Underground operation robot path planning method based on improved ant colony algorithm

Abstract

The invention relates to a downhole operation robot path planning method based on an improved ant colony algorithm, and the method comprises the steps: carrying out the planning of the path of a downhole operation robot through employing the ant colony algorithm, and obtaining an optimal planning path; according to the method, the ant colony algorithm is improved, and the convergence speed and the path performance of the algorithm are improved by improving the initial pheromone concentration and optimizing path selection; and the feasibility and stability of the trajectory are further improved through trajectory smoothing processing. According to the method, the planning success rate of the robot in a dynamic obstacle scene is improved, and efficient and stable technical support is provided for path planning of the underground coal mine inspection robot.

Description

Technical Field

[0001] The present application relates to the field of safety monitoring and intelligent equipment, and specifically to a path planning method for an underground operation robot based on an improved ant colony algorithm. Background Art

[0002] Coal mines are mainly mined underground, and the environment is complex and very dangerous. Traditional manual inspection and operation methods are high-risk and inefficient. Intelligent and unmanned operations have become important directions for safe and efficient mining in coal mines. Robot inspection technology has been listed as a key research and development area due to its autonomy, collaboration, and anti-interference capabilities. The path planning of underground coal mine inspection robots is mainly aimed at the trajectory planning needs in complex and restricted environments (such as narrow tunnels, dense obstacles, gas monitoring points, and dynamic equipment areas). It solves the production monitoring problems of inspection robots in the limited space and complex working conditions of underground coal mine working faces, and plays a vital role in the application of robots in safe production in underground coal mines. The robot path planning methods in the existing technology have the problems of slow algorithm convergence speed and poor reliability of the planned path. Summary of the Invention

[0003] In order to overcome at least one deficiency in the prior art, the present application provides a path planning method for an underground operation robot based on an improved ant colony algorithm.

[0004] In a first aspect, a path planning method for an underground operation robot based on an improved ant colony algorithm is provided, comprising:

[0005] Ant colony algorithm is used to plan the path of the underground operation robot and obtain the optimal planned path;

[0006] The ant colony algorithm involves initializing the pheromone at each point in the spatial grid map using the following formula:

[0007]

[0008] Among them, ρ (x,y,z) is the pheromone of any point (x, y, z), d (x,y,z) is the distance from point (x, y, z) to the end point of the path, and k is a coefficient related to the map size;

[0009] The ant colony algorithm also includes calculating the fitness of each path using the following formula:

[0010] f n =α1s n +α2θ n , n∈[1,N]

[0011] Among them, f n is the fitness of path n, α1 and α2 are the magnitude coefficients used to limit the distance term and the average steering angle term, sn is the total distance of path n, θ n is the average turning angle of path n, and N is the number of paths.

[0012] In one embodiment, the average turning angle θ of path n is n , determined in the following way:

[0013] Calculate the steering angle θ when the robot passes each turning point while running along path n, using the following formula:

[0014]

[0015] Among them, arcsin is the inverse sine function, is the vector from the starting point A to the turning point B, is the vector from the starting point A to the end point C, is the vector from the turning point B to the end point C; d (C,AB) From the end point C to The vertical distance, d (B,C) is the straight-line distance from the turning point B to the end point C;

[0016] Find the mean of the steering angles θ of all turning points on path n and get the average steering angle θ of path n n .

[0017] In one embodiment, the method further comprises:

[0018] The optimal planning path is smoothed using cubic spline interpolation.

[0019] In a second aspect, a path planning device for an underground working robot based on an improved ant colony algorithm is provided, which is used to implement the above-mentioned path planning method for an underground working robot based on an improved ant colony algorithm.

[0020] In a third aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned underground operation robot path planning method based on the improved ant colony algorithm.

[0021] In a fourth aspect, a computer program product is provided, comprising a computer program / instruction. When the computer program / instruction is executed by a processor, the above-mentioned path planning method for an underground operation robot based on the improved ant colony algorithm is implemented.

[0022] Compared with the existing technology, the present application has the following beneficial effects: the path planning method of the underground working robot based on the improved ant colony algorithm of the present application can effectively avoid obstacles and find a safe path from the starting point to the end point; by improving the initial pheromone concentration and optimizing the path selection, the convergence speed and path performance of the algorithm are improved; the trajectory smoothing processing further improves the feasibility and stability of the trajectory; the present application improves the planning success rate of the robot in dynamic obstacle scenes, and provides efficient and stable technical support for the path planning of underground inspection robots in coal mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The present application may be better understood by referring to the following description in conjunction with the accompanying drawings, which together with the following detailed description are incorporated into and form a part of this specification. In the drawings:

[0024] Figure 1 A comparison of robot trajectories using the unmodified ant colony algorithm and the improved ant colony algorithm is shown;

[0025] Figure 2 The robot trajectory after trajectory smoothing using cubic spline interpolation is shown. DETAILED DESCRIPTION

[0026] Exemplary embodiments of the present application are described below with reference to the accompanying drawings. For the sake of clarity and conciseness, not all features of actual embodiments are described in this specification. However, it should be understood that in the process of developing any such actual embodiment, many implementation-specific decisions may be made to achieve the developer's specific goals, and these decisions may vary from one implementation to another.

[0027] It is also necessary to explain here that, in order to avoid obscuring the present application due to unnecessary details, the accompanying drawings only show the device structure closely related to the solution according to the present application, while other details that are not closely related to the present application are omitted.

[0028] It should be understood that the present application is not limited to the described embodiments due to the following description with reference to the accompanying drawings. In this document, where feasible, the embodiments may be combined with each other, features between different embodiments may be replaced or borrowed, and one or more features may be omitted in one embodiment.

[0029] An embodiment of the present application provides a path planning method for an underground working robot based on an improved ant colony algorithm, comprising: using the ant colony algorithm to plan the path of the underground working robot to obtain an optimal planned path.

[0030] The ant colony algorithm (ACO) is abstracted from the foraging process of ants. Starting from a burrow, each ant releases pheromones along its path. These pheromones evaporate over time, and the probability that subsequent ants will choose that path is proportional to the pheromone concentration. The shorter a path, the shorter the time it takes for ants to reach their destination and return, and the less pheromone evaporates, leading to a greater number of ants traversing that path. This positive feedback mechanism enables the ant colony to find the shortest path to food and avoid obstacles without requiring strong sensory capabilities. The ACO explores pheromones in every direction in three-dimensional space, selects the most suitable direction, increases the pheromone concentration at that point, and decays it over time, allowing subsequent ants to choose the path with the highest concentration. Ultimately, the shortest feasible path between the starting and ending points is determined. The ant colony algorithm (ACO) process begins by initializing pheromones across the entire map and then exploring paths. Each time a new point is selected, the optimal point is sought based on a heuristic value function. Upon successfully reaching the destination, the path's performance is evaluated, namely, its fitness is calculated. Based on this performance parameter, the pheromones at the points along the path are enhanced, while those at other points are attenuated. The algorithm then proceeds to the next iteration until the end of the iteration. The algorithm is an iterative optimization process, continuously adjusting the pheromone concentration of the optimal path to ensure that the next explored path meets expectations.

[0031] The ant colony algorithm selects a path based on pheromone concentration. In this embodiment, in order to accelerate convergence during the path planning process, different pheromone concentrations are assigned to different points in the map when initializing the pheromone concentration. A concentration sphere is created with the end point as the center. The farther from the center, the lower the concentration. This can accelerate convergence. Therefore, the pheromone concentration of each point in the spatial grid map is initialized using the following formula:

[0032]

[0033] Among them, ρ (x,y,z) is the pheromone of any point (x, y, z), d (x,y,z) is the distance from the point (x, y, z) to the end of the path, and k is a coefficient related to the map size. Here, k is a constant whose value depends on the specific problem, the scale of the map, the location of the target point, and the performance requirements of the algorithm. For larger maps with greater distances between points, a larger k value can enhance global search capabilities, but this can slow convergence.

[0034] After experiments, the uninitialized ant colony algorithm took 3.3258 seconds, and the initialized ant colony algorithm took 2.8976 seconds, saving 12.88% of the time.

[0035] The ant colony algorithm also includes calculating the fitness of each path. The fitness of the existing ant colony algorithm when selecting a path is f n The calculation formula cannot fully meet the requirements. During the operation of the robot, it is necessary to select a path with smaller angle changes when selecting a path, which is more conducive to shortening the robot's operation path, reducing energy loss and path reliability.

[0036] Assume that the robot is at the starting point A (the origin of the coordinate system) at the initial moment and needs to turn after passing through point B to reach the end point C. To calculate the angle θ that the robot needs to turn when running along the prescribed path at point B, you can use vector knowledge to solve this problem. The three vectors: , use the pheromone attenuation formula to calculate the turning angle θ when the robot passes each turning point when running along path n:

[0037]

[0038] Among them, arcsin is the inverse sine function, is the vector from the starting point A to the turning point B, is the vector from the starting point A to the end point C, is the vector from the turning point B to the end point C; d (C,AB) From the end point C to The vertical distance, d (B,C) is the straight-line distance from the turning point B to the end point C;

[0039] Then, find the mean of the steering angles θ of all turning points on path n and get the average steering angle θ of path n. n .

[0040] In this embodiment, the average steering angle of path n is calculated and weighted into the fitness calculation formula to obtain a trajectory with a smaller steering angle. Therefore, the fitness of each path is calculated using the following formula:

[0041] f n =α1s n +α2θ n , n∈[1,N]

[0042] Among them, f n is the fitness of path n, α1 and α2 are the magnitude coefficients used to limit the distance term and the average steering angle term, s n is the total distance of path n, θ n is the average turning angle of path n, and N is the number of paths.

[0043] Furthermore, the path planning method for an underground operation robot based on the improved ant colony algorithm also includes: using a cubic spline interpolation method to smooth the trajectory of the optimal planned path.

[0044] Here, cubic spline interpolation is used for trajectory smoothing. The cubic spline interpolation method fits a set of data points into a smooth curve, which is composed of a set of cubic polynomials. Each polynomial only works between two adjacent data points and satisfies the continuity of the first-order and second-order derivatives at each data point, making the shape of the curve smoother. Therefore, the cubic spline interpolation method generates a smoother curve than simple interpolation methods (such as linear interpolation). In practical applications, it can reduce unnecessary speed fluctuations, reduce energy consumption, avoid sudden starts and stops, and better meet the requirements of actual application scenarios.

[0045] In order to further verify the effectiveness of the underground operation robot path planning method based on the improved ant colony algorithm in this application, an experimental analysis was carried out. Figure 1 The comparison of robot trajectories of the unimproved ant colony algorithm and the improved ant colony algorithm is shown. Figure 2 The robot trajectory after trajectory smoothing using cubic spline interpolation is shown.

[0046] According to the experimental results, the underground operation robot path planning method based on the improved ant colony algorithm of the present application accelerates the convergence speed of the algorithm by optimizing the initial pheromone concentration. The results show that the algorithm time after initialization is reduced from 3.3258 seconds to 2.8976 seconds, saving 12.88% of the time; the fitness calculation formula is improved, and the constraint of the average steering angle of the path is added, so that the planned path steering angle is smaller, which is more suitable for the stable operation of the robot, and the cubic spline interpolation method is used to smooth the trajectory, which improves the smoothness of the trajectory and reduces the speed fluctuation.

[0047] Adopting the same inventive concept as the underground working robot path planning method based on the improved ant colony algorithm, this embodiment also provides a corresponding underground working robot path planning device based on the improved ant colony algorithm, which is used to implement the above-mentioned underground working robot path planning method based on the improved ant colony algorithm.

[0048] The underground working robot path planning device based on the improved ant colony algorithm of this embodiment has the same inventive concept as the underground working robot path planning method based on the improved ant colony algorithm mentioned above. Therefore, the specific implementation method of the device can be seen in the embodiment part of the underground working robot path planning method based on the improved ant colony algorithm in the above text, and its technical effect corresponds to the technical effect of the above method, which will not be repeated here.

[0049] An embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned underground operation robot path planning method based on the improved ant colony algorithm.

[0050] An embodiment of the present application provides a computer program product, including a computer program / instruction. When the computer program / instruction is executed by a processor, it implements the above-mentioned underground operation robot path planning method based on the improved ant colony algorithm.

[0051] The above descriptions are merely examples of various embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A path planning method for an underground operation robot based on an improved ant colony algorithm, characterized in that: include: Ant colony algorithm is used to plan the path of the underground operation robot and obtain the optimal planned path; The ant colony algorithm involves initializing the pheromone of each point in the spatial grid map using the following formula: Among them, ρ (x，y，z) is the pheromone at any point (x, y, z), d (x，y，z) is the distance from point (x, y, z) to the end point of the path, and k is a coefficient related to the map size; The ant colony algorithm also includes calculating the fitness of each path using the following formula: f n =α1s n +α2θ n ,n∈[1,N] Among them, f n is the fitness of path n, α1 and α2 are the magnitude coefficients used to limit the distance term and the average steering angle term, s n is the total distance of path n, θ n is the average turning angle of path n, and N is the number of paths.

2. The method according to claim 1, wherein The average turning angle θ of the path n n , determined in the following way: Calculate the steering angle θ when the robot passes each turning point while running along path n, using the following formula: Among them, arcsin is the inverse sine function, is the vector from the starting point A to the turning point B, is the vector from the starting point A to the end point C, is the vector from the turning point B to the end point C; d (C，AB) From the end point C to The vertical distance, d (B，C) is the straight-line distance from the turning point B to the end point C; Find the mean of the steering angles θ of all turning points on path n and get the average steering angle θ of path n n .

3. The method according to claim 1, wherein The method further comprises: The optimal planned path is smoothed by using a cubic spline interpolation method.

4. A path planning device for an underground operation robot based on an improved ant colony algorithm, characterized in that: Used to implement the underground operation robot path planning method based on the improved ant colony algorithm as described in any one of claims 1-3.

5. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it implements the underground operation robot path planning method based on the improved ant colony algorithm according to any one of claims 1 to 3.

6. A computer program product, characterized in that The method comprises a computer program / instruction, which, when executed by a processor, implements the path planning method for an underground operation robot based on an improved ant colony algorithm as described in any one of claims 1 to 3.

Images