Unmanned aerial vehicle heuristic path planning method and device based on large language model and medium

Abstract

The invention belongs to the technical field of unmanned aerial vehicle path planning, and discloses an unmanned aerial vehicle heuristic path planning method and device based on a large language model, and a medium. The method comprises the following steps: modeling an unmanned aerial vehicle, and planning and modeling a flight path based on a flight task; a data set including flight problem examples and solutions is collected as input parameters of the large language model, and the large language model is trained and then is used for performing path planning on a flight task. According to the unmanned aerial vehicle heuristic path planning method based on the large language model, the accurate path searching capability of a traditional path planning algorithm is combined with the global reasoning capability of the large language model. The objective of the invention is to improve the efficiency of path searching in a large-scale scene, especially in terms of time and space complexity, while maintaining the effectiveness of a path. By integrating the advantages of the two methods, the limitation of the traditional algorithm in the aspects of calculation and memory is solved, and the effectiveness required by path searching is not influenced.

Description

Technical Field

[0001] The present invention belongs to the technical field of UAV path planning. Specifically, it relates to a heuristic path planning method, device, and medium for UAVs based on large language models. Background Art

[0002] As the core of UAV technology, the development of trajectory planning has received extensive attention globally. Early trajectory planning mainly relied on manual settings by technicians, and its accuracy was closely related to the professional level and experience of technicians. However, with the progress of informatization and intelligence, the manually drawn trajectory lines can no longer meet the requirements of the modern battlefield environment. The development of high-tech has brought about the continuous emergence of various reconnaissance means, greatly enhancing the ability to collect environmental information, thus providing strong support for planning high-precision trajectory flight routes.

[0003] During the trajectory planning process, it is necessary to consider the self-condition constraints closely related to the UAV and the constraints related to the mission. More importantly, it is necessary to consider the flight performance constraints, such as different turning radii and different speeds due to different aircraft models. How to quantify these constraint conditions and threat factors, transform them into symbols that the planning system can recognize, and comprehensively consider them is of great significance for the development of trajectory planning technology. Path planning is a basic scientific problem in UAVs and autonomous navigation, which requires a path from the starting point to the ending point to be both efficient and avoid obstacles. Traditional algorithms, such as A* and its variants, although they can ensure the effectiveness of the path, their computational and memory efficiency decreases significantly when the state space increases. In contrast, large large language models can provide a global insight into the environment through a broader environmental analysis based on context understanding. However, they are insufficient in detailed spatial and temporal reasoning, which may lead to invalid paths. Summary of the Invention

[0004] In view of this, the present invention provides a heuristic path planning method, device, and medium for UAVs based on large language models to solve the above problems.

[0005] To solve the above technical problems, the present invention provides a heuristic path planning method for UAVs based on large language models, including: Model the UAV, and obtain key flight features and flight objective functions based on the flight mission; Collect a dataset including flight problem instances and solutions as input parameters for the large language model, train the large language model, and then use it for path planning of the flight mission; Among them, the path planning includes: Construct the basic structure and data for path planning, calibrate the starting node, and then use the large language model to generate a target list and calculate the priority of the nodes; Update the node ratio in sequence based on the priority of the nodes and complete the path planning; and reconstruct and dynamically update the planned path in real time based on the dynamic evaluation of the environmental changes made by the large language model.

[0006] As an alternative, the flight path planning and modeling based on the flight mission includes: Based on the flight mission, obtain the key flight features in the flight mission; perform joint optimization on each key flight feature based on the constraint conditions to generate a flight objective function; the constraint conditions include safety constraint conditions and concealment constraint conditions.

[0007] As an alternative, the key flight features include distance features, average speed features, probability of being monitored by radar, probability of being hit, and probability of fuel consumption.

[0008] As an alternative, the modeling of the unmanned aerial vehicle includes: Based on the physical properties of the target aircraft, construct the dynamic modeling, kinematic modeling, and aerodynamic modeling of the target aircraft; The components of the dynamic modeling of the target aircraft include the position of the target aircraft in the inertial coordinate system, the velocity components, angular velocity components, and force components in the body coordinate system, and the mass of the target aircraft; The components of the kinematic modeling of the target aircraft include roll angle, pitch angle, yaw angle, the principal axis moment of inertia and product moment of inertia of the target aircraft in the inertia matrix, and the moment components of the target aircraft in the body coordinate system; The components of the aerodynamic modeling of the target aircraft include lift, drag, side force, air density, flight speed, projected area of the wing, angle of attack, and sideslip angle.

[0009] As an alternative, the flight problem instance includes the starting point, ending point, environmental map, and environmental dynamic factors of the flight mission; the environmental dynamic factors are associated with the environmental map.

[0010] As an alternative, the training of the large language model includes: Initialize the flight mission planning conditions, and input the starting point, ending point, heuristic function, neighbor function, environmental map, and environmental dynamic factors; Call the large language model to generate a target list, predict environmental changes and / or environmental dynamic factors based on the flight problem instance; and perform incremental updates according to the evaluation results to reconstruct the planned path.

[0011] As an alternative, the path planning further includes: Initialize the path record, add the target node to the list to be processed, and initialize the best cost and estimated cost of the target node to zero, and set the costs of all other nodes to infinity; Calculate the optimal cost and estimated cost of each node in the list to be processed, establish the priority of each node for forming the planned path, and form the planned path; Input the starting point, target node, and environmental information into the large language model to generate a target list; Calculate the priority for each node, and the priority is used for sorting and path selection in path planning; When the list to be processed is not empty or the priority of the starting point is less than the priority of any node in the list, select the node with the lowest priority from the list to plan the starting point. After calculating the priority for each node in turn, call the large language model to predict new obstacles or other dynamic changes according to the environmental changes, and update the priority and adjacent relationship of the relevant nodes; Recalculate the priority of the relevant nodes, add them to the list to be processed and then recalculate again, reconstruct the priority order of each node, and update the path.

[0012] As an optional method, calculating the priority includes, for each node, calculating its priority based on the optimal cost, estimated cost, and heuristic function; where When calculating the priority for each node in turn: If the optimal cost of the node is greater than its estimated cost, update its optimal cost to the estimated cost, remove it from the list to be processed, update the estimated cost of all its neighbor nodes, and add the neighbor nodes not in the list to the list to be processed; If the optimal cost of the node is not greater than its estimated cost, reset its optimal cost to infinity, update the estimated cost of itself and all its neighbor nodes at the same time, and add the neighbor nodes not in the list to the list to be processed.

[0013] On the other hand, the present invention also provides an electronic device, including: a memory for storing a computer program; a processor for implementing the steps of the above-mentioned heuristic path planning method for drones based on a large language model when executing the computer program.

[0014] On the other hand, the present invention also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the above-mentioned heuristic path planning method for drones based on a large language model.

[0015] The beneficial effects of the present invention are: The heuristic path planning method for drones based on large language models provided by the present invention combines the precise path finding ability of traditional path planning algorithms with the global reasoning ability of large large language models. This hybrid method aims to improve the efficiency of path finding, especially in terms of time and space complexity, while maintaining the validity of the path, especially in large-scale scenarios. By integrating the advantages of the two methods, the path planning algorithm integrating large language models solves the limitations of traditional algorithms in terms of computing and memory without affecting the validity required for path finding. Brief Description of the Drawings

[0016] Figure 1 It is a schematic flow chart of the heuristic path planning method for drones based on large language models provided by an embodiment of the present invention; Figure 2 It is a schematic flow chart of the flight path modeling provided by an embodiment of the present invention; Figure 3 It is a schematic flow chart of the path planning algorithm provided by an embodiment of the present invention; Figure 4 It is a visualization diagram of the simulation result in a certain case provided by an embodiment of the present invention. Detailed Embodiments

[0017] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below in conjunction with specific embodiments.

[0018] Modern trajectory planning technology needs to comprehensively consider the constraints of the UAV itself (such as flight performance, fuel limitations, etc.) and mission-related constraints (such as mission time, mission priority, etc.). These external factors need to be effectively quantified and transformed into symbols that the planning system can recognize for comprehensive consideration and processing. Traditional path planning algorithms, such as heuristic algorithms and their variants (such as the A* algorithm), have been widely used in the field of path planning. These algorithms usually use heuristic search methods, combined with cost functions and heuristic functions, to find the optimal path from the starting point to the ending point. The D* algorithm is a classic heuristic search algorithm that guides the search process by evaluating the path cost (usually including the actual cost from the starting point to the current node and the estimated cost from the current node to the ending point). The D* algorithm can find the path with the lowest cost in a static environment, but in a dynamic environment, environmental changes will cause the need to recalculate the entire path. The D* algorithm is an extension of the A* algorithm, designed specifically for dynamic environments. It uses an incremental update mechanism to only update the affected part of the path when the environment changes, rather than recalculating the entire path. This enables the path planning algorithm integrated with large language models to perform excellently in dynamic environments, but its implementation complexity is relatively high. Large language models have powerful context understanding and reasoning capabilities, and can conduct global analysis and insight into complex environments. Although large language models have deficiencies in detailed spatial and temporal reasoning, they can provide a global perspective of the environment, identify potential threats and obstacles. Large language models can process a large amount of environmental data, identify and classify different types of threat factors, and provide corresponding avoidance suggestions. Through the global understanding of the environment, large language models can identify the best trajectory planning strategy to help UAVs effectively avoid obstacles in complex environments.

[0019] Therefore, the present invention proposes a heuristic path planning method for UAVs based on large language models. This method is based on the integration of large language models, combining the accurate path finding ability of traditional path planning algorithms with the global reasoning ability of large language models. This hybrid method aims to improve the efficiency of path finding, especially in terms of time and space complexity, while maintaining the effectiveness of the path, especially in large-scale scenarios. By integrating the advantages of the two methods, an improved heuristic search UAV path planning method based on large language models solves the limitations of traditional algorithms in terms of calculation and memory without affecting the effectiveness required for path finding.

[0020] Please refer to Figures 1 - 3 , as an optional method, this embodiment selects a certain type of fixed-wing UAV to illustrate the implementation process: Model a fixed-wing unmanned aerial vehicle (UAV), plan and model the flight path based on the flight mission; collect a dataset including flight problem instances and solutions as input parameters for a large language model, train the large language model and use it for path planning of the flight mission; where the path planning includes: Construct the basic structure and data for path planning, calibrate the starting node, and then use the large language model to generate a target list to be processed and calculate the priority of the nodes; based on the priority of the nodes, update the node ratio in sequence and complete the path planning; and dynamically reconstruct and update the path planning in real time based on the dynamic evaluation made by the large language model on environmental changes.

[0021] Specifically, in this embodiment, first, conduct flight path planning modeling, convert the description of the above flight path planning into an optimization objective formula, and regard it as a multi-objective optimization problem. This problem requires optimizing multiple objective functions while satisfying various constraint conditions. Then, based on the fixed-wing UAV modeling, construct a simulation environment. Then, by providing a small number of examples to the large large language model, the model can learn patterns and rules from these examples, thereby improving its accuracy and efficiency in new tasks. This method is particularly suitable for scenarios with scarce data. Finally, according to the analysis of the global information by the large large language model, guide the heuristic algorithm to expand the strategy of the nodes to improve efficiency. It includes: Model the flight mission. The primary step is to obtain the key flight characteristics in the flight mission based on the dynamic equations and aerodynamic equations of the aircraft, establish the constraint conditions of physical properties and the design requirements of flight performance. Define a series of functions to accurately describe these constraints and requirements to ensure that the model can truly reflect the flight characteristics and operation limitations of the aircraft.

[0022] Furthermore, when designing the algorithm, adopt the D* algorithm to adapt to environmental changes by dynamically updating the path cost and estimated cost. At the same time, the path planning algorithm integrating the large language model combines global insight and local search mechanisms, and uses few-shot fine-tuning and recursive path evaluation techniques to improve the efficiency and optimality of path planning. This integrated method can better handle dynamic changes in complex environments.

[0023] Finally, after determining the starting point and ending point of the planning problem, first input the obstacle information into the algorithm. Subsequently, generate the planned path from the starting point to the ending point according to the steps specified in the pseudocode.

[0024] In the above steps, establish the overall objective function f(x) and construct the distance function , assuming the total distance is the sum of the Euclidean distances between adjacent points on the path

[0025] where iis an index variable that ranges from 0 to n-1 , where n is the number of points. Therefore,[[]] , , and represent the coordinates of the i -th point, while , , and represent the coordinates of the i+1 -th point. This formula calculates the sum of the distances between each point.[[]]

[0026]

[0027] Among them, T(x) represents the average time spent, V is the average speed of the UAV:[[]] After that, construct the constraint function C(x):[[]]

[0028] where RadarRisk() and MissileRisk() represent the probabilities of being detected by the radar and being hit, and are the weight coefficients used to adjust the impacts of different risks.[[]]

[0029] Construct the fuel consumption constraint function :[[]]

[0030] In the formula, FuelRate represents the fuel consumption from xi to xi+1, which depends on the speed and altitude of the aircraft, is the time interval from to , calculated as

[0031] After that, perform aircraft modeling. First, construct the aircraft dynamics equation, the formula of which is as follows:[[]]

[0032] x, y, z are the positions of the UAV in the inertial coordinate system. u, v, w are the velocity components in the body coordinate system. p, q, r are the angular velocity components in the body coordinate system. m is the mass of the UAV. X, Y, Z are the force components in the body coordinate system.[[]]

[0033] Construct the kinematic equation, the formula of which is as follows:[[]]

[0034] , , are the roll, pitch, and yaw angles, are the principal moments of inertia of the inertia matrix, are the products of inertia of the inertia matrix, and L, M, N are the moment components in the body coordinate system.

[0035] Construct the aircraft aerodynamic equations, the formulas of which are as follows:

[0036] In the formula, L is the lift force, that is, the force perpendicular to the flight direction, which helps the aircraft overcome gravity. D is the drag force, that is, the force opposite to the flight direction, which hinders the aircraft's forward movement. Y is the side force, that is, the force parallel to the side of the aircraft, which affects the lateral stability of the aircraft. ρ is the air density, and the unit is usually kilograms per cubic meter (kg / m³). V is the flight speed, and the unit is usually meters per second (m / s). S is the reference area, usually the projected area of the wing, and the unit is usually square meters (m²). is the lift coefficient, is the drag coefficient, is the side force coefficient, and these coefficients depend on the angle of attack and the sideslip angle.

[0037] After completion of the construction, training the large language model includes: initializing the flight mission planning conditions, inputting the starting point, ending point, heuristic function, neighbor function, environment map, and environmental dynamic factors; calling the large language model to generate a target list, predicting environmental changes and / or environmental dynamic factors based on the flight problem instance; and performing incremental updates according to the evaluation results and reconstructing the planned path.

[0038] At this time, all the preliminary work for path planning is completed, and it is ready to start the UAV path planning. In this embodiment, the process of path planning is as follows: Initialize the path record, add the target node to the list of nodes to be processed, and initialize the best cost and estimated cost of the target node to zero, and set the costs of all other nodes to infinity; Calculate the best cost and estimated cost of each node in the list of nodes to be processed, establish the priority of each node for forming the planned path, and form the planned path; Input the starting point, target node, and environmental information to the large language model to generate a target list; Calculate the priority for each node, and the priority is used for sorting and path selection in path planning; When the list to be processed is not empty or the priority of the starting point is less than the priority of any node in the list, select the node with the lowest priority in the list to plan the starting point. After calculating the priority of each node in turn, call the large language model to predict new obstacles or other dynamic changes according to the environmental changes and update the priorities and adjacent relationships of the relevant nodes; Recalculate the priorities of the relevant nodes, add them to the list to be processed, and then recalculate again. Reconstruct the priority order of each node and update the path.

[0039] Among them, calculating the priority includes calculating the priority of each node based on the best cost, estimated cost, and heuristic function; among them, When calculating the priority of each node in turn: If the best cost of the node is greater than its estimated cost, update its best cost to the estimated cost, remove it from the list to be processed, update the estimated costs of all its neighbor nodes, and add the neighbor nodes not in the list to the list to be processed; If the best cost of the node is not greater than its estimated cost, reset its best cost to infinity, update the estimated costs of itself and all its neighbor nodes at the same time, and add the neighbor nodes not in the list to the list to be processed.

[0040] In the above steps, the target list is generated by the large language model. It generates a possible target list to be processed based on environmental information (such as obstacles, starting point, target location, etc.). These target nodes may be some key intermediate states, or special nodes that the algorithm needs to pay attention to during the path planning process. Its role is to provide a high-level target guidance for path planning, so that the method provided in this embodiment can better cope with the changes in the dynamic environment. The target nodes in this list represent important reference points in path planning, but they are not the operation targets when the algorithm directly performs path search.

[0041] The list to be processed stores the nodes that need to be processed during the current path search process. During the path planning process of this embodiment, the nodes in the list to be processed will be continuously sorted and selected according to their costs (i.e., priorities). The nodes in this list are the actual operation objects during the search process. When a node is processed, its priority will be calculated, and path updates (such as cost updates, re-evaluation of neighbor nodes, etc.) will depend on these nodes.

[0042] Based on this, the target list and the list to be processed exist independently, and the nodes in the target list do not directly participate in the priority calculation. The main role of the target list is to provide a high-level goal for path planning, while the list to be processed contains the nodes that the algorithm actually needs to process during the specific search process. When calculating the priority of a node, it is the nodes in the list to be processed that are involved, rather than the nodes in the target list. Each node in the list to be processed calculates its priority based on its current cost and heuristic estimate value to determine its priority.

[0043] In addition, as the drone moves in the environment, the environment may change, such as the appearance or disappearance of obstacles, or a change in the radar range. To cope with these changes, this embodiment performs dynamic evaluation through a large language model. This includes: invoking the large language model to predict changes in the position of obstacles or targets based on the current environmental state. According to the prediction of the model, update the obstacle information or target position in the environment. Update the cost function and adjacency relationship of the affected nodes. Add the affected nodes back to the list to be processed and recalculate their costs. Therefore, once a valid path is found, it is checked whether the estimated cost of the starting point is equal to the optimal cost. If they are equal, it means that the optimal path has been found. Then, backtracking calculation is performed to reconstruct the optimal path from the starting point to the target. Among them, Figure 4 This is a demonstration of a simulation visualization interface based on the solution of this embodiment.

[0044] Based on the above solution, this embodiment combines the D* algorithm with a large language model, and uses the prediction ability of the large language model to anticipate environmental changes, thereby optimizing the path planning of the drone. The D* algorithm itself is suitable for path planning in a dynamic environment and can quickly adjust the path, while the large language model provides predictions of environmental changes (such as obstacles, dynamic objects, etc.), enhancing the robustness and intelligence of the algorithm in complex scenarios. This method is suitable for tasks where the drone flies in an unknown or constantly changing environment.

[0045] On the other hand, this embodiment also provides an electronic device, including: a memory for storing a computer program; a processor for implementing the steps of the above-mentioned drone heuristic path planning method based on a large language model when executing the computer program.

[0046] On the other hand, this embodiment also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the above-mentioned drone heuristic path planning method based on a large language model.

[0047] The above are only the preferred embodiments of the present invention. It should be noted that the above preferred embodiments should not be construed as limiting the present invention, and the protection scope of the present invention should be subject to the scope defined by the claims. For those of ordinary skill in the art, without departing from the spirit and scope of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as within the protection scope of the present invention.

Claims

1. A heuristic path planning method for unmanned aerial vehicles based on a large language model, characterized in that: include: Model the UAV and obtain key flight characteristics and flight objective functions based on the flight mission; Collecting a data set including flight problem instances and solutions as input parameters of a large language model, training the large language model and using it to plan flight mission paths; Wherein, the path planning includes: Build the basic structure and data for path planning, identify the starting node, use the large language model to generate the target list and calculate the node priority; Based on the priorities of the nodes, the node ratios are updated in sequence and the path planning is completed; and based on the dynamic evaluation of environmental changes made by the large language model, the planned path is reconstructed and dynamically updated in real time.

2. The method for heuristic path planning of unmanned aerial vehicles based on a large language model according to claim 1 is characterized in that: The key flight characteristics include distance characteristics, average speed characteristics, probability of being detected by radar, probability of being hit and probability of fuel consumption.

3. The method for heuristic path planning of unmanned aerial vehicles based on a large language model according to claim 1 is characterized in that: Obtaining the flight objective function includes: Based on constraint conditions, each of the key flight characteristics is jointly optimized to generate a flight objective function; the constraint conditions include safety constraint conditions and hidden constraint conditions.

4. The method for heuristic path planning of unmanned aerial vehicles based on a large language model according to claim 1 is characterized in that: The modeling of the drone includes: Based on the physical properties of the target aircraft, construct the dynamics modeling, kinematics modeling and aerodynamic modeling of the target aircraft; The dynamic modeling components of the target aircraft include the position of the target aircraft in the inertial coordinate system, the velocity component, angular velocity component and force component in the body coordinate system and the mass of the target aircraft; The kinematic modeling components of the target aircraft include roll angle, pitch angle, yaw angle, principal axis inertia moment of the target aircraft in the inertia matrix, product inertia moment and moment component of the target aircraft in the body coordinate system; The aerodynamic modeling components of the target aircraft include lift, drag, lateral force, air density, flight speed, wing projection area, angle of attack and sideslip angle.

5. The method for heuristic path planning of unmanned aerial vehicles based on a large language model according to claim 1 is characterized in that: The flight problem instance includes a starting point, an end point, an environmental map and environmental dynamic factors of a flight mission; the environmental dynamic factors are associated with the environmental map.

6. The method for heuristic path planning of unmanned aerial vehicles based on a large language model according to claim 5 is characterized in that: The training of the large language model includes: Initialize the flight mission planning conditions, input the starting point, end point, heuristic function, neighbor function, environment map and environment dynamic factors; The large language model is called to generate a target list, and based on the flight problem instance, environmental changes and / or environmental dynamic factors are predicted; and incremental updates are performed according to the evaluation results to reconstruct the planned path.

7. The method for heuristic path planning of unmanned aerial vehicles based on a large language model according to claim 6 is characterized in that: The path planning also includes: Initialize the path record, add the target node to the pending list, and initialize the best cost and estimated cost of the target node to zero, and the costs of all other nodes to infinity; Calculating the best cost and estimated cost of each node in the pending list, establishing the priority of each node for forming a planned path and forming a path plan; Inputting a starting point, a target node and environmental information into the large language model to generate a target list; Calculating the priority of each node in the target list, wherein the priority is used for sorting and path selection in path planning; When the pending list is not empty or the priority of the starting point is lower than the priority of any node in the list, the node with the lowest priority is selected from the pending list to plan the starting point. After calculating the priority of each node in turn, the large language model is called to predict new obstacles or other dynamic changes based on environmental changes and update the priority and adjacent relationship of related nodes. The priorities of the related nodes are recalculated, and they are added to the pending list and recalculated again, the priority order of each node is reconstructed and the path is updated.

8. The method for heuristic path planning of unmanned aerial vehicles based on a large language model according to claim 7 is characterized in that: The calculating the priority of each node in the target list includes calculating the priority of each node based on the best cost, the estimated cost and the heuristic function; wherein, When calculating the priority of each node in turn: If the best cost of the node is greater than its estimated cost, update its best cost to the estimated cost and remove it from the pending list. Update the estimated costs of all its neighboring nodes and add the neighboring nodes that are not in the list to the pending list. If the best cost of the node is not greater than its estimated cost, reset its best cost to infinity, update the estimated costs of itself and all its neighbor nodes, and add neighbor nodes that are not in the list to the pending list.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the heuristic path planning method for unmanned aerial vehicles based on a large language model as described in any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the large language model-based unmanned aerial vehicle heuristic path planning method as described in any one of claims 1 to 8.

Images