Unmanned aerial vehicle path planning method and system based on FLC-APF-RRT*

By introducing fuzzy controllers and artificial potential field methods in the UAV path planning, dynamically adjusting the influence of new node generation, solving the problem of inefficiency of existing algorithms in high-dimensional space, achieving more efficient and reliable Path planning.

CN119088051AActive Publication Date: 2024-12-06LINGNAN NORMAL UNIV
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411130616.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-12-06
Estimated Expiration
2044-08-16

AI Technical Summary

Technical Problem

The existing drone path planning algorithms have problems such as poor performance, long time-consuming, slow convergence speed, relying on precise environmental modeling and easy to fall into local optimal solutions, and it is difficult to effectively apply to path planning in high-dimensional space.

Method used

A UAV path planning method based on FLC-APF-RRT* is designed. The growth stage of the random tree is divided by the fuzzy controller output target bias threshold, and combined with the artificial potential field method, an improved new node generation method is proposed. Assign the forces of random points and artificial potential fields to optimize the average path length, search time and number of nodes of path planning.

Benefits of technology

It significantly improves the efficiency and quality of path planning, reduces path redundant nodes and search time, improves search success rate, and is suitable for path planning in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088051A_ABST
    Figure CN119088051A_ABST
Patent Text Reader

Abstract

The invention relates to an unmanned aerial vehicle path planning method based on FLC-APF-RRT *. The method comprises the following specific steps: presetting a target deviation threshold value Pbias and a random generation probability P, and dividing random tree expansion into two stages of exploration and convergence according to the size relationship between the Pbias and the P; designing a fuzzy controller PbiasFuzzy, and dynamically outputting a target deviation threshold value according to environmental factors; an improved new node generation method is provided in combination with an artificial potential field method and a target deviation threshold. According to the method, the advantage that the fuzzy controller does not need accurate modeling and the environmental factors of unmanned aerial vehicle path planning are fully considered, the running speed, the path length and the node number of unmanned aerial vehicle path planning are optimized, and a reference is provided for searching an expansion method of a random tree. Figure 1 is a method flow chart involved in the invention.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle technology, and in particular to an unmanned aerial vehicle path planning method and system based on FLC-APF-RRT*. Background Art

[0002] Path planning is one of the key issues in UAV mission planning. In recent years, a large number of studies have been devoted to finding faster and more efficient path planning methods. The UAV path planning problem can be described as finding a collision-free feasible path from the initial position to the target position that meets the performance requirements of the UAV under certain constraints. Existing traditional algorithms have the disadvantages of poor performance and long time consumption. Existing swarm intelligence algorithms generally have problems such as slow convergence speed, reliance on accurate modeling of the environment, and easy to fall into local optimal solutions, making them difficult to apply to path planning in high-dimensional space.

[0003] To this end, the present invention analyzes a fuzzy controller that has the advantage of not requiring precise modeling, and provides a design method for a fuzzy controller. The growth stage of the random tree is divided according to the output dynamic target bias threshold, and on this basis, the present invention designs an improved new node generation method by combining the artificial potential field method with the target bias threshold. The present invention fully considers the distribution ratio of the artificial potential field force and the new node effect in the new node generation process, guides the generation of new nodes according to the environment through the target bias threshold, and well optimizes the average path length, search time and number of nodes of the path planning, providing a reference for the UAV path planning algorithm.

[0004] In addition, on the one hand, there are differences in understanding among those skilled in the art; on the other hand, the applicant studied a large number of documents and patents when making the present invention, but due to space limitations, not all details and contents are listed in detail. However, this does not mean that the present invention does not have the characteristics of these prior arts. On the contrary, the present invention already has all the characteristics of the prior art, and the applicant reserves the right to add relevant prior art to the background technology. Summary of the invention

[0005] The purpose of the present invention is to provide a UAV path planning method based on FLC-APF-RRT*. Considering the problems of accurate obstacle modeling and long search time in the existing algorithm, the present invention designs a UAV path planning method based on FLC-APF-RRT* through an improved new node generation method. The improved new node generation method comprises the following steps: designing a fuzzy controller to output a target deviation threshold, and dividing the sampling stage according to the target deviation threshold.

[0006] To achieve the purpose of the above invention, the UAV path planning method based on FLC-APF-RRT* involved in the present invention comprises the following steps:

[0007] (1) Preset a target deviation threshold P bias , randomly generate probability P, according to P bias The relationship between the size of P and random tree expansion is divided into two stages: exploration and convergence;

[0008] (2) Design a fuzzy controller PbiasFuzzy to dynamically output the target bias threshold according to environmental factors;

[0009] (3) Combining the artificial potential field method with the target bias threshold, an improved method for generating new nodes is proposed.

[0010] According to a preferred embodiment, a target deviation threshold P is preset. bias , randomly generate probability P, according to P bias The relationship between the size of and P is that the random tree expansion is divided into two stages: exploration and convergence.

[0011] Artificial Potential Field (APF) is a path planning method that drives a robot or vehicle to avoid obstacles and reach the target by introducing a potential field in the environment. Fuzzy Logic Control (FLC) is a fuzzy logic system that is used to process fuzzy information and uncertainty and is often used in control systems. The Rapidly-exploring Random Tree (RRT*) algorithm can find the optimal path faster and better, but the search efficiency is still not high in complex constrained environments. There are a large number of invalid area searches and redundant nodes. Therefore, the sampling phase is divided into two phases: exploration and convergence. The specific steps include: presetting a target deviation threshold P bias , a probability value P is randomly generated by uniform probability distribution, and the random tree expansion is divided into two stages: exploration stage ( Figure 2 ) and convergence phase ( Figure 3 ).

[0012] When P ≥ P bias When the random tree is in the exploration phase, it randomly generates sampling points X rand , perform random tree horizontal expansion; when P <P bias When , the random tree is in the convergence stage, the direction of the sampling point is the direction of the target point, and the next sampling point is X nearest With X goal The sampling position of the extended line is step. The new node (X new ) is extended as shown in formula (1):

[0013]

[0014] Among them, X' goal For Xnearest Point to X goal The point on the extension line of X that is step away; rand A random point for the new extension.

[0015] According to a preferred embodiment, a fuzzy controller PbiasFuzzy is designed to dynamically output the target bias threshold according to environmental factors. The fuzzy controller has two inputs and one output. The first input parameter is the obstacle density near the sampling point, the second input parameter is the Euclidean distance from the sampling point to the target point, and the output value is the target bias threshold. The obstacle density ObsDensity and the distance from the sampling point to the target point GoalDist are configured with the same subset {NL, NM, ZE, PM, PL}, and their value range after normalization is [0, 1] and [0, 10]. Output the target bias threshold P bias The output range of is [0,0.7], and the fuzzy subset is {NL,NM,NS,ZE,PS,PM,PL}. The purpose of the above settings is to divide P more finely. bias The output range is used to reduce the error. Table 1 shows the meaning of the symbols of the membership function, the input ObsDensity, GoalDist and the output P bias The membership functions are as follows: Figure 4 As shown (from top to bottom). The fuzzy controller rule set designed based on experience is shown in Table 2. The fuzzy controller output P designed based on this fuzzy rule set bias Fuzzy values ​​such as Figure 5 shown.

[0016] The present invention combines the artificial potential field method with the target bias threshold to propose an improved new node generation method. The new node generation method of the traditional APF-RRT* algorithm only considers the role of the artificial potential field and random points, but does not consider the proportion of the influence of these two factors on the new nodes. This makes the new node generation method of the traditional APF-RRT* algorithm lack of adaptability to the environment and easy to fall into local optimality. bias As influencing factors, random points and artificial potential fields that have an impact on new nodes are dynamically allocated. The configuration method of improved new nodes is shown in formula (2):

[0017]

[0018] Among them, X' goal For X nearest With X goal Extend the line to a point with a distance of step, ||X rand -X nearest || represents X rand With X nearest The Euclidean distance between them. att is gravity, F repis the repulsive force, which is defined as shown in equations (3) and (4):

[0019]

[0020]

[0021] Among them, K a represents the gravitational constant; X nearest Indicates the current node of the random tree expansion; X goal is the target point; ρ(X goal ,X nearest ) is a vector with a length of X nearest To X goal The Euclidean distance in the direction of X nearest Point to X goal ; K r represents the repulsive force constant; X obstacle represents the position of the obstacle; ρ(X obstacle ,X nearest ) is a vector with a length of X obstacle To X nearest The Euclidean distance in the direction of X obstacle Point to X nearest ; ρ0 is the range of action of the repulsive field;

[0022]

[0023] From the above, we can see that P bias It has an obvious guiding role for new nodes. bias The smaller it is, the more complex the environment is, the more the random tree is in the exploration stage, and the new node generation process is more affected by random points and less affected by the artificial potential field; bias The larger the value is, the more likely the node is in a simpler environment. The random tree tends to converge. The new node is affected by the artificial potential field more, and the influence of random points is reduced. bias The new node extension position is corrected to increase the flexibility and adaptability of the algorithm search. The improved new node generation principle is as follows: Figure 6 shown.

[0024] The UAV path planning algorithm process based on the FLC-APF-RRT* algorithm is as follows Figure 7 As shown, the process steps are as follows:

[0025] The algorithm performs N iterations;

[0026] Use numNodes to control the total number of generated nodes. If this limit is exceeded, the planning is considered a failure.

[0027] In the iterative process, the obstacle density ObsDensity and the distance GoalDist from the sampling point to the target point are input into the fuzzy controller PbiasFuzzy to obtain the output Pbias. If the uniform probability distribution randomly generates a probability value rand(1) less than Pbias, the random point is set as the target point; otherwise, a new random point X is sampled within the map range. rand .

[0028] Determine the target point (new random point X rand Or a random point), find the node X closest to the random point in the path nearest , and then use the improved new node generation method proposed by the present invention to generate a new node X new [Generated by formula (2)], if the connection between the new node and the adjacent nodes does not collide with obstacles, the new node is added to the random tree, and the new node is rewired and the parent node is reselected, and the result is updated to the random tree.

[0029] A UAV path planning system based on FLC-APF-RRT*, characterized in that the system is configured to: (1) preset a target deviation threshold P bias , randomly generate probability P, according to P bias and P, the random tree expansion is divided into two stages: exploration and convergence; (2) a fuzzy controller is designed to dynamically output the target bias threshold according to environmental factors; (3) an improved method for generating new nodes is proposed by combining the artificial potential field method with the target bias threshold.

[0030] The beneficial effects of the present invention relative to the prior art are:

[0031] Based on the characteristics of fuzzy controllers that do not require precise data modeling and are easy to implement, the present invention establishes an environmental target deviation threshold control method based on a fuzzy controller. Based on the artificial potential field method and the target deviation threshold, the present invention proposes an improved new node generation method. The present invention fully considers the advantages of fuzzy controllers that do not require precise modeling and the environmental factors of path planning, optimizes the running speed, path length and number of nodes of drone path planning, and provides a reference for the expansion method of searching random trees. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A flow chart of the method involved in this application;

[0033] Figure 2 This is a schematic diagram of the exploration phase;

[0034] Figure 3 It is a schematic diagram of the convergence stage;

[0035] Figure 4ObsDensity,GoalDist,P bias Membership function diagram of (from top to bottom);

[0036] Figure 5 P bias Fuzzy value;

[0037] Figure 6 Generate schematics for new and improved nodes;

[0038] Figure 7 is the algorithm flow chart;

[0039] Figure 8 There are two maps, the left one is the Figure 1 , the right picture is the ground Figure 2 ;

[0040] Fig. 9 For the Earth Figure 1 Parameter comparison chart of each algorithm;

[0041] Fig.10 For the Earth Figure 1 Comparison chart of various algorithm paths;

[0042] Fig.11 For the Earth Figure 2 Parameter comparison chart of each algorithm;

[0043] Fig.12 For the Earth Figure 2 Comparison chart of various algorithm paths. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. For ordinary technicians in this field, the specific meanings of the terms in the present invention can be understood according to specific circumstances.

[0045] This embodiment provides a UAV path planning method based on FLC-APF-RRT*. To verify the feasibility, applicability and effectiveness of the present invention, Matlab was used to build a map, and the average path length, average time, average number of nodes and success rate of the improved algorithm and the existing algorithm under different map environments were compared and analyzed.

[0046] The present invention simulates the narrow road environment and the dense environment in the complex environment respectively. The two initial maps are Figure 8 .

[0047] The initial parameters are set as follows: the maximum number of iterations is set to 500, the maximum number of nodes in a narrow channel environment is set to 5000, the maximum number of nodes in a dense environment is set to 3000, the attraction factor and the repulsion factor are both set to 1, and the step size is fixed to 25; the map size of all experimental environments is standardized to [1000,1000], and the starting and end points are defined as [0,0] and [999,999], respectively.

[0048] (1) Experimental comparison in narrow channel environment

[0049] In order to verify the reliability of the method in the narrow channel environment, Figure 1 Two narrow channels are set in the middle, and the channel widths are 35 units and 50 units respectively. In order to ensure the reliability of the experiment and reduce the impact of accidental errors on the experiment, the method of the present invention is repeated 50 times, and each experiment is repeated 500 times.

[0050] Table 3 is a summary of the average path length, average time, average number of nodes, and success rate of the four algorithms. The target bias thresholds for APF-RRT*, IRRT*, and RRT-connect are all set to the commonly used 0.3.

[0051] The experimental results are shown in Table 3 and Fig. 9 As shown in the figure, compared with APF-RRT*, the method of the present invention reduces the average path length from 1939.02 to 1905.62, a decrease of 1.72%, which significantly improves the path quality; the average number of nodes is reduced by 7.75%, effectively eliminating redundant nodes in the path; the average time is reduced by 39.79%, greatly improving the search efficiency, and the search success rate is also increased by 4.33%, further verifying the superiority of FLC-APF-RRT*.

[0052] Compared with IRRT*, the method of the present invention shortened the average path length by 1.46%, the average time by 29.05%, the average number of nodes by 39.91%, and the search success rate by 2.76%. Compared with the RRT-connect algorithm, the method of the present invention reduced the average path length and average time by 18.69% and 14.5% respectively, and the success rate was also improved by 8.91%. Although the RRT-connect algorithm has a slight advantage in the average number of nodes, the present invention significantly improves the path quality and success rate and significantly reduces the running time through the path finding strategy and new node generation method.

[0053] In summary, the method of the present invention is generally superior to the other three algorithms in terms of average path length, average time, average number of nodes and success rate, and provides a more efficient and reliable method for path planning.

[0054] Fig.10The proposed method is compared with three comparison algorithms. Figure 1 The red path represents the feasible path found, and the blue one represents the generated random tree. Fig.10 It can be seen that the method of the present invention has a certain degree of guidance in the path search process. When it is close to the end point and there are few obstacles, it directly moves to the end point, avoiding unnecessary random expansion; near the starting point or close to narrow obstacles, it increases the intensity of random exploration to ensure that a feasible path can be searched. It can be seen from the comparison of the four algorithms that the path of the method of the present invention is more concise and smooth.

[0055] (2) Experimental comparison in dense environment

[0056] In order to verify the reliability of the method in the dense environment, Figure 2 50 dense obstacles are randomly distributed in the experiment, and each experiment is still repeated for 500 times. The experimental data are recorded after the iteration. Table 4 records the average data of 50 repeated experiments. The target bias threshold of APF-RRT*, IRRT* and RRT-connect is still 0.3.

[0057] From Table 4 and Fig.11 It can be seen that the method of the present invention performs well under dense maps. Compared with the APF-RRT* algorithm, the IRRT* algorithm, and the RRT-connect algorithm, the method of the present invention shortens the average path length by 3.59%, 5.29%, and 1.98%. At the time level, even compared with the RRT-connect algorithm that performs bidirectional expansion at the same time, the method of the present invention still shows high efficiency, and the time consumption is reduced by 42.86%; compared with APF-RRT* and IRRT*, the time is reduced by 39.62% and 54.29%. In addition, compared with APF-RRT* and IRRT*, the method of the present invention reduces the average number of nodes by 39.85% and 63.63%, indicating that the method of the present invention expands fewer invalid nodes and occupies less memory, but due to the dual-tree expansion method of RRT-connect, its number of nodes is slightly better than the method of the present invention. In terms of success rate, compared with RRT-connect, the success rate of the method of the present invention has increased by 2.37%. The above results prove the stability and reliability of the method of the present invention in complex environments.

[0058] Fig.12 (a), (b), (c), and (d) show the four algorithms in the local Figure 2Path comparison chart below. It can be observed that the method of the present invention is more purposeful when expanding the random tree, and effectively reduces redundant nodes and random tree bifurcations. However, in areas with dense obstacle density and close to the starting point, the algorithm will explore more roads. Once it finds that the quality of the new path is not as good as the original quality, it will quickly adjust the strategy. The algorithm has a good balance between the path exploration stage and the convergence stage. Compared with the APF-RRT*, IRRT* and RRT-connect algorithms, the path generated by the method of the present invention is smoother and of higher quality, ultimately achieving a better path planning effect.

[0059] Table 1 Symbols and meanings

[0060]

[0061] Table 2 Fuzzy rule sets

[0062]

[0063]

[0064] Table 3 Figure 1 Comparison of algorithm performance

[0065]

[0066] Table 4 Figure 2 Comparison of algorithm performance

[0067]

[0068] It should be noted that the above-mentioned specific embodiments are exemplary, and those skilled in the art can come up with various solutions inspired by the disclosure of the present invention, and these solutions also belong to the disclosure scope of the present invention and fall within the protection scope of the present invention. Those skilled in the art should understand that the present invention specification and its drawings are illustrative and do not constitute a limitation on the claims. The scope of protection of the present invention is defined by the claims and their equivalents. The present invention specification contains multiple inventive concepts, such as "according to a preferred embodiment" means that the corresponding paragraph discloses an independent concept, and the applicant reserves the right to file a divisional application based on each inventive concept. Throughout the text, the features guided by "according to a preferred embodiment" are only an optional method and should not be understood as a must-have setting. Therefore, the applicant reserves the right to abandon or delete the relevant preferred features at any time.

Claims

1. A UAV path planning method based on FLC-APF-RRT*, characterized in that: The steps include: (1) Preset a target deviation threshold P bias , randomly generate probability P, according to P bias The relationship between the size of P and random tree expansion is divided into two stages: exploration and convergence; (2) Design a fuzzy controller PbiasFuzzy to dynamically output the target bias threshold according to environmental factors; (3) Combining the artificial potential field method with the target bias threshold, an improved method for generating new nodes is proposed.

2. The UAV path planning method according to claim 1, characterized in that: When P <P bias When , the random tree is in the convergence stage, the direction of the sampling point is the direction of the target point, and the next sampling point is X nearest With X goal The sampling position on the extended line is step away.

3. The UAV path planning method according to claim 2, characterized in that: When P ≥ P bias When the random tree is in the exploration phase, it randomly generates sampling points X rand , and perform horizontal expansion of random trees.

4. The UAV path planning method according to claim 3, characterized in that: New Node X new The extended definition is shown in formula (1): Among them, X′ goal For X nearest Point to X goal The point on the extension line of X that is step away, rand A random point for the new extension.

5. The UAV path planning method according to claim 4, characterized in that: The fuzzy controller has two inputs and one output. The first input parameter is the obstacle density near the sampling point, the second input parameter is the Euclidean distance from the sampling point to the target point, and the output value is the target deviation threshold. The obstacle density ObsDensity and the distance from the sampling point to the target point GoalDist are configured with the same subset {NL, NM, ZE, PM, PL}. After normalization, the value range is [0, 1] and [0, 10]. The output target deviation threshold P bias The output range is [0,0.7] and the fuzzy subsets are {NL,NM,NS,ZE,PS,PM,PL}.

6. The UAV path planning method according to claim 5, characterized in that: P bias As influencing factors, random points and artificial potential fields that have an impact on new nodes are dynamically allocated, where the configuration method of improving new nodes is shown in formula (2): Among them, X' goal For X nearest With X goal Extend the line to a point with a distance of step, ||X rand -X nearest || represents X rand With X nearest The Euclidean distance between .

7. The UAV path planning method according to claim 6, characterized in that: The F att is the gravitational force, which is defined as shown in formula (3): U att represents the gravitational function; K a represents the gravitational constant; X nearest represents the current node of the random tree expansion; ρ(X goal ,X nearest ) is a vector with a length of X nearest To X goal The Euclidean distance in the direction of X nearest Point to X goal .

8. The UAV path planning method according to claim 7, characterized in that: The F rep is the repulsive force, which is defined as shown in formula (4): X nearest Indicates the current node of the random tree expansion; X obstacle represents the position of the obstacle; ρ(X obstacle ,X nearest ) is a vector with a length of X obstacle To X nearest The Euclidean distance in the direction of X obstacle Point to X nearest ; ρ0 is the range of action of the repulsive field; 9. The UAV path planning method according to claim 8, characterized in that: The method comprises the following steps: Perform N iterations based on the FLC-APF-RRT* algorithm; Use numNodes to control the total number of generated nodes. If this limit is exceeded, the planning is considered a failure.

10. A UAV path planning system based on FLC-APF-RRT*, characterized in that: The system is configured to: (1) Preset a target deviation threshold P bias , randomly generate probability P, according to P bias The relationship between the size of P and random tree expansion is divided into two stages: exploration and convergence; (2) Design a fuzzy controller PbiasFuzzy to dynamically output the target bias threshold according to environmental factors; (3) Combining the artificial potential field method with the target bias threshold, an improved method for generating new nodes is proposed.

Citation Information

Patent Citations

  • Unmanned aerial vehicle flight path planning method based on PF-RRT* algorithm

    CN115167513A

  • Self-adaptive tangential obstacle avoidance path planning method and system

    CN116009530A

  • Remote puncture robot path planning method based on improved RRT algorithm

    CN116476058A

  • Track planning and control method based on tailstock type vertical unmanned aerial vehicle patrolling bomb

    CN116594421A

  • Mobile robot mixed path planning method based on improved A* algorithm and dynamic window method

    CN116795120A