A method, device, equipment and storage medium for multi-level motion planning of aircraft

Abstract

The present invention discloses a method, device, equipment and storage medium for multi-level motion planning of an aircraft. The method comprises: in the first-level path planning, a path-finding algorithm is used to determine a target waypoint; wherein the target waypoint is composed of each waypoint between the route starting point and the route end point; in the second-level path planning, a target path is generated based on the target waypoint, the route starting point and the route end point based on a hard constraint method; in the third-level path planning, a local path planning algorithm is used to determine control points based on the target path, and the target path is optimized according to the control points to obtain an optimized path; wherein the control points are used to change the curve shape of the path to optimize the path. This technical solution realizes all-round obstacle perception and obstacle avoidance capabilities from short distance to long distance. The path planning strategy can be dynamically adjusted according to the scale and complexity of the obstacle to ensure the safe and efficient operation of the drone in a complex environment.

Description

Technical Field

[0001] The present invention relates to the field of motion planning technology, and in particular to a method, device, equipment and storage medium for multi-level motion planning of an aircraft. Background Art

[0002] Against the backdrop of the rapid development of drone technology, traditional binocular parallax models and obstacle avoidance algorithms face challenges in dealing with large-scale and complex obstacles.

[0003] Traditional methods usually focus on local path planning and short-range obstacle avoidance, and have limited ability to handle large and long-range obstacles in complex environments. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for multi-level motion planning of an aircraft, which can dynamically adjust the path planning strategy according to the scale and complexity of obstacles.

[0005] According to one aspect of the present invention, a method for multi-level motion planning of an aircraft is provided, the method comprising:

[0006] In the first level of path planning, a pathfinding algorithm is used to determine a target waypoint; wherein the target waypoint is composed of each waypoint between the route start point and the route end point;

[0007] In the second-level path planning, a target path is generated according to the target waypoint, the route starting point and the route end point based on a hard constraint method;

[0008] In the third-level path planning, a local path planning algorithm is used to determine control points based on the target path, and the target path is optimized according to the control points to obtain an optimized path; wherein the control points are used to change the curve shape of the path.

[0009] According to another aspect of the present invention, there is provided a multi-level motion planning device for an aircraft, the device comprising:

[0010] A target waypoint determination module is used to determine the target waypoint by using a pathfinding algorithm in the first-level path planning; wherein the target waypoint is composed of each waypoint between the route starting point and the route end point;

[0011] A target path generation module, used for generating a target path according to the target waypoint, the route starting point and the route end point based on a hard constraint method in the second-level path planning;

[0012] The optimized path obtaining module is used to determine the control points based on the target path using a local path planning algorithm in the third-layer path planning, and optimize the target path according to the control points to obtain the optimized path; wherein the control points are used to change the curve shape of the path.

[0013] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0014] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a multi-level motion planning method for an aircraft as described in any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a multi-level motion planning method for an aircraft as described in any embodiment of the present invention when executed.

[0016] The technical solution of the embodiment of the present invention is to determine the target waypoint by using the path-finding algorithm in the first-level path planning, and then generate the target path based on the target waypoint, the route starting point and the route end point based on the hard constraint method in the second-level path planning, and determine the control points based on the target path by using the local path planning algorithm in the third-level path planning, and optimize the target path according to the control points to obtain the optimized path. This technical solution can dynamically adjust the path planning strategy according to the scale and complexity of obstacles by designing a three-level planning framework from coarse to fine.

[0017] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 is a flowchart of a multi-level motion planning method for an aircraft provided according to Embodiment 1 of the present invention;

[0020] Figure 2A schematic diagram of a multi-level motion planning process for an aircraft provided in Embodiment 2 of the present invention;

[0021] Figure 3 It is a schematic diagram of a multi-level motion planning framework for an aircraft with respect to obstacles of multiple sizes provided in the second embodiment of the present application;

[0022] Figure 4 A schematic diagram of the structure of a multi-level motion planning device for an aircraft provided in Embodiment 3 of the present invention;

[0023] Figure 5 It is a structural schematic diagram of an electronic device for implementing a multi-level motion planning method for an aircraft according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification 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 data 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] Embodiment 1

[0027] Figure 1 This is a flowchart of a multi-level motion planning method for an aircraft provided according to the first embodiment of the present invention. This embodiment is applicable to the case of generating a planned path that can adapt to obstacles of different sizes in real time. The method can be executed by a multi-level motion planning device for an aircraft. The multi-level motion planning device for an aircraft can be implemented in the form of hardware and / or software. The multi-level motion planning device for an aircraft can be configured in a device. For example, the device can be a background server or other device with communication and computing capabilities. Figure 1 As shown, the method includes:

[0028] S110. In the first-level path planning, a path-finding algorithm is used to determine a target waypoint; wherein the target waypoint is composed of each waypoint between a route start point and a route end point.

[0029] In this embodiment, the target waypoints are composed of each waypoint between the route start point and the route end point, and each target waypoint can be obtained by segmenting the target route. Specifically, the target route can be segmented based on distance. For example, the distance can be set to 150 meters, that is, the target route is segmented every 150 meters.

[0030] Specifically, in the first-level path planning, a pathfinding algorithm is used to generate a guide path connecting the route start point and the route end point in the free space, and by generating a target waypoint, the time and space complexity of each path search is not too high, and the target waypoint is ensured not to be in an obstacle. Among them, the pathfinding algorithm includes depth-first search method, genetic algorithm, etc.

[0031] Optionally, in the first-level path planning, a path-finding algorithm is used to determine a target waypoint, including steps A1-A3:

[0032] Step A1: perform route planning according to the predetermined route starting point and route end point to obtain the target route;

[0033] The starting point and the end point of the route can be pre-set according to the flight requirements of the drone. The drone may include a quad-rotor aircraft.

[0034] In this embodiment, a path planning method can be used to generate a target route connecting the route start point and the route end point in the free space. The path planning method may include a sampling-based method, a search-based method, etc. The sampling-based method generates possible paths by random sampling, and then selects the best path as the target path; the search-based method discretizes the state space into a graph in a certain way, and then uses various heuristic search algorithms to search for feasible solutions or even optimal solutions, including graph search basics, jump point search algorithms, etc.

[0035] Step A2, segmenting the target route to obtain various waypoints;

[0036] Furthermore, in order to be applicable to large-scale flights, after setting the route starting point and the route end point to generate a target route, the target route is segmented to obtain each waypoint after segmentation.

[0037] Step A3: adjusting each waypoint according to the position of each waypoint and the preset adjustment step to obtain the target waypoint.

[0038] The adjustment step size can be set dynamically according to the waypoint position adjustment requirements. express.

[0039] Furthermore, each waypoint obtained after segmentation is likely to be in an obstacle, so each waypoint needs to be adjusted to avoid the obstacle, thereby determining the target waypoint.

[0040] Specifically, the following formula can be used to adjust each waypoint:

[0041] ;

[0042] in, is the location of the next waypoint, is the location of the current target waypoint, is the step length, The location of the next target waypoint.

[0043] Furthermore, after obtaining each target waypoint, path planning is performed, with the starting point being the current position of the drone and the end point being the target waypoint (the next waypoint or the end point of the route). Since the path points obtained based on the path planning method are relatively small in spacing, which will lead to the Runge phenomenon during subsequent path optimization, the Douglas Peucker algorithm is used to thin the obtained path. The Douglas Peucker algorithm mainly samples the curve, that is, takes a finite number of points on the curve, converts it into a broken line, and can maintain the original shape to a certain extent.

[0044] Specifically, during the path planning process, a target route is generated that connects the route start point and the route end point in the free space, and by generating target waypoints, it is ensured that the time and space complexity of each path search is not too high and that the target waypoint is not in an obstacle.

[0045] By adjusting the waypoints to determine the target waypoint, obstacles of different sizes in a wide range can be bypassed during the path planning process, ensuring that the drone can operate safely and efficiently in complex environments.

[0046] Optionally, after obtaining the target waypoint, the method further includes steps B1-B2:

[0047] Step B1, determining a first distance and a second distance according to a preset time condition; wherein the first distance is the distance between the position of the UAV and the starting point of the route; and the second distance is the distance between the starting point of the route and the end point of the route;

[0048] The time condition can be set according to the target waypoint replanning requirements. For example, the time condition can be set as , that is, every time Perform a path planning.

[0049] Specifically, every time The first distance is obtained by calculating the distance between the position of the UAV and the starting point of the route; and the second distance is obtained by calculating the distance between the starting point of the route and the end point of the route.

[0050] Step B2: When the ratio of the first distance to the second distance is greater than a preset threshold, adjusting the target waypoint.

[0051] In this embodiment, the threshold value may also be set according to the target waypoint replanning requirement.

[0052] In this solution, in order to better adapt to the changing environment, a timed re-planning mechanism is introduced. Perform a path planning. The basis of path planning is to determine whether the target waypoint needs to be updated to the next collision-free waypoint and to search for a path to the target waypoint.

[0053] Specifically, it is determined whether the ratio of the first distance to the second distance is greater than a preset threshold. If so, the target waypoint is adjusted and the path is replanned; if not, the path is not replanned.

[0054] By adjusting the target waypoints to achieve path replanning, the accuracy of path planning can be improved, as well as the ability of the drone to operate in complex environments.

[0055] S120. In the second-level path planning, a target path is generated according to the target waypoint, the route starting point and the route ending point based on a hard constraint method.

[0056] In this solution, a path planning method can be used to process the target waypoint, the route starting point and the route end point to generate a target path. The path planning method may include a sampling-based method, a search-based method, and the like.

[0057] Specifically, in the second-level path planning, trajectory optimization is used to optimize the geometry of the guidance path based on the hard constraint method, which can reduce the computational resources required to generate the target path. Among them, the hard constraint method is used to constrain the path to avoid falling into a local minimum.

[0058] Optionally, in the second-level path planning, a target path is generated according to the target waypoint, the route starting point and the route end point based on a hard constraint method, including steps C1-C2:

[0059] Step C1, determining a path constraint condition; wherein the path constraint condition is used to constrain the path to avoid falling into a local minimum;

[0060] Among them, the path constraint conditions are used to constrain the path to avoid falling into local minima, including the location of the route starting point, the location of the route end point, the initial and final speed limits of the drone, and time allocation. Time is the ratio of the straight-line distance to the maximum speed. The maximum speed is variable. In order to ensure that the drone can fly fast in places with sparse obstacles and fly slowly in places with dense obstacles, a variable speed strategy based on the distance from the drone to the obstacle is adopted. A cubic polynomial is fitted between the obstacle distance and the expected speed to obtain a mapping relationship model between distance and speed, and the maximum speed is dynamically adjusted during path optimization.

[0061] Step C2: Generate a target path according to the path constraint conditions, the target waypoint, the route starting point and the route end point.

[0062] In this scheme, in order to quickly optimize the geometrically continuous and obstacle-free target path and guide the path to avoid falling into the local minimum, a hard constraint method can be used, and the target path is generated through a closed-form solution. Among them, the hard constraint requires that both the equality constraint and the inequality constraint must be satisfied under global conditions, so that the generated path can be an acceptable solution.

[0063] By optimizing the geometry of the path, the computational resources required to generate the target path can be reduced.

[0064] S130. In the third-level path planning, a local path planning algorithm is used to determine control points based on the target path, and the target path is optimized according to the control points to obtain an optimized path; wherein the control points are used to change the curve shape of the path.

[0065] In this embodiment, the control point is used to change the curve shape of the path, and multiple points can be selected from the target path as the control points. Specifically, multiple points can be selected from the target path as the control points based on a preset distance.

[0066] Optimized Path In this solution, the target path can be optimized by optimizing the control points. Specifically, the optimized path can be generated by uniform B-splines.

[0067] In this embodiment, a three-layer planning framework from coarse to fine is designed to generate an optimized path that can adapt to obstacles of different sizes in real time. The layers of the framework are cascaded and can be applied to drones with different computing power. In the first layer, a segmented pathfinding algorithm with timed replanning is used to generate a guide path connecting the route start and the route end in free space, and the target waypoint is generated to ensure that the time and space complexity of each path search is not too high and the target waypoint is not in an obstacle; in the second layer, trajectory optimization is used to optimize the geometry of the guide path, which can reduce the computing resources required to generate the target path; in the third layer, the optimized path is generated by using B-splines.

[0068] The technical solution of the embodiment of the present invention is to determine the target waypoint by using the path-finding algorithm in the first-level path planning, and then generate the target path based on the target waypoint, the route starting point and the route end point based on the hard constraint method in the second-level path planning. In the third-level path planning, the local path planning algorithm is used to determine the control points based on the target path, and the target path is optimized according to the control points to obtain the optimized path. By executing this technical solution, through end-to-end learning combined with visual depth perception technology, all-round obstacle perception and obstacle avoidance capabilities from close range to long range are achieved. The path planning strategy can be dynamically adjusted according to the scale and complexity of the obstacle to ensure the safe and efficient operation of the drone in a complex environment.

[0069] Embodiment 2

[0070] Figure 2 This is a schematic diagram of a multi-level motion planning process for an aircraft provided in the second embodiment of the present invention. The relationship between this embodiment and the above embodiment is a detailed description of the target path optimization process. Figure 2 As shown, the method includes:

[0071] S210. In the first-level path planning, a path-finding algorithm is used to determine a target waypoint; wherein the target waypoint is composed of each waypoint between a route start point and a route end point.

[0072] S220. In the second-level path planning, a target path is generated according to the target waypoint, the route starting point and the route ending point based on a hard constraint method.

[0073] S230. In the third-layer path planning, a local path planning algorithm is used to determine control points based on the target path; wherein the control points are used to change the curve shape of the path.

[0074] S240: construct an objective function based on the control points.

[0075] Among them, the objective function is a function in the optimization problem, which is used to describe the goal of the optimization problem. The objective function can be constructed based on various control points.

[0076] Optionally, constructing an objective function based on the control points includes steps D1-D2:

[0077] Step D1, based on the control point, construct a first loss term, a second loss term, a third loss term and a fourth loss term; wherein the first loss term is used to characterize the smoothness penalty of the path; the second loss term is used to characterize the path collision penalty; the third loss term is used to characterize the path dynamic feasibility penalty; the fourth loss term is used to characterize the path safety distance penalty;

[0078] Step D2: construct an objective function based on the first loss term, the second loss term, the third loss term and the fourth loss term.

[0079] Specifically, the B-spline trajectory generation algorithm can be used to construct the objective function based on the control points. , Control Points and the node vector The only certainty is that , , For efficient path planning, uniform B-splines are used, which means that each node is separated from its previous node by the same time interval. . B-spline has the convex hull property. This property indicates that a single interval of a B-spline curve is only affected by its continuous control points, and the curve lies in the convex hull formed by these points. For example, in the interval A curve in Another property of B-splines is that The derivative is still of order , The velocity curve , acceleration curve and acceleration curve The control points of are calculated as follows:

[0080] ;

[0081] ;

[0082] .

[0083] In this scheme, the first loss term is the smoothness term, the second loss term is the collision term, the third loss term is the dynamic feasibility term, and the fourth loss term is the safety distance term. The smoothness term, collision term, dynamic feasibility term and safety distance term can be weightedly combined to construct the objective function.

[0084] Specifically, the objective function is: ;in, is a smooth term, is the collision term, It is a power feasible item. is the safety distance term. are the weights of each penalty term respectively.

[0085] Furthermore, the purpose of the smoothness term is to minimize the acceleration and jerk of the control point to make the entire trajectory smoother. The calculation formula is as follows: ;

[0086] In this embodiment, the collision term is calculated by comparing the distance between the control point and the obstacle. Set a safe distance , and penalize the distance between the control point and the obstacle less than The specific formula is as follows:

[0087] ;

[0088] ;

[0089] in, .

[0090] In this scheme, the calculation formula of the power feasibility item is: ; Its purpose is to ensure the feasibility of the trajectory by limiting the value of the high-order derivative of the control point in each single dimension. This penalty makes the optimization process tend to select control points whose speed, acceleration and jerk are within a reasonable range, thereby ensuring the smoothness and feasibility of the trajectory. Among them, , , is the weight.

[0091] Specific functions is defined as follows: ,in, is defined as follows:

[0092] ;

[0093] in, , , , , , , is the weight, is the derivative limit, is the splitting point between the quadratic interval and the cubic interval, is the elastic coefficient.

[0094] Furthermore, the safety distance term is used to keep a certain distance between the drone and the obstacle, rather than just having a collision penalty in the part where the B-spline passes through the obstacle. The reason for this is that there is a certain uncertainty in the point cloud based on visual perception, and there may be close obstacles when the drone approaches. If the planned trajectory is close to the obstacle, it will be affected by the perception error and collide with it. Therefore, the generated trajectory should always try to keep a distance from the obstacle.

[0095] The safety distance term is obtained by giving a safety distance , the safety distance loss is defined as The number of points found in: ,in, This is the first Points, is the total number of points searched, express arrive The Euclidean distance between . is an indicator function. It takes the value 1 if the condition in the brackets is true, otherwise it takes the value 0.

[0096] By constructing the objective function, the optimized path can be determined based on the objective function, thereby ensuring the safe and efficient operation of the UAV in a complex environment.

[0097] S250: Optimize the target path according to the objective function to obtain an optimized path.

[0098] In this solution, an optimization algorithm can be used to optimize the objective function to determine the optimized path. The optimization algorithm may include a gradient descent method, an exponential weighted average algorithm, a momentum gradient descent algorithm, and the like.

[0099] Optionally, optimizing the target path according to the objective function to obtain an optimized path includes steps E1-E2:

[0100] Step E1, optimizing the objective function using the gradient to determine the optimal control point;

[0101] Step E2: Optimize the target path according to the optimal control point to obtain an optimized path.

[0102] In this solution, the objective function can be optimized using the gradient descent method to obtain the optimized path. The gradient descent method is used to solve the minimum or maximum value of a function. It continuously updates the value of the parameter through iteration so that the value of the objective function gradually approaches the optimal solution.

[0103] In this embodiment, the partial derivatives of each variable may be calculated to calculate the gradients of the smoothing term, the collision term, and the dynamic feasible term.

[0104] Specifically, ,in, belong .

[0105] Furthermore, the gradient of the safety distance term is calculated based on the repulsive force between the searched point and the control point. The repulsive force is calculated as follows: in, is a constant used to adjust the repulsion strength, here it is set to -7. is the distance between the control point and the obstacle point.

[0106] The final calculated gradient is: ;

[0107] in, , is the repulsive force direction vector.

[0108] By determining the optimized path, it is possible to ensure that the drone can operate safely and efficiently in complex environments.

[0109] In this scheme, a benchmark is designed to verify the ability of the proposed algorithm to bypass large-scale obstacles in real time. Compared with the ego planner, the perception range is consistent, and the parameters of the ego planner remain the values ​​set in the original algorithm. The speed limit is set to 3m / s, and the same reference trajectory is generated. A 20m×10m rectangular map is used in the test, and each experiment is performed 10 times. The test scenarios include large-scale obstacle avoidance scenarios, small-scale obstacle avoidance scenarios, and multi-scale obstacle avoidance scenarios. The proposed algorithm can start to bypass obstacles as early as possible, while the ego planner cannot bypass obstacles. The benchmark test shows that the proposed algorithm has better environmental adaptability and can bypass large-scale obstacles while having the ability to bypass obstacles in complex environments. At the same time, the CPU (Central Processing Unit) consumption in planning is also compared. The CPU usage of the proposed algorithm during the bypass period is only half of that of the local planner.

[0110] In this embodiment, Figure 3 is a schematic diagram of a multi-level motion planning architecture for aircraft with multi-sized obstacles provided in the second embodiment of the present application, such as Figure 3 As shown, the initial route planning is performed based on the route starting point and the route end point, and the target waypoint is generated to ensure that the time and space complexity of each path search is not too high, and to ensure that the target waypoint is not in the obstacle. After the target waypoint is generated, the target waypoint is readjusted using the timed replanning mechanism, and then the target path is generated based on the target waypoint, and the target path is optimized to obtain the optimized path, thereby controlling the flight of the drone. By providing a multi-level architecture, multi-level path planning and trajectory planning can be effectively performed, and obstacles of different sizes in a large range can be bypassed. The safety distance is integrated into the trajectory planning module to further improve the algorithm's obstacle avoidance ability.

[0111] The technical solution of the embodiment of the present invention is to determine the target waypoint by using the path-finding algorithm in the first layer of path planning, and then generate the target path based on the target waypoint, the route starting point and the route end point based on the hard constraint method in the second layer of path planning. In the third layer of path planning, the local path planning algorithm is used to determine the control points based on the target path, and the objective function is constructed based on the control points. The target path is optimized according to the objective function to obtain the optimized path. By executing this technical solution, through end-to-end learning combined with visual depth perception technology, all-round obstacle perception and obstacle avoidance capabilities from close range to long range are achieved. The path planning strategy can be dynamically adjusted according to the scale and complexity of the obstacle to ensure the safe and efficient operation of the drone in a complex environment.

[0112] Embodiment 3

[0113] Figure 4 This is a schematic diagram of the structure of a multi-level motion planning device for an aircraft provided in Embodiment 3 of the present invention. Figure 4 As shown, the device comprises:

[0114] The target waypoint determination module 410 is used to determine the target waypoint by using a pathfinding algorithm in the first-level path planning; wherein the target waypoint is composed of each waypoint between the route starting point and the route end point;

[0115] A target path generation module 420, for generating a target path according to the target waypoint, the route start point and the route end point based on a hard constraint method in the second-level path planning;

[0116] The optimized path obtaining module 430 is used to determine the control points based on the target path using a local path planning algorithm in the third-level path planning, and optimize the target path according to the control points to obtain the optimized path; wherein the control points are used to change the curve shape of the path.

[0117] Optionally, the optimized path obtaining module 430 includes:

[0118] An objective function construction unit, used for constructing an objective function according to the control points;

[0119] The optimized path obtaining unit is used to optimize the target path according to the objective function to obtain the optimized path.

[0120] Optional, objective function building unit, specifically used for:

[0121] Based on the control point, a first loss term, a second loss term, a third loss term and a fourth loss term are constructed; wherein the first loss term is used to characterize the smoothness penalty of the path; the second loss term is used to characterize the path collision penalty; the third loss term is used to characterize the path dynamic feasibility penalty; and the fourth loss term is used to characterize the path safety distance penalty;

[0122] An objective function is constructed according to the first loss term, the second loss term, the third loss term and the fourth loss term.

[0123] Optionally, the optimized path obtains a unit, which is specifically used for:

[0124] Optimizing the objective function using the gradient to determine the optimal control point;

[0125] The target path is optimized according to the optimal control point to obtain an optimized path.

[0126] Optionally, the target waypoint determination module 410 is specifically configured to:

[0127] Perform path planning based on the predetermined route starting point and route end point to obtain the target route;

[0128] Divide the target route into sections to obtain various waypoints;

[0129] According to the position of each waypoint and the preset adjustment step, each waypoint is adjusted to obtain the target waypoint.

[0130] Optionally, the device further comprises:

[0131] A distance determination module, used to determine a first distance and a second distance according to a preset time condition; wherein the first distance is the distance between the position of the drone and the starting point of the route; and the second distance is the distance between the starting point of the route and the end point of the route;

[0132] The target waypoint adjustment module is used to adjust the target waypoint when the ratio of the first distance to the second distance is greater than a preset threshold.

[0133] Optionally, the target path generation module 420 is specifically configured to:

[0134] Determine a path constraint condition; wherein the path constraint condition is used to constrain the path to avoid falling into a local minimum;

[0135] A target path is generated according to the path constraints, the target waypoint, the route starting point and the route end point.

[0136] An aircraft multi-level motion planning device provided in an embodiment of the present invention can execute an aircraft multi-level motion planning method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0137] Embodiment 4

[0138] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0139] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0140] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0141] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a multi-level motion planning method for an aircraft.

[0142] In some embodiments, a method for multi-level motion planning of an aircraft may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for multi-level motion planning of an aircraft described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute a method for multi-level motion planning of an aircraft in any other appropriate manner (e.g., by means of firmware).

[0143] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0144] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0145] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0146] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or path ball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0147] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0148] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0149] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0150] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A multi-level motion planning method for an aircraft, characterized in that: include: In the first level of path planning, a pathfinding algorithm is used to determine a target waypoint; wherein the target waypoint is composed of each waypoint between the route start point and the route end point; In the second-level path planning, a target path is generated according to the target waypoint, the route starting point and the route end point based on a hard constraint method; In the third-level path planning, a local path planning algorithm is used to determine control points based on the target path, and the target path is optimized according to the control points to obtain an optimized path; wherein the control points are used to change the curve shape of the path; In the first level of path planning, the pathfinding algorithm is used to determine the target waypoint, including: Perform path planning based on the predetermined route starting point and route end point to obtain the target route; Divide the target route into sections to obtain various waypoints; According to the position of each waypoint and the preset adjustment step, each waypoint is adjusted to obtain the target waypoint.

2. The method according to claim 1, characterized in that Optimizing the target path according to the control points to obtain an optimized path includes: According to the control points, construct an objective function; The target path is optimized according to the objective function to obtain an optimized path.

3. The method according to claim 2, characterized in that According to the control points, an objective function is constructed, including: Based on the control point, a first loss term, a second loss term, a third loss term and a fourth loss term are constructed; wherein the first loss term is used to characterize the smoothness penalty of the path; the second loss term is used to characterize the path collision penalty; the third loss term is used to characterize the path dynamic feasibility penalty; and the fourth loss term is used to characterize the path safety distance penalty; An objective function is constructed according to the first loss term, the second loss term, the third loss term and the fourth loss term.

4. The method according to claim 2, characterized in that: Optimizing the target path according to the objective function to obtain an optimized path includes: Optimizing the objective function using the gradient to determine the optimal control point; The target path is optimized according to the optimal control point to obtain an optimized path.

5. The method according to claim 1, characterized in that After obtaining the target waypoint, the method further includes: Determine a first distance and a second distance according to a preset time condition; wherein the first distance is the distance between the position of the drone and the starting point of the route; and the second distance is the distance between the starting point of the route and the end point of the route; When the ratio of the first distance to the second distance is greater than a preset threshold, the target waypoint is adjusted.

6. The method according to claim 1, characterized in that In the second-level path planning, a target path is generated according to the target waypoint, the route starting point and the route end point based on a hard constraint method, including: Determine a path constraint condition; wherein the path constraint condition is used to constrain the path to avoid falling into a local minimum; A target path is generated according to the path constraints, the target waypoint, the route starting point and the route end point.

7. A multi-level motion planning device for an aircraft, characterized in that: include: A target waypoint determination module is used to determine the target waypoint by using a pathfinding algorithm in the first-level path planning; wherein the target waypoint is composed of each waypoint between the route starting point and the route end point; A target path generation module, used for generating a target path according to the target waypoint, the route starting point and the route end point based on a hard constraint method in the second-level path planning; The optimized path obtaining module is used to determine the control points based on the target path using the local path planning algorithm in the third layer path planning, and optimize the target path according to the control points to obtain the optimized path; wherein the control points are used to change the curve shape of the path; The target waypoint determination module is specifically used for: Perform path planning based on the predetermined route starting point and route end point to obtain the target route; Divide the target route into sections to obtain various waypoints; According to the position of each waypoint and the preset adjustment step, each waypoint is adjusted to obtain the target waypoint.

8. An electronic device, characterized in that: The electronic device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a multi-level motion planning method for an aircraft according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a multi-level motion planning method for an aircraft according to any one of claims 1 to 6 when executed.

Images