Unmanned vehicle path planning method and system based on unmanned aerial vehicle perception, and medium

Abstract

The invention provides an unmanned vehicle path planning method and system based on unmanned aerial vehicle perception and a medium, and belongs to the technical field of path planning, and the method comprises the following steps: building a grid map of a ground environment based on a perception system and a positioning navigation system carried by an unmanned aerial vehicle, and carrying out the correction based on environment information; determining a path planning starting point and an unmanned vehicle path planning target function with the constraint of shortest moving path, shortest time consumption or least energy consumption, and performing position updating on the corrected grid map through an improved seagull optimization algorithm to determine an optimal seagull position; and determining an optimal path planning result according to the optimal seagull position which is sequentially updated according to a preset maximum number of iterations. According to the method, the problems of local optimum and convergence precision of the sea gull optimization algorithm are solved, and the unmanned vehicle path planning effect can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned vehicles, and in particular to an unmanned vehicle path planning method based on drone perception. Background Art

[0002] The air-ground heterogeneous robot system constructed by aerial drones and ground unmanned vehicles has become a research focus in the field of distributed artificial intelligence technology. In this system, the seamless coordination and cross-domain cooperation between drones and unmanned vehicles indicate that robotics technology and its applications are about to enter a new stage of development. Unmanned vehicles have shown significant advantages in close-range operations with their excellent ability to accurately track ground targets. However, when faced with challenges with incomplete or partially unknown environmental information, relying solely on on-board sensors for environmental perception is inadequate, limiting their ability to perform global path planning, and in most cases only local path planning can be completed. In contrast, drones, with their high-altitude perspective advantage, can capture comprehensive information about the surrounding environment at a specific flight altitude, providing a more macroscopic perspective for decision-making. However, this advantage also comes with a price, that is, due to the increase in altitude, drones may miss some details or local important information on the ground. In order to overcome their respective limitations and maximize their effectiveness, the collaborative work between drones and unmanned vehicles is particularly important. Through the complementary advantages and deep integration of the two, drones can provide unmanned vehicles with a global overview of the environment and path guidance, while unmanned vehicles can perform specific tasks with their precise ground positioning capabilities. This air-ground coordination mechanism makes it possible to achieve more accurate and efficient global path planning for unmanned vehicles, marking a solid step forward in the advancement of robotics technology towards a higher level of intelligence.

[0003] The path planning problem of unmanned vehicles based on drone perception can actually be regarded as a complex optimization problem with constraints. As an efficient problem-solving strategy, intelligent optimization algorithms are particularly suitable for the field of path planning. Among them, the Seagull Algorithm, as an innovative intelligent optimization method, provides a new solution to the path planning problem by simulating the natural behavior of seagulls foraging. However, the Seagull Optimization Algorithm is not perfect. It faces some significant challenges, mainly including the difficulty of the algorithm falling into the dilemma of local optimal solutions and the relatively low accuracy of convergence to solutions. These problems may lead to unsatisfactory results in the actual application of path planning and make it difficult to achieve the expected optimization effect. Summary of the invention

[0004] To solve the above problems, the present invention provides an unmanned vehicle path planning method based on drone perception. The method introduces the position update mechanism of the transient search optimization algorithm and the spider monkey optimization algorithm to improve the seagull position update method, which effectively solves the problem that the seagull algorithm is prone to falling into local optimality during path planning, resulting in general planning effect.

[0005] To achieve the above object, the present invention provides the following technical solutions.

[0006] A method for unmanned vehicle path planning based on drone perception includes the following steps:

[0007] A grid map of the ground environment is established based on the perception system and positioning navigation system carried by the drone, and corrections are made based on environmental information;

[0008] Determine the starting point of path planning and the objective function of unmanned vehicle path planning with the shortest moving path, or the shortest time consumption, or the least energy consumption as constraints, and update the position on the corrected grid map through the improved seagull optimization algorithm to determine the optimal seagull position; wherein, the improved seagull optimization algorithm introduces the position update mechanism of the transient search optimization algorithm and the spider monkey optimization algorithm into the position update method of the original seagull optimization algorithm to improve the seagull position update method, and comprehensively considers the optimal position of the seagull in this iteration, different position update modes, the average position of other seagulls in the population, and the global leader probability value factors to update the seagull position;

[0009] The optimal seagull position is updated in sequence according to the preset maximum number of iterations to determine the optimal path planning result.

[0010] Preferably, the updating of the optimal position by using the improved Seagull optimization algorithm comprises the following steps:

[0011] Set the size of the seagull population, the maximum number of iterations, and the upper and lower bounds of the seagull search;

[0012] Introduce Gaussian mapping to initialize the position of the seagull population;

[0013] Simulate the migration and attack behaviors of seagulls, and introduce the position update mechanism of transient search optimization algorithm and spider monkey optimization algorithm to improve the seagull position update method, perform position update, and record the optimal seagull position in the iteration;

[0014] The optimal seagull position is further updated through bidirectional sine mutation in each dimension, and the optimal position in the iteration is recorded;

[0015] The optimal position is updated in sequence according to the preset number of iterations, and the optimal path result is output.

[0016] Preferably, the Gaussian mapping initialization of the seagull population position comprises the following steps:

[0017] Determine the population size N, the lower boundary LB and the upper boundary UB of the seagull search;

[0018] Generate random number x through Gaussian mapping t :

[0019]

[0020] In the formula, mod(·) is the remainder function, x t+1 is the next random number;

[0021] Use the generated Gaussian random numbers to initialize the seagull position:

[0022] P s (t) = (UB - LB) × x t +LB.

[0023] Preferably, the position updating mechanism of introducing the transient search optimization algorithm and the spider monkey optimization algorithm to improve the seagull position updating method and perform position updating includes the following steps:

[0024] Simulate the migratory behavior of seagulls, including avoiding collisions, moving in the direction of the best position, and approaching the best position;

[0025] To avoid collisions with other seagulls, the algorithm uses an additional variable A to calculate the new position of the seagull:

[0026] C s (t) = A × P s (t)

[0027] A=f c -(t×f c / Miter)

[0028] Where: C s (t) is the new position that does not conflict with other seagulls, P s (t) is the current position of the seagull, t is the current iteration number, Miter is the maximum iteration number, and A is the movement behavior of the seagull in the given search space; f c is the control coefficient, and its value decreases from 2 to 0;

[0029] After avoiding overlapping with other seagulls, the seagull will move in the direction of the best position:

[0030] M s (t) = B × (P bs (t)-P s (t))

[0031] B = 2 × A 2 × d

[0032] Where: M s (t) represents the direction of the optimal position, P bs(t) represents the best position of the tth iteration, B is a random number responsible for balancing global and local searches; r d is a random number in the range [0,1];

[0033] When the seagull moves to a position where it does not collide with other seagulls, it moves in the direction of the best position and reaches a new position:

[0034] D s (t)=|C s (t)+M s (t)|

[0035] Where: D s (t) is the distance the seagull moves to its new position;

[0036] Simulating seagull attack behavior: When attacking prey, seagulls can continuously change the attack angle and speed through spiral motion. The spiral motion is expressed as:

[0037]

[0038] Where: r is the radius of each spiral; θ is a random angle value in the range [0, 2π]; u and v are related constants that define the shape of the spiral, both of which can be set to 1; e is the base of the natural logarithm;

[0039] By introducing the transient search optimization algorithm and the spider monkey optimization algorithm, the improved seagull position update formula is as follows:

[0040]

[0041] Where:

[0042] C t =k·z·λ3+1

[0043] T=2·z·λ2-z

[0044]

[0045] Among them, P s (t+1) is the updated position of the seagull at the t+1th iteration; P bs (t) represents the best position of the tth iteration; P s (t) is the current position of the seagull; α and β are random numbers between [0, 1]; C t and T are random thermal resistance coefficients; z is the attenuation coefficient, which decreases from 2 to 0 as the number of iterations increases; k is a constant (k = 0, 1, 2…); λ1, λ2 and λ3 are random numbers in [0, 1]; P r1 (t), P r2 (t) and P r3(t) represents three seagull individuals randomly selected at the tth iteration, r1≠r2≠r3; P avg (t) is P r1 (t), P r2 (t) and P r3 The average value of (t); p i is the global leader probability of the i-th seagull in the t-th iteration; fitness i is the fitness value of the i-th seagull; i is the maximum fitness value of the seagull group in the tth iteration;

[0046] Calculate the fitness value:

[0047] fitness(t)=F f (P s (t+1))

[0048] In the formula, F f (·) is the fitness function when calculating the fitness value;

[0049] Record the best seagull in the iteration.

[0050] Preferably, further updating the optimal position by bidirectional sine mutation dimension by dimension comprises the following steps:

[0051] For dimension j, the sine chaos value is calculated according to the current number of iterations, and the positive and negative directions are switched with equal probability:

[0052] sin Value = sin(πx0)

[0053]

[0054] In the formula, rand is a random number between 0 and 1; x0 is the iteration sequence value;

[0055] Perform mutation perturbation on the optimal position:

[0056] P bs(j) (t+1)′=P bs(j) (t+1)+SinValue×P bs(j) (t+1)

[0057] Where: P bs(j) (t+1) represents the optimal position P of the t+1th iteration bs The jth dimension of (t+1);

[0058] Greedy Update:

[0059]

[0060] After each dimension has been mutated, stop mutation.

[0061] A path planning system for an unmanned vehicle based on drone perception, the system comprising:

[0062] processor;

[0063] a memory having stored thereon a computer program executable on the processor;

[0064] Among them, when the computer program is executed by the processor, the steps of the unmanned vehicle path planning method based on drone perception are implemented.

[0065] A computer-readable storage medium stores a data processing program, and when the data processing program is executed by a processor, the steps of the unmanned vehicle path planning method based on unmanned aerial vehicle perception are implemented.

[0066] Beneficial effects of the present invention:

[0067] The present invention proposes an unmanned vehicle path planning method based on drone perception. The method improves the seagull position update method, introduces a transient search optimization algorithm and a spider monkey optimization algorithm to improve the seagull position update method, and comprehensively considers factors such as the optimal position of the seagull in this iteration, different position update modes, the average position of other seagulls within the population, and the global leader probability value to update the seagull position, thereby increasing the search range and avoiding falling into the local optimal situation. Combined with the objective function of path planning, better path planning points can be obtained, and further better path planning results are obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 is a flow chart of a method for unmanned vehicle path planning based on drone perception according to an embodiment of the present invention;

[0069] Figure 2 is a path planning result of an unmanned vehicle path planning method based on drone perception in an embodiment of the present invention;

[0070] Figure 3 It is an iterative process curve of an unmanned vehicle path planning method based on drone perception in an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0072] Example 1

[0073] The present invention proposes a path planning method for unmanned vehicles based on drone perception. Aiming at several problems existing in SOA, an improved seagull optimization algorithm (ISOA) is proposed and used for path planning of unmanned vehicles based on drone perception. The specific process is as follows: Figure 1 As shown, the specific steps are as follows:

[0074] S1: A grid map of the ground environment is established based on the perception system and positioning navigation system carried by the drone. The unmanned vehicle obtains the grid map established by the drone and corrects and supplements the grid map based on the environmental information it perceives.

[0075] S2: Establish the objective function of the unmanned vehicle path planning based on air-ground information coordination (which can be set to the shortest moving path, shortest time consumption, least energy consumption, etc. according to actual needs), and set the corresponding constraints and the number of key nodes D of the path.

[0076] S3: Parameter setting, mainly including: the size of the seagull population (i.e. the number of seagull individuals) N; the maximum number of iterations (i.e. the condition for stopping iteration) Miter; the lower boundary LB of the seagull optimization; the upper boundary UB of the seagull optimization.

[0077] S4: Determine the size of the population N, the lower boundary LB and the upper boundary UB of the seagull optimization search; introduce Gaussian mapping to initialize the position of the seagull population, including the following steps:

[0078] Determine the population size N, the lower boundary LB and the upper boundary UB of the seagull search.

[0079] Generate random number x through Gaussian mapping t :

[0080]

[0081] In the formula, mod(·) is the remainder function, x t+1 The next random number.

[0082] Use the generated Gaussian random numbers to initialize the seagull position:

[0083] P s (t) = (UB - LB) × x t +LB.

[0084] By introducing Gaussian mapping to initialize the positions of seagull populations, the uniformity and diversity of population position distribution can be improved, thereby enhancing the stability of the algorithm.

[0085] S5: Simulate the migratory behavior of seagulls, including avoiding collisions, moving toward the optimal position, and approaching the optimal position.

[0086] To avoid collisions with other seagulls, the algorithm uses an additional variable A to calculate the new position of the seagull:

[0087] C s (t) = A × P s (t)

[0088] A=f c -(t×f c / Miter)

[0089] Where: C s (t) is the new position that does not conflict with other seagulls, P s (t) is the current position of the seagull, t is the current iteration number, Miter is the maximum iteration number, and A is the movement behavior of the seagull in the given search space; f c is the control coefficient, and its value decreases from 2 to 0.

[0090] After avoiding overlapping with other seagulls, the seagull will move in the direction of the best position:

[0091] M s (t) = B × (P bs (t)-P s (t))

[0092] B = 2 × A 2 × d

[0093] Where: M s (t) represents the direction of the optimal position, P bs (t) represents the best position of the tth iteration, B is a random number responsible for balancing global and local searches; r d is a random number in the range [0,1].

[0094] When the seagull moves to a position where it does not collide with other seagulls, it moves in the direction of the best position and reaches a new position:

[0095] D s (t)=|C s (t)+M s (t)|

[0096] Where: D s (t) is the distance the seagull moves to its new position.

[0097] Simulating seagull attack behavior: When attacking prey, seagulls can continuously change the attack angle and speed through spiral motion. The spiral motion is expressed as:

[0098]

[0099] Where r is the radius of each spiral; θ is a random angle value in the range [0, 2π]; u and v are related constants that define the shape of the spiral, both of which can be set to 1; e is the base of the natural logarithm.

[0100] In the original seagull algorithm, only the optimal seagull position is used for guidance to update the seagull position. In order to more effectively improve the global search ability of the seagull, the position update mechanism of the transient search optimization algorithm and the spider monkey optimization algorithm is introduced to improve the seagull position update method. The optimal position of the seagull in this iteration, different position update modes, the average position of other seagulls in the population, the probability value of the global leader and other factors are comprehensively considered to update the seagull position, avoid local optimality in each iteration, and thus improve the global search ability of the seagull algorithm.

[0101] Drawing on the transient search optimization algorithm and the spider monkey optimization algorithm, the improved seagull position update formula is as follows:

[0102]

[0103] Where:

[0104] C t =k·z·λ3+1

[0105] T=2·z·λ2-z

[0106]

[0107] Among them, P s (t+1) is the updated position of the seagull at the t+1th iteration; P bs (t) represents the best position of the tth iteration; P s (t) is the current position of the seagull; α and β are random numbers between [0,1]; C t and T are random thermal resistance coefficients; z is the attenuation coefficient, which decreases from 2 to 0 as the number of iterations increases; k is a constant (k = 0, 1, 2…); λ1, λ2 and λ3 are random numbers in [0, 1]; P r1 (t), P r2 (t) and P r3 (t) represents three seagull individuals randomly selected at the tth iteration, r1≠r2≠r3; P avg (t) is P r1 (t), P r2 (t) and P r3 The average value of (t); p i is the global leader probability of the i-th seagull in the t-th iteration; fitness i is the fitness value of the i-th seagull; i is the maximum fitness value of the seagull colony in the tth iteration.

[0108] The present invention improves the position update method of seagulls, introduces the position update mechanism of transient search optimization algorithm and spider monkey optimization algorithm to improve the position update method of seagulls, comprehensively considers the optimal position of the seagull in this iteration, different position update modes, the average position of other seagulls in the population, the probability value of the global leader and other factors to update the position of the seagull, thereby increasing the search range of the algorithm and enhancing the adaptability of the algorithm.

[0109] S6: Calculate the fitness value.

[0110] fitness(t)=F f (P s (t+1))

[0111] In the formula, F f (·) is the fitness function when calculating the fitness value;

[0112] S7: Record information, record the best seagull in the iteration.

[0113] S8: For the optimal seagull, bidirectional sine mutation is performed dimension by dimension, which enables the algorithm to jump out of the local optimal solution in the later stage. For dimension j, the sine chaos value is first calculated according to the current number of iterations, and the positive and negative directions are switched with equal probability.

[0114] sin Value = sin(πx0)

[0115]

[0116] In the formula, rand is a random number between 0 and 1; x0 is the iteration sequence value;

[0117] Perform mutation perturbation on the optimal position:

[0118] P bs(j) (t+1)′=P bs(j) (t+1)+SinValue×P bs(j) (t+1)

[0119] Where: P bs(j) (t+1) represents the optimal position P of the t+1th iteration bs The jth dimension of (t+1);

[0120] Greedy Update:

[0121]

[0122] After each dimension has been mutated, stop mutation.

[0123] S9: Record information, record the best seagull in the iteration.

[0124] S10: Repeat steps S5 to S9. When the maximum number of iterations Miter is reached, the algorithm stops and the optimal path result is output.

[0125] In this embodiment:

[0126] Using MATLAB as the simulation platform, assuming that a 20×20 grid map is constructed, with the shortest moving distance as the goal, the SOA method and ISOA method are analyzed. The parameters in the SOA algorithm are:

[0127] N = 50, Maxiter = 200, LB = 1, UB = 20; the parameters of the ISOA algorithm are: N = 50, Maxiter = 200, LB = 1, UB = 20. The simulation environment and the movement paths obtained by the two methods are shown in the figure.

[0128] Figure 2 As shown, Figure 3 is the iterative process curve. Table 1 is the comparison of the data results of the two algorithms.

[0129] Table 1. Comparison of algorithm path results

[0130] algorithm Path length SOA 36.9706 ISOA 32.1421

[0131] from Figure 2 It can be intuitively found that the moving path obtained by SOA is longer and more circuitous than that of ISOA, while the path obtained by ISOA is more reasonable. Figure 2 and Figure 3 From the results in , we can see that when the SOA algorithm is used, the algorithm converges slowly; when the ISOA algorithm is used, the convergence speed is faster and a better path can be found faster. It can be seen that the ISOA algorithm designed in this paper has a faster convergence speed and convergence accuracy. The simulation results show that under a variety of identical environments, the ISOA algorithm has a stronger search capability and obtains a better mobile path, verifying the effectiveness of the algorithm.

[0132] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for unmanned vehicle path planning based on drone perception, characterized in that: The following steps are involved: A grid map of the ground environment is established based on the perception system and positioning navigation system carried by the drone, and corrections are made based on environmental information; Determine the starting point of path planning and the objective function of unmanned vehicle path planning with the shortest moving path, or the shortest time consumption, or the least energy consumption as constraints, and update the position on the corrected grid map through the improved seagull optimization algorithm to determine the optimal seagull position; wherein, the improved seagull optimization algorithm introduces the position update mechanism of the transient search optimization algorithm and the spider monkey optimization algorithm into the position update method of the original seagull optimization algorithm to improve the seagull position update method, and comprehensively considers the optimal position of the seagull in this iteration, different position update modes, the average position of other seagulls in the population, and the global leader probability value. Factors update the seagull position; The optimal seagull position is updated in sequence according to the preset maximum number of iterations to determine the optimal path planning result.

2. The unmanned vehicle path planning method based on drone perception according to claim 1 is characterized in that: The optimal position update by the improved seagull optimization algorithm comprises the following steps: Set the size of the seagull population, the maximum number of iterations, and the upper and lower bounds of the seagull search; Introduce Gaussian mapping to initialize the position of the seagull population; Simulate the migration and attack behaviors of seagulls, and introduce the position update mechanism of transient search optimization algorithm and spider monkey optimization algorithm to improve the seagull position update method, perform position update, and record the optimal seagull position in the iteration; The optimal seagull position is further updated through bidirectional sine mutation in each dimension, and the optimal position in the iteration is recorded; The optimal position is updated in sequence according to the preset number of iterations, and the optimal path result is output.

3. The unmanned vehicle path planning method based on unmanned aerial vehicle perception according to claim 2 is characterized in that: The Gaussian mapping initializes the seagull population position, including the following steps: Determine the population size N, the lower boundary LB and the upper boundary UB of the seagull search; Generate random number x through Gaussian mapping t : In the formula, mod(·) is the remainder function, x t+1 is the next random number; Use the generated Gaussian random numbers to initialize the seagull position: P s (t)=(UB-LB)×x t +LB。 4. The unmanned vehicle path planning method based on drone perception according to claim 2 is characterized in that: The method of introducing the position updating mechanism of the transient search optimization algorithm and the spider monkey optimization algorithm to improve the seagull position updating method and perform position updating includes the following steps: Simulate the migratory behavior of seagulls, including avoiding collisions, moving in the direction of the best position, and approaching the best position; To avoid collisions with other seagulls, the algorithm uses an additional variable A to calculate the new position of the seagull: C s (t)=A×P s (t) A=f c -(t×f c / Miter) Where: C s (t) is the new position that does not conflict with other seagulls, P s (t) is the current position of the seagull, t is the current iteration number, Miter is the maximum iteration number, and A is the movement behavior of the seagull in the given search space; f c is the control coefficient, and its value decreases from 2 to 0; After avoiding overlapping with other seagulls, the seagull will move in the direction of the best position: M s (t)=B×(P bs (t)-P s (t)) B=2×A 2 ×r d Where: M s (t) represents the direction of the optimal position, P bs (t) represents the best position of the tth iteration, B is a random number responsible for balancing global and local searches; r d is a random number in the range [0,1]; When the seagull moves to a position where it does not collide with other seagulls, it moves in the direction of the best position and reaches a new position: D s (t)=|C s (t)+M s (t)| Where: D s (t) is the distance the seagull moves to its new position; Simulating seagull attack behavior: When attacking prey, seagulls can continuously change the attack angle and speed through spiral motion. The spiral motion is expressed as: Where: r is the radius of each spiral; θ is a random angle value in the range [0, 2π]; u and v are related constants that define the shape of the spiral, both of which can be set to 1; e is the base of the natural logarithm; By introducing the transient search optimization algorithm and the spider monkey optimization algorithm, the improved seagull position update formula is as follows: Where: C t =k·z·λ3+1 T=2·z·λ2-z Among them, P s (t+1) is the updated position of the seagull at the t+1th iteration; P bs (t) represents the best position of the tth iteration; P s (t) is the current position of the seagull; α and β are random numbers between [0,1]; C t and T are random thermal resistance coefficients; z is the attenuation coefficient, which decreases from 2 to 0 as the number of iterations increases; k is a constant (k = 0, 1, 2…); λ1, λ2 and λ3 are random numbers in [0, 1]; P r1 (t), P r2 (t) and P r3 (t) represents three seagull individuals randomly selected at the tth iteration, r1≠r2≠r3; P avg (t) is P r1 (t), P r2 (t) and P r3 The average value of (t); p i is the global leader probability of the i-th seagull in the t-th iteration; fitness i is the fitness value of the i-th seagull; i is the maximum fitness value of the seagull group in the tth iteration; Calculate the fitness value: fitness(t)=F f (P s (t+1)) In the formula, F f (·) is the fitness function when calculating the fitness value; Record the best seagull in the iteration.

5. The unmanned vehicle path planning method based on unmanned aerial vehicle perception according to claim 4 is characterized in that: The method of further updating the optimal position by bidirectional sine mutation in each dimension includes the following steps: For dimension j, the sine chaos value is calculated according to the current number of iterations, and the positive and negative directions are switched with equal probability: sin Value = sin(πx0) In the formula, rand is a random number between 0 and 1; x0 is the iteration sequence value; Perform mutation perturbation on the optimal position: P bs(j) (t+1)′=P bs(j) (t+1)+SinValue×P bs(j) (t+1) Where: P bs(j) (t+1) represents the optimal position P of the t+1th iteration bs The jth dimension of (t+1); Greedy Update: After each dimension has been mutated, stop mutation.

6. A path planning system for unmanned vehicles based on drone perception, characterized in that: The system comprises: processor; a memory having stored thereon a computer program executable on the processor; Wherein, when the computer program is executed by the processor, the steps of the unmanned vehicle path planning method based on drone perception as described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a data processing program, and when the data processing program is executed by the processor, the steps of the unmanned vehicle path planning method based on drone perception as described in any one of claims 1 to 5 are implemented.

Images