for the target aircraft, the process also includes: During the movement of the target aircraft along the optimal path, real-time obstacle change information in the four-dimensional space is acquired; Based on the real-time obstacle change information, the expanded hexadecimal tree of the obstacle region is updated, and the flight path of the target aircraft is adjusted based on the updated hexadecimal tree.

9. The path planning method according to claim 1, characterized in that, The preset extension range is determined based on the size information of the obstacle and the range of influence of the obstacle on the target aircraft.

10. A path planning device, characterized in that, include: A hexadecimal tree construction module is used to construct a hexadecimal tree based on a preset four-dimensional space range, and to map obstacle information within the four-dimensional space range to nodes in the hexadecimal tree; An expansion module is used to perform time and / or spatial expansion processing on the obstacle information in the hexadecimal tree based on a preset expansion range, so as to obtain a hexadecimal tree with expanded obstacle region. The path planning module is used to perform path search in the expanded hexadecimal tree of the obstacle area based on the starting point and ending point of the target aircraft to determine the optimal path of the target aircraft.

11. An aircraft, characterized in that, Includes the path planning device as described in claim 10.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the path planning method as described in any one of claims 1 to 9.

13. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the path planning method as described in any one of claims 1 to 9.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the path planning method as described in any one of claims 1 to 9.

Images