An unmanned aerial vehicle path planning method based on global optimization method

Abstract

The application provides a UAV path planning method based on a global optimization method, comprising the following steps: S1, establishing a three-dimensional space environment model of a construction site, and setting coordinates of a starting point and a target point of a UAV; S2, constructing a multi-dimensional physical constraint model and a path cost function; S3, obtaining an optimal global path of the UAV in a known obstacle environment by a global optimization method in combination with the three-dimensional space environment model of the construction site and the path cost function; S4, when the UAV encounters an unknown dynamic obstacle in the flight process, triggering local path re-planning in combination with an RRT* algorithm and a dynamic obstacle detection method, generating an obstacle avoidance path in real time and fusing the obstacle avoidance path with the optimal global path to generate a final path; and S5, smoothing the final path by using a B-spline curve to eliminate sharp corners and sharp turns; and the application realizes autonomous path generation and dynamic obstacle avoidance of the UAV in a complex construction environment, and guarantees the continuity of the path.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle path planning, in particular to an unmanned aerial vehicle path planning method based on a global optimization method. BACKGROUND

[0002] With the acceleration of urban construction process, the demand for construction site safety monitoring is increasing, and more and more unmanned aerial vehicles are used for inspection and monitoring; the operation efficiency and task completion quality of unmanned aerial vehicles in the construction site are closely related to their flight path, so path planning has become one of the key research directions.

[0003] However, the construction site environment is complex, and there are a large number of known obstacles such as building frames, pipelines, tower cranes, and various dynamic unknown obstacles such as construction machinery, piled materials, and personnel vehicles; these obstacles make the path planning problem extremely challenging, and only using global planning algorithms often ignores sudden obstacles, and the planning speed is slow or it is difficult to obtain the optimal route, while only using local obstacle avoidance algorithms may fall into local optimization, and the reaction is not timely enough; therefore, the present application proposes a technical solution to ensure the flight safety of unmanned aerial vehicles by realizing global obstacle avoidance planning in the known environment and quickly switching to local obstacle avoidance strategy when encountering unknown obstacles.

[0004] After detailed search, no related technical solution has been found, therefore, a detailed technical solution is needed. SUMMARY

[0005] The present application provides an unmanned aerial vehicle path planning method based on a global optimization method, comprising the following steps:

[0006] S1: establishing a three-dimensional space environment model of the construction site, and setting the starting point coordinates and target point coordinates of the unmanned aerial vehicle;

[0007] S2: constructing a multi-dimensional physical constraint model according to the flight characteristics of the unmanned aerial vehicle, and at the same time, constructing a path cost function;

[0008] S3: obtaining the optimal global path of the unmanned aerial vehicle in the known obstacle environment by introducing a global optimization method that combines the wild dog optimization algorithm and the symbiotic organism search algorithm, and combining the three-dimensional space environment model of the construction site and the path cost function;

[0009] S4: when the unmanned aerial vehicle encounters unknown dynamic obstacles during flight, combining the RRT* algorithm and the dynamic obstacle detection method to trigger local path re-planning, real-time generating an obstacle avoidance path and fusing it with the optimal global path to generate a final path;

[0010] S5: smoothing the final path using a B-spline curve to eliminate sharp corners and sharp turns.

[0011] As a preferred solution, the construction site environment parameters collected in S1 are used to establish a three-dimensional space environment model of the construction site, and the construction site environment parameters include the spatial position and size information of known obstacles and the dynamic characteristics of unknown obstacles.

[0012] As a preferred solution, in the construction of the multi-dimensional physical constraint model in S2, the minimum turning radius, the maximum pitch angle, the flight height limit and the maximum flight distance are set.

[0013] As a preferred solution, the formula of the flight path cost function is:

[0014] wherein, J cost represents the flight path cost function, J length represents the flight path length cost, J height represents the flight path height cost, J turn represents the maximum turning angle cost, w1 represents the weight value of the flight path length cost function, w2 represents the weight value of the flight path height cost function, and w3 represents the weight value of the maximum turning angle cost function; w i i=1, 2, 3.

[0015] As a preferred solution, the calculation formula of the flight path length cost is:

[0016] wherein, x i represents the x-axis coordinate value of the i-th flight path node in the three-dimensional coordinate system; y i represents the y-axis coordinate value of the i-th flight path node in the three-dimensional coordinate system; z i represents the z-axis coordinate value of the i-th flight path node in the three-dimensional coordinate system; and n is the total number of flight path nodes.

[0017] As a preferred solution, the calculation formula of the flight path height cost is:

[0018] wherein, p i is the coordinate of the i-th flight path node p.

[0019] As a preferred solution, the calculation formula of the maximum turning angle cost is:

[0020] wherein, δ is the maximum turning angle, γ i is the flight turning angle of a certain segment, and a i is the vector of the i-th segment in the flight path.

[0021] As a preferred solution, the flow of the global optimization method in S3 is:

[0022] B1: Initialize parameters and randomly generate the initial population;

[0023] B2: Fitness value calculation;

[0024] B3: Determine if the random number P is less than 0.5. If so, use the group attack-mutual benefit mechanism to update the current position of the individual; otherwise, use the sweeping behavior-symbiosis mechanism to update the current position of the individual. P is a uniformly distributed random number in the interval (0, 1).

[0025] B4: Determine if the individual survival rate is less than 0.3. If yes, continue to B5; otherwise, proceed to B6.

[0026] B5: Employs a survival-parasitism mechanism to update individual location;

[0027] B6: Update the optimal fitness value;

[0028] B7: Determine whether all individuals have been traversed. If yes, execute B8; otherwise, jump to B2.

[0029] B8: Determine if the iteration has ended. If so, output the optimal global path and end the process; otherwise, jump to B2.

[0030] As a preferred approach, the final trajectory is smoothed using a cubic B-spline curve.

[0031] As a preferred embodiment, the flow of the RRT* algorithm in S4 is as follows:

[0032] A1: Initialize the random tree T;

[0033] A2: During the sampling process, the RRT* algorithm either directly selects the target point or randomly samples a point in space;

[0034] A3: After sampling, the RRT* algorithm searches for the distance X during the tree search process. rand The nearest node X nearest It expands towards the sampling point direction with a fixed step size Δx, generating a new node X. new ;

[0035] A4: Determine the new node X new If a collision occurs with an unknown dynamic obstacle, return to A2 if yes, otherwise proceed to A5;

[0036] A5: The RRT* algorithm searches for the optimal parent node within a specific radius; where the specific radius is 1.5 to 3 times the step size.

[0037] A6: Add the optimal parent node to the random tree T;

[0038] A7: judge whether a path meeting the requirements has been found, if not, return to A2, if yes, execute A8;

[0039] A8: judge whether the termination condition of the algorithm is met, if yes, end the flow; if not, execute A9;

[0040] A9: update the starting node of the path planning;

[0041] A10: update the obstacle environment, correct or re-record the position, shape and state information of the obstacles in the current scene according to real-time information or environmental changes;

[0042] A11: re-plan, return to A2 and re-execute.

[0043] As a preferred solution, the formula of A2 is:

[0044] Wherein: X rand represents the coordinates of the randomly sampled nodes, ξ is a uniform random number, P goal represents the target bias sampling probability parameter, X goal represents the directly selected target point, used for guidance, X free represents the randomly sampled point in space, used for exploration. RandomSample X free represents the operation of randomly sampling the feasible coordinate points in the free space region.

[0045] As a preferred solution, the calculation formula of the new node X new in A3 is:

[0046] Wherein, X new represents the new node, X nearest represents the nearest node, and Δx represents a fixed step length.

[0047] As a preferred solution, the selection formula of the optimal parent node in A5 is:

[0048] X parent = argmin {Cos t ( X near )+ d ( X near , X new )}

[0049] X ​parent represents the optimal parent node, Cos t X represents the cumulative cost from the starting point to node X, d represents the Euclidean distance; X near denotes the candidate nearest neighbor nodes located within X new neighborhood, usually any node in the set of nodes that satisfy the distance constraint within the set of existing nodes in the tree, used as candidate parent nodes, each node in the candidate neighbor set is traversed and compared when selecting the optimal parent node.

[0050] As a preferred solution, the B-spline curve formula is:

[0051] where P(u) is the B-spline curve, d i (i = 0,1,2,..., n) represents the control points, N i ,k (u) represents the K-order normalized B-spline basis function defined by the following recursive formula; n represents the highest index of the control point sequence of the B-spline curve, used to represent the range of the number of control points, i.e. the total number of control points is n+1, and the control point set is d 0 , d 1 , d n}; the summation symbol denotes the weighted summation of all control points and their corresponding basis functions, thereby obtaining the point coordinates of the B-spline curve P(u);

[0052] ;

[0053] where i represents the index of the basis function, k represents the order of the B-spline, u represents the curve parameter, u i represents the i-th node in the node vector; define represents a mathematical convention used to handle the indeterminate form that may occur in the recursive formula.

[0054] Based on the fusion strategy of global planning and local obstacle avoidance, the application realizes the autonomous path generation and dynamic obstacle avoidance of the unmanned aerial vehicle in the complex construction environment, solves the problems of insufficient path optimization ability and lack of effective avoidance strategy for unknown obstacles in the existing method in the construction site environment; the application uses B-spline curve for path smoothing, ensures the continuity and flight stability of the path, and enables the unmanned aerial vehicle to efficiently and safely perform the construction site safety monitoring task, and the application has strong engineering practical value and popularization potential. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 ​A logic block diagram for the present application;

[0056] Figure 2 A pitch angle θ constraint schematic diagram for the present application;

[0057] Figure 3 A B-spline curve for the present application;

[0058] Figure 4 A flowchart of a global optimization method;

[0059] Figure 5 A two-dimensional experiment convergence curve;

[0060] Figure 6 A two-dimensional experiment fitness value comparison diagram;

[0061] Figure 7 A three-dimensional experiment convergence curve;

[0062] Figure 8 A three-dimensional experiment fitness value comparison diagram;

[0063] Figure 9 A flowchart of an RRT* algorithm. DETAILED DESCRIPTION

[0064] The specific embodiments of the present application are described in detail below with reference to the accompanying drawings; it should be noted that the specific embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. Embodiment one

[0065] The embodiment provides a UAV path planning method based on a global optimization method, more specifically, a UAV path planning method for a construction site based on a global optimization method, aiming to solve the problems of low path planning efficiency and poor obstacle avoidance capability of a UAV in a complex construction environment, and to realize a high-precision and high-robustness safety monitoring task; comprising the following steps:

[0066] S1: Before starting the task, a three-dimensional space environment model of the construction site is established, and the starting point coordinates and target point coordinates of the UAV are set, to provide a data basis for subsequent path planning; specifically, the construction site environment parameters are collected to establish the three-dimensional space environment model of the construction site, the construction site environment parameters including the spatial position and size information of known obstacles, and the dynamic characteristics of unknown obstacles; the three-dimensional space environment model of the construction site is realized through a programming language, more specifically, a simplified modeling strategy is adopted, the known obstacles of fixed facilities such as buildings, tower cranes and construction equipment are represented as regular bodies such as cylinders through geometric simplification modeling, and the unknown obstacles such as transport vehicles, construction personnel or temporarily stacked materials are modeled as spheres, in this way, the three-dimensional space environment model of the complex construction site can be quickly constructed, and through the construction of the complete three-dimensional space environment model, basic data support is provided for subsequent path planning and simulation.

[0067] S2: According to the flight characteristics of the unmanned aerial vehicle, parameters such as minimum turning radius, maximum pitch angle, flight height limit and maximum distance are set, a multi-dimensional physical constraint model is constructed, and it is ensured that the generated flight path meets the flight dynamics limit of the vehicle, which not only ensures that the generated flight path is mathematically feasible, but also can be safely executed by the flight control system of the unmanned aerial vehicle; at the same time, according to the flight path parameter minimization principle, a multi-parameter flight path cost function is constructed, considering factors such as flight path length cost, height cost, maximum turning angle cost, etc., to provide quantitative evaluation indicators for optimized path planning, ensuring obstacle avoidance capability while taking into account energy economy and task completion efficiency, and the flight path cost function is realized through programming language.

[0068] S3: A global optimization method combining the Dog Optimization Algorithm (DOA algorithm) and the Symbiotic Organisms Search (SOS algorithm) is used to perform global flight path planning on the three-dimensional space environment model, and an initial global path that avoids known obstacles is generated; then, combined with the environment model and the cost function, the optimal global path of the unmanned aerial vehicle in the known obstacle environment is obtained; the global flight path planning is realized through programming language, and the global optimization method is used for simulation, and the global optimal path is obtained.

[0069] The global optimization method in S3 combines the group attack, cleaning behavior and survival rate mechanism of the Dog Optimization Algorithm with the mutual benefit, symbiosis and parasitism stages of the Symbiotic Organisms Search algorithm, realizes the cooperative optimization of the two algorithms, that is, introduces three mechanisms of group attack-mutual benefit, cleaning-symbiosis, and survival rate-parasitism, improves the search efficiency and convergence speed, and obtains the optimal global path (optimal flight path); compared with traditional single algorithm, the global optimization method can find a feasible path faster and avoid falling into a local optimal solution, so as to generate a globally optimized global flight path in a complex construction site environment.

[0070] S4: When the unmanned aerial vehicle flies according to the optimal global path, real-time detection of unknown obstacles is encountered, such as temporary entry of construction vehicles or movement of construction personnel, combined with the RRT* algorithm and dynamic obstacle detection method, local path re-planning is triggered, real-time obstacle avoidance path is generated to realize real-time obstacle avoidance, and is fused with the optimal global path, and is seamlessly connected to the original global flight path through smooth transition, to generate the final flight path, so as to ensure that the unmanned aerial vehicle continues to execute the remaining flight range safely; it can ensure the safety of the unmanned aerial vehicle and the continuity of the task, and there is no risk of collision.

[0071] S5: Smooth optimization is performed on the final flight path, and a cubic B-spline curve is used for smoothing to eliminate sharp corners and sudden turns, so that the curvature of each segment of the flight path is continuous and changes smoothly to meet the requirements of the UAV turning radius and attitude change, and a smooth flight path suitable for actual flight of the UAV is obtained; the continuity and stability of the flight trajectory are improved, and the final flight path is more in line with the actual flight characteristics of the UAV; the UAV can efficiently and safely perform the construction site safety monitoring task.

[0072] The B-spline curve formula is:

[0073] wherein, P(u) is the B-spline curve, d i (i = 0, 1, 2,..., n) represents the control points, N i ,k (u) represents the K-order normalized B-spline basis function defined by the following recursive formula; n represents the highest index of the control point sequence of the B-spline curve, which is used to represent the range of the number of control points, i.e. the total number of control points is n+1, and the control point set is d 0 , d 1 , d n}; the summation symbol represents the weighted summation of all control points and their corresponding basis functions, so as to obtain the point coordinates of the B-spline curve P(u);

[0074] wherein, i represents the index of the basis function, k represents the order of the B-spline, u represents the curve parameter, u i represents the i-th node in the node vector; define represents a mathematical convention used to handle the indeterminate form that may occur in the recursive formula.

[0075] This step corrects the inflection points in the final flight path, so that the path curvature is continuous and the turning is soft. The flight path after smoothing optimization can effectively reduce the attitude adjustment frequency during flight, reduce the burden of the control system, and improve the stability and energy utilization efficiency of the flight process. Embodiment Two

[0076] This embodiment provides a specific technical method of a flight path cost function, specifically:

[0077] The formula of the flight path cost function is:

[0078] wherein, J cost represents the flight path cost function, J length represents the length cost of the flight path, J height represents the height cost, and J turnw1 represents the weight value of the path length cost function, w2 represents the weight value of the height cost function, w3 represents the weight value of the maximum turning angle cost function, and w1, w2 and w3 satisfy and , i = 1, 2, 3.

[0079] Specifically, the path length cost directly affects the task efficiency, and the smaller the path length cost function is, the shorter the path is, the lower the energy consumption is, and the higher the completion rate is; the distance cost (path length cost) of the flight phase is shown in the formula, and the distance cost is the sum of the distance of each segment between the path nodes, wherein n is the total number of path nodes.

[0080] The calculation formula of the path length cost is:

[0081] Specifically, in order to avoid collision and improve energy efficiency, the unmanned aerial vehicle needs to maintain a reasonable flight height; in the site path optimization, the height configuration is particularly important, in order to make the unmanned aerial vehicle generate a suitable route, the height cost is introduced;

[0082] wherein, x i represents the x-axis coordinate value of the i-th path node in the three-dimensional coordinate system; y i represents the y-axis coordinate value of the i-th path node in the three-dimensional coordinate system; z i represents the z-axis coordinate value of the i-th path node in the three-dimensional coordinate system; n is the total number of path nodes;

[0083] The calculation formula of the height cost is:

[0084] , wherein p i is the coordinate of the i-th path node p.

[0085] Specifically, in order to avoid sharp turning of the path and avoid excessive steep turning, the calculation formula of the maximum turning angle cost is:

[0086] wherein, δ is the maximum turning angle, γ i is the flight turning angle of a certain segment, a i is the vector of the i-th segment in the path. Embodiment three

[0087] This embodiment describes the process of the RRT* algorithm in S4: the RRT* algorithm is a sampling-based path planning algorithm, which is an improved version of RRT (rapidly-exploring random tree), and the core advantage is that it can efficiently search for a path close to the optimal path in a complex environment;

[0088] A1: the random tree T is initialized;

[0089] A2: In the sampling process, the RRT* algorithm can directly select the target point or randomly sample a point in the space with a certain probability; the formula of the random sampling rule is as follows:

[0090] Wherein: X rand represents the random node coordinates obtained by sampling, which is used for node expansion of the RRT* tree; ξ is a uniform random number, specifically a random number uniformly distributed in the interval (0, 1); P goal represents the target bias sampling probability parameter; X goal represents the directly selected target point, which is used to guide X ; free represents the randomly sampled point in the space, which is used for exploration, i.e. the unobstructed free space region; RandomSample ( X free ) represents the operation of randomly sampling a feasible coordinate point in the free space region;

[0091] In this step, in order to improve the convergence efficiency of the algorithm, the target bias sampling strategy is introduced, when ξ < P goal , set X rand to the target point coordinates X goal to guide the search process to converge to the target direction; otherwise, randomly sample in the unobstructed free space X free to obtain X rand = RandomSample ( X free ).

[0092] A3: After the sampling is completed, the RRT* algorithm finds the node X rand closest to X nearest in the process of searching the tree, and expands in the direction of the sampling point with a fixed step length Δx to generate a new node X new ;

[0093] The calculation formula of the new node X new is as follows:

[0094] X new represents the new node, X nearest represents the nearest node, and Δx represents the fixed step length.

[0095] A4: Determine the new node X new If a collision occurs with an unknown dynamic obstacle, return to A2 if yes, otherwise proceed to A5;

[0096] A5: Generate a new node X new Then, the RRT* algorithm searches for the optimal parent node within a specific radius; where the specific radius is 1.5 to 3 times the step size; the key to the RRT* algorithm is to find the optimal parent node for the new node X. new The formula for finding the optimal parent node is as follows:

[0097] X parent = argmin {Cos t ( X near )+ d ( X near , X new )}

[0098] X parent Cos represents the optimal parent node. t ( X ) represents the cumulative cost from the starting point to node X. d Represents Euclidean distance; X near Indicates that it is located at X new Candidate nearest neighbor nodes within the neighborhood are typically any node in the set of nodes that satisfy the distance constraint within the existing set of nodes in the tree. These nodes are used as candidate parent nodes, and the nodes in the candidate nearest neighbor set are traversed and compared when selecting the optimal parent node.

[0099] Compared to the RRT algorithm, the RRT* algorithm has a range-based reconnection strategy. This rewiring mechanism ensures that the path from the starting point to each node is as short as possible, thereby continuously optimizing the overall path quality.

[0100] A6: Add the optimal parent node to the random tree T;

[0101] A7: Determine if a path that meets the requirements has been found; otherwise, return to A2; otherwise, execute A8.

[0102] A8: Determine if the algorithm's termination conditions are met, such as the path length being sufficient or the number of iterations being enough. If yes, end the process; otherwise, execute A9.

[0103] A9: Update the starting node of the path planning;

[0104] A10: update the obstacle environment, according to real-time information or environmental changes, correct or re-record the position, shape, state information of the obstacles in the current scene;

[0105] A11: re-planning, return to A2 to re-execute. Embodiment four

[0106] This embodiment illustrates the global optimization method, the following combination Figure 4 Specifically discuss the logic of global optimization method, the core logic of the global optimization algorithm is to explore and develop in parallel in the solution space through simulating the cooperative evolution and competition mechanism of biological population, in order to find the optimal flight path of unmanned aerial vehicle; Its flow can be clearly divided into the following stages:

[0107] B1: initialize parameters and randomly generate initial population;

[0108] The algorithm first sets the control parameters, such as population size, maximum iteration number and weight coefficient of cost function, etc.; Then, a group of initial "wild dog" individuals are randomly generated in the three-dimensional environment model of the construction site, each "wild dog" individual represents a complete flight path from the starting point to the end point; This step aims to initialize a solution set with sufficient diversity, laying the foundation for the subsequent evolution process, and ensuring that the algorithm can widely explore the entire solution space.

[0109] B2: fitness value calculation;

[0110] According to the constructed cost function, the fitness value of each individual in the population is calculated; This step is to quantitatively evaluate the pros and cons of the solution, and the fitness value directly reflects the pros and cons of the flight path, such as: the lower the cost, the better the fitness; This is the fundamental basis for driving the entire algorithm to evolve towards the optimal solution.

[0111] B3: judge whether the random number P is less than 0.5, if yes, use the group attack-symbiosis mechanism to update the current position of the individual, otherwise use the cleaning behavior-symbiosis mechanism to update the current position of the individual; P represents a random number parameter used for strategy selection, P is a uniformly distributed random number in the interval (0, 1);

[0112] A random number in the range of [0, 1] is generated, and different position update strategies are selected according to its value; This is a branch decision point, this mechanism aims to dynamically balance the exploration and development ability of the algorithm, taking 0.5 as the boundary, guiding the population to execute global search and local optimization with similar probability, avoiding premature convergence to local optimum.

[0113] If P < 0.5, the individual position is updated using a group attack-mutualism mechanism. Entering this branch, the mechanism combines the group attack behavior of the Wild Dog algorithm and the mutualism phase of the Symbiotic Biology algorithm. This step focuses on global exploration. It simulates group cooperative hunting, guides individuals to learn towards historical optimal solutions, and explores new areas through interaction with random individuals, aiming to discover more potential solution spaces.

[0114] The formula for calculating the group attack-mutual benefit mechanism is:

[0115] ;

[0116] ;

[0117] ;

[0118] V new = V r1 + rand 0,1 * (V best - Mutual_vector.BF);

[0119] Among them, V new This indicates that the individual's position has been updated. and β1 represents the individual positions of two randomly generated wild dogs; β1 represents... Uniformly generated random numbers within the interval, β1 is a scaling factor that can change the size and direction of the wild dog's trajectory; na represents [2, SearchAgents The random number generated by the reciprocal of [2]; V best φk(t) represents the current optimal solution; φk(t) represents the subset of wild dogs that will attack, where φk... X, where X represents the number of randomly generated stray dogs; Represents the position of the current iteration of the search; Represents the best search proxy obtained in the previous iteration; Mutual_vector represents and The mutually beneficial relationship between them; BF represents the benefit factor, BF∈{1, 2}; rand 0,1 ∈{0,1}.

[0120] If P ≥ 0.5, the individual position is updated using a sweeping behavior-symbiosis mechanism. This mechanism combines the sweeping (random foraging) behavior of wild dogs with the symbiotic phase of the symbiotic biological algorithm. This step focuses on local development, which encourages individuals to conduct fine searches in their current location and learn from the information of other random individuals in the population. The aim is to deeply optimize existing good solutions and improve the quality of the solutions.

[0121] Cleaning behavior - the calculation formula of symbiotic mechanism is:

[0122] ;

[0123] ;

[0124] ;

[0125] wherein, , are two candidate search vectors generated in the cleaning behavior stage, β2 represents a random number generated, σ represents a randomly generated binary number, σ ∈ {0,1}; r 1、 r 2 represents a random number from 1 to the number of stray dog populations, represents the position of the search agent of the first stray dog; r represents the position of the search agent of the second stray dog; r

[0126] represents the position of the current iteration search; .

[0127] B4: Determine whether the individual survival rate is less than 0.3. If yes, continue to execute B5, otherwise jump to B6;

[0128] After the above update, the survival rate of each individual is calculated. If the survival rate is lower than the threshold value 0.3, the individual is determined to be a disadvantaged individual. This step is a selection mechanism for population survival of the fittest, which is used to identify and mark individuals with poor fitness, and to prepare for population update and diversification;

[0129] B5: Update the individual position by using the survival rate - parasitic mechanism; specifically: adopt the parasitic strategy for individuals with low survival rate to update the individual position;

[0130] For the marked disadvantaged individual, it is replaced by a newly generated or strongly mutated new individual through the parasitic strategy. This step is the key to maintaining population diversity and jumping out of local optimum. It effectively prevents the premature convergence of the population and increases the possibility of exploring unknown areas by introducing new genetic materials.

[0131] The calculation formula of the survival rate - parasitic mechanism is:

[0132] ;

[0133] wherein, ​​This represents a search agent with a low survival rate that is about to be updated; r1 and r2 represent two different random numbers, r 1, r2∈ (1, SearchAgents), and r1≠ r2; (t) (t) represents the r1 and r2th search agents; σ represents the best search agent obtained in the previous iteration; σ represents a randomly generated binary number, σ∈{0,1}.

[0134] B6: Update the optimal fitness value;

[0135] After updating all individuals, the entire population is examined, and the optimal fitness value found in the current iteration and its corresponding trajectory are recorded. This step ensures that the algorithm does not lose the best solution found during the evolution process, thus guaranteeing convergence.

[0136] B7: Determine whether all individuals have been traversed. If yes, execute B8; otherwise, jump to B2.

[0137] Check whether the above update operations from B3 to B6 have been completed for every individual in the population in the current iteration. This step is the termination check of the inner loop, ensuring that the entire population has a fair chance to evolve in a complete iteration, thereby coordinating the search process.

[0138] B8: Determine if the iteration has ended. If yes, output the globally optimal path and end the process; otherwise, jump to B2.

[0139] Checking whether the maximum number of iterations has been reached, or whether the optimal solution has not improved significantly for several consecutive generations, is the termination check of the outer loop. It determines the timing of the end of the entire optimization process, achieving a balance between computational resources and solution quality.

[0140] When the algorithm terminates, it outputs the globally optimal individual recorded throughout the evolution process, i.e., the planned optimal trajectory. This step is the final output of the algorithm, which delivers a safe trajectory that has the lowest overall cost and is most suitable for UAV flight under all constraints.

[0141] This embodiment iterates until convergence, and finally outputs the global optimal solution. This algorithm successfully integrates the advantages of two metaheuristic algorithms and solves the global trajectory planning problem of UAVs in complex environments efficiently and robustly through the built-in balancing mechanism.

[0142] In summary, by adopting the technical scheme, the application solves the problems of insufficient path optimization ability of the existing method in a construction site environment and lack of effective avoidance strategy for unknown obstacles. Figures 5 to 8 The experimental results show that, compared with the traditional planning algorithm, the method can significantly shorten the flight path, improve the obstacle avoidance success rate and task completion efficiency, and provide a practical technical solution for intelligent monitoring and management of construction sites, and has broad engineering practical value, engineering application prospect and popularization value.

[0143] Figure 5 Figure 8 The HIDOA-SOS algorithm in the application represents a global optimization method of the fusion of the wild dog optimization algorithm and the symbiotic organism search algorithm; the DOA algorithm represents the wild dog optimization algorithm; the SOS algorithm represents the symbiotic organism search algorithm; and the SSA algorithm represents the sparrow search algorithm.

[0144] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and a general hardware platform, and of course, it can also be realized by hardware, but in many cases, the former is a better embodiment; based on such understanding, the technical solutions of the application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, an optical disk), and includes a plurality of instructions for causing a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the methods described in the various embodiments of the application.

[0145] The embodiments of the application are described above in combination with the drawings, but the application is not limited to the above specific embodiments, and the above specific embodiments are only illustrative and not restrictive, and those skilled in the art can make many forms under the inspiration of the application without departing from the scope of the application and the protection scope of the claims.​

Claims

1. A UAV trajectory planning method based on global optimization, characterized in that, Includes the following steps: S1: Establish a three-dimensional spatial environment model of the construction site and set the starting point coordinates and target point coordinates of the UAV; S2: Based on the flight characteristics of the UAV, construct a multi-dimensional physical constraint model; at the same time, construct a trajectory cost function; S3: By introducing a global optimization method that integrates the Wild Dog optimization algorithm and the Symbiotic Biology Search algorithm, and combining it with the 3D spatial environment model of the construction site and the trajectory cost function, the optimal global path of the UAV in a known obstacle environment is obtained. The process of the global optimization method is as follows: B1: Initialize parameters and randomly generate the initial population; B2: Fitness value calculation; B3: Determine if the random number P is less than 0.

5. If so, use the group attack-mutual benefit mechanism to update the current position of the individual; otherwise, use the sweeping behavior-symbiosis mechanism to update the current position of the individual. P is a uniformly distributed random number in the interval (0, 1). B4: Determine if the individual survival rate is less than 0.

3. If yes, continue to B5; otherwise, proceed to B6. B5: Employs a survival-parasitism mechanism to update individual location; B6: Update the optimal fitness value; B7: Determine whether all individuals have been traversed. If yes, execute B8; otherwise, jump to B2. B8: Determine if the iteration has ended. If yes, output the optimal global path and end the process; otherwise, jump to B2. S4: When the UAV encounters an unknown dynamic obstacle during flight, it combines the RRT* algorithm with the dynamic obstacle detection method to trigger local path replanning, generate an obstacle avoidance path in real time and merge it with the optimal global path to generate the final trajectory. S5: The final trajectory is smoothed using B-spline curves to eliminate sharp angles and abrupt turns.

2. The UAV trajectory planning method based on global optimization as described in claim 1, characterized in that, The multi-dimensional physical constraint model constructed in S2 includes setting the minimum turning radius, maximum pitch angle, flight altitude limit, and maximum range.

3. The UAV trajectory planning method based on global optimization as described in claim 1, characterized in that, The formula for the trajectory cost function is: Among them, J cost J represents the trajectory cost function. length J represents the cost of track length. height J represents the cost of track altitude. turn w1 represents the cost of the maximum turning angle, w2 represents the weight of the track length cost function, w3 represents the weight of the maximum turning angle cost function, and w represents the weight of the track altitude cost function. i i=1, 2, 3.

4. The UAV trajectory planning method based on global optimization as described in claim 3, characterized in that, The formula for calculating the cost of track length is: ； in, x i This represents the x-axis coordinate of the i-th track node in the three-dimensional coordinate system; y i This represents the y-axis coordinate of the i-th track node in the three-dimensional coordinate system; z i This represents the z-axis coordinate of the i-th track node in the three-dimensional coordinate system; n is the total number of track nodes.

5. The UAV trajectory planning method based on global optimization as described in claim 3, characterized in that, The formula for calculating the altitude cost of a flight path is: , where p i Let p be the coordinates of the i-th track node.

6. The UAV trajectory planning method based on global optimization as described in claim 3, characterized in that, The formula for calculating the maximum corner cost is: ； Where δ is the maximum steering angle, γ i For a certain flight turn angle, a i Let be the vector of the i-th segment of the track.

7. The UAV trajectory planning method based on global optimization as described in claim 1, characterized in that, In S5, the formula for the B-spline curve is: ； Where P(u) is a B-spline curve, d i (i = 0,1,2,...,n) represent control points, N i ,k (u) represents the K-order normalized B-spline basis function defined by the following recursive formula; n represents the highest index of the control point sequence of the B-spline curve, used to characterize the range of the number of control points, that is, the total number of control points is n+1; ； Where i represents the index of the basis function, k represents the order of the B-spline, and u represents the curve parameter. i represents the i-th node in the node vector; define represents a mathematical convention used to handle indeterminate forms that may appear in recursive formulas.

8. The UAV trajectory planning method based on global optimization as described in claim 1, characterized in that, The process of the RRT* algorithm in S4 is as follows: A1: Initialize random tree T; A2: During the sampling process, the RRT* algorithm either directly selects the target point or randomly samples a point in space; A3: After sampling, the RRT* algorithm searches for the distance X during the tree search process. rand The nearest node X nearest It expands towards the sampling point direction with a fixed step size Δx, generating a new node X. new ; A4: Determine the new node X new If a collision occurs with an unknown dynamic obstacle, return to A2 if yes, otherwise proceed to A5; A5: The RRT* algorithm searches for the optimal parent node within a specific radius; where the specific radius is 1.5 to 3 times the step size. A6: Add the optimal parent node to the random tree T; A7: Determine if a path that meets the requirements has been found; otherwise, return to A2; otherwise, execute A8. A8: Determine if the algorithm's termination condition is met; if yes, end the process; otherwise, execute A9. A9: Update the starting node of the path planning; A10: Update obstacle environment. Based on real-time information or environmental changes, correct or re-record the position, shape, and status information of obstacles in the current scene. A11: Replan and return to A2 to execute again.

9. The UAV trajectory planning method based on global optimization as described in claim 8, characterized in that, The formula for A2 is: ； in: X rand Let P represent the coordinates of the random nodes obtained from sampling, where ξ is a uniformly random number. goal X represents the target bias sampling probability parameter. goal X represents the directly selected target point. free Represents points randomly sampled in space. RandomSample ( X free This indicates the operation of randomly sampling feasible coordinate points within a free space region; The new node X in A3 new The calculation formula is: ;X new Represents a new node, X nearest Represents the nearest node, and Δx represents a fixed step size; The formula for selecting the optimal parent node in A5 is: X parent = argmin {Cos t ( X near )+ d ( X near , X new )} X parent Cos represents the optimal parent node. t ( X ) represents the cumulative cost from the starting point to node X. d Represents Euclidean distance; X near Indicates that it is located at X new The candidate nearest neighbor node in the neighborhood is any node in the set of nodes that satisfy the distance constraint in the existing set of nodes in the tree. It is used as a candidate parent node. When selecting the optimal parent node, each node in the candidate nearest neighbor set is traversed and compared.

Images