Mobile robot path planning method used in building material unmanned detection laboratory

Abstract

A mobile robot path planning method used in a building material unmanned detection laboratory belongs to the field of path planning, and adopts a grid method to establish an environment map and a starting point and a target point of a mobile robot, and introduces a smooth function influenced by path turning times in an ant state transition formula. By introducing a target factor, heuristic information is improved, the directivity of an ant exploration path is increased, and the robustness and convergence of the ant colony algorithm are enhanced. A path smoothness factor is introduced into ant pheromone updating, an elite ant pheromone updating rule is established, the pheromone concentration on an explored better path is enhanced, and the optimization capacity and convergence speed of an ant colony are improved. And a Bezier curve is used to perform smoothing processing near a turning point in the optimal path finally output by the ant colony, so that the final path becomes smoother, and trajectory tracking of the path by the mobile robot is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of robot path planning, and in particular to a method for mobile robot path planning in an unmanned building material testing laboratory. Background Art

[0002] With the development of society and advancements in technology, the application of mobile robots in the field of unmanned inspection of building materials has received increasing attention, especially in the field of path planning. Mobile robot path planning technology involves finding an optimal or near-optimal path from a starting point to a destination in a complex environment based on predetermined rules and standards.

[0003] Currently, many researchers at home and abroad are dedicated to the study of path planning algorithms. Commonly used path planning algorithms include the ant colony algorithm, Dijkstra algorithm, A* algorithm, particle swarm algorithm, genetic algorithm, etc. Among them, the ant colony algorithm, which uses a random heuristic search method based on group foraging, has been widely used in solving path planning problems due to its better robustness and adaptability compared to other path planning algorithms.

[0004] However, traditional ant colony algorithms have some flaws. For example, the heuristic function only considers the distance between the current node and the next node to move to, and does not consider the impact of the target point on the overall path planning. The pheromone update rule also only considers the length of the path traversed by the ants, failing to account for the tortuosity of the path. Summary of the Invention

[0005] In order to overcome the shortcomings of the above technologies, the present invention provides a path planning method for a mobile robot in an unmanned testing laboratory for building materials, which can overcome the problems of slow convergence speed, many path turns and poor smoothness in path planning of traditional ant colony algorithms.

[0006] The technical solution adopted by the present invention to overcome the technical problems is: A method for mobile robot path planning in an unmanned building materials testing laboratory, comprising: S1. Create an environment map; S2. Initialize the ant colony algorithm parameters and place the ant colony in the environment map; S3. Calculate the first An ant's State transition probability at time; S4. According to all ants The state transition probability at each moment selects the optimal path and the corresponding ant as the elite ant; S5. iterate the improved ant colony algorithm; S6. Determine whether the ant colony algorithm has reached the maximum number of iterations. If so, execute step S8. If not, perform a global pheromone update and return to step S3. S7. Select the final optimal path based on the iterated state transition probabilities; S8. Smoothing the final optimal path to obtain the final path for the mobile robot to perform trajectory tracking.

[0007] Furthermore, in step S1, a grid method is used to establish an environment map, and the environment map is divided into a number of grids of the same size.

[0008] Furthermore, step S2 includes the following steps: S2-1. Initialize the ant colony algorithm parameters and determine the number of ants , maximum number of iterations , heuristic function heuristic factor , pheromone-inducing factors and the starting grid and target grid of the ant colony in the environment map; S2-2. will include Place the ant colony of ants into the starting grid.

[0009] Furthermore, step S3 includes the following steps: S3-1. Through the formula Calculated Moment Ants from the current Grid to Heuristic function for mesh transfer , , where is the adaptive adjustment factor, , is the current iteration number, is a natural constant, is the distance weight coefficient, For the Ants from the current Grid to The distance between the grids, For the The ant from the grid to target grid the distance between them; S3-2. Through the formula Calculated Moment The influence of an ant turning , where is the path smoothing factor, for Moment Ants from the previous grid To the current The direction of the grid, for Moment Ants from the current Grid to The direction of the grid; S3-3. Through the formula Calculated Moment The state transition probability of an ant , for Moment The grid and The pheromone concentration on the path composed of grids is is the weight of influence, For the The set of grids that ants are waiting to visit.

[0010] Preferably, The value range is between 0 and 1.

[0011] Furthermore, step S4 includes the following steps: S4-1. Comparison The state transition probability of each ant is selected, and the path of the ant with the largest state transition probability value is selected as the optimal path in the environment; S4-2. The ant with the largest state transition probability value is regarded as the elite ant.

[0012] Furthermore, step S6 includes the following steps: S6-1. Determine whether the ant colony algorithm has reached the maximum number of iterations ; S6-2. If the maximum number of iterations is reached Then execute step S8; S6-3. If the maximum number of iterations is not reached Then through the formula Calculate the updated global information elements Moment The grid and The pheromone concentration on the path composed of grids , where is the global pheromone volatility coefficient, For the Ant At the moment The grid and The pheromone concentration on the path composed of grids, , is the pheromone enhancement coefficient, For this iteration The ant passed by The grid and The length of the path formed by the grid, is the path smoothing coefficient, For the The grid and The number of turns in the path composed of grids, The elite ants pass through the first The grid and Whether the pheromone concentration after the path formed by the grid is , is the optimal path of the environment in the current iteration, is the information weight coefficient of the elite ant, , where is the length of the optimal path in the current iteration, for The length of the optimal path in the moment history; S6-4. Alternative Then return to step S3.

[0013] Furthermore, in step S7, the state transition probabilities of the ants after iteration are compared, and the path of the ant with the largest state transition probability value is selected as the final optimal path in the environment.

[0014] Furthermore, in step S8, a cubic Bezier curve is used to smooth the final optimal path to obtain a final path for the mobile robot to track.

[0015] The beneficial effects of the present invention are: A grid method was used to build an environmental map, determine the starting and target points of the mobile robot, and introduce a smoothing function influenced by the number of path turns into the ant state transition formula. By introducing the target factor, the heuristic information was improved, the directionality of the ant's exploration path was increased, and the robustness and convergence of the ant colony algorithm were enhanced.

[0016] The path smoothness factor is introduced into the ant pheromone update, and the elite ant pheromone update rule is established to enhance the pheromone concentration on the explored better path, thereby improving the ant colony's optimization ability and convergence speed.

[0017] The turning points in the optimal path finally output by the ant colony are smoothed with Bezier curves to make the final path smoother, which is conducive to the trajectory tracking of the mobile robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of the method of the present invention; Figure 2 The present invention uses Bezier curves to smooth the turning points in the output optimal path. Figure 3 A comparison chart of the improved ant colony algorithm of the present invention and the classic ant colony algorithm. DETAILED DESCRIPTION

[0019] The following is combined with Figure 1 , Attachment Figure 2 , Attachment Figure 3 The present invention is further described.

[0020] A method for mobile robot path planning in an unmanned building materials testing laboratory, comprising: S1. Create an environment map.

[0021] S2. Initialize the ant colony algorithm parameters and place the ant colony in the environment map.

[0022] S3. Calculate the first An ant's The state transition probability at time .

[0023] S4. According to all ants The state transition probability at each moment selects the optimal path and the corresponding ant as the elite ant.

[0024] S5. Iterate the improved ant colony algorithm.

[0025] S6. Determine whether the ant colony algorithm has reached the maximum number of iterations. If so, execute step S8. If not, perform a global pheromone update and then return to step S3.

[0026] S7. Select the final optimal path based on the iterated state transition probability.

[0027] S8. Smoothing the final optimal path to obtain the final path for the mobile robot to perform trajectory tracking.

[0028] A grid-based approach is used to construct the mobile robot's motion environment, starting point, and destination. An adaptive dynamic adjustment factor is introduced, and heuristic information is improved by combining the number of turns and the destination. Elite ants are also introduced to update the optimal path using pheromone differences. Furthermore, Bezier curves are used to smooth the turning points of the optimal path output by the ant colony algorithm. The resulting optimal path is shorter, has fewer turns, and is smoother, making it more conducive to tracking the trajectory of mobile robots in real environments.

[0029] In order to verify the innovation and rationality of the method of the present invention, the Matlab programming language was used to simulate the present invention in a 30×30 environment and compared with the classic ant colony algorithm.

[0030] The path planning results are as follows Figure 3 As shown in the figure, the blue one is the improved ant colony algorithm of the present invention, and the red one is the classic ant colony algorithm. Figure 3 As shown in the figure, although both algorithms successfully plan the path from the starting point to the target point, the classic ant colony algorithm does not consider the impact of the target point on the overall path planning, does not consider the number of turns in the path, etc., resulting in the planned path being long and having multiple turns.

[0031] Attachment Figure 2 The figure shows the result of smoothing the path turning point by using the cubic Bezier curve in the present invention. Figure 2 It can be seen that there is little overall difference between the original path and the smoothed path. Smoothing is only performed at the turning points of the path, which is more suitable for the moving route of the mobile robot in a real environment.

[0032] In step S1, a grid method is used to create an environmental map, dividing the environmental map into several equally sized grids. The advantage of using the grid method to create an environmental map is that it can divide a complex environment into many equally sized grids, each of which represents a discrete spatial region. Different spaces can be marked based on the different properties of the grid cells, for example, white grids represent free movement space, and black grids represent obstacle space.

[0033] In one embodiment of the present invention, step S2 includes the following steps: S2-1. Initialize the ant colony algorithm parameters and determine the number of ants , maximum number of iterations , heuristic function heuristic factor , pheromone-inducing factors As well as the starting grid and target grid of the ant colony in the environment map.

[0034] S2-2. will include Place the ant colony of ants into the starting grid.

[0035] In one embodiment of the present invention, step S3 includes the following steps: S3-1. Through the formula Calculated Moment Ants from the current Grid to Heuristic function for mesh transfer , , where is the adaptive adjustment factor, , is the current iteration number, is a natural constant, is the distance weight coefficient, For the Ants from the current Grid to The distance between the grids, For the The ant from the grid to target grid The distance between them.

[0036] S3-2. Through the formula Calculated Moment The influence of an ant turning , where is the path smoothing factor, for Moment Ants from the previous grid To the current The direction of the grid, for Moment Ants from the current Grid to The direction of the grid.

[0037] S3-3. Through the formula Calculated Moment The state transition probability of an ant , for Moment The grid and The pheromone concentration on the path composed of grids is is the weight of influence, For the The set of grids that ants are waiting to visit.

[0038] In this embodiment, The value range is between 0 and 1.

[0039] In one embodiment of the present invention, step S4 includes the following steps: S4-1. Comparison The state transition probability of each ant is calculated, and the path of the ant with the largest state transition probability value is selected as the optimal path in the environment.

[0040] S4-2. The ant with the largest state transition probability value is regarded as the elite ant.

[0041] In one embodiment of the present invention, step S6 includes the following steps: S6-1. Determine whether the ant colony algorithm has reached the maximum number of iterations .

[0042] S6-2. If the maximum number of iterations is reached Then execute step S8.

[0043] S6-3. If the maximum number of iterations is not reached Then through the formula Calculate the updated global information elements Moment The grid and The pheromone concentration on the path composed of grids , where is the global pheromone volatility coefficient, For the Ant At the moment The grid and The pheromone concentration on the path composed of grids, , is the pheromone enhancement coefficient, For this iteration The ant passed by The grid and The length of the path formed by the grid, is the path smoothing coefficient, For the The grid and The number of turns in the path composed of grids, The elite ants pass through the first The grid and Whether the pheromone concentration after the path formed by the grid is , is the optimal path of the environment in the current iteration, is the information weight coefficient of the elite ant, , where is the length of the optimal path in the current iteration, for The length of the optimal path in the time history.

[0044] S6-4. Alternative Then return to step S3.

[0045] In one embodiment of the present invention, the comparison after iteration in step S7 is performed. The state transition probability of each ant is calculated, and the path of the ant with the largest state transition probability value is selected as the final optimal path in the environment.

[0046] In one embodiment of the present invention, in step S8, a cubic Bezier curve is used to smooth the final optimal path to obtain a final path for trajectory tracking by the mobile robot.

[0047] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for mobile robot path planning in an unmanned building material testing laboratory, characterized in that: include: S1. Create an environment map; S2. Initialize the ant colony algorithm parameters and place the ant colony in the environment map; S3. Calculate the first An ant's State transition probability at time; S4. According to all ants The state transition probability at each moment selects the optimal path and the corresponding ant as the elite ant; S5. iterate the improved ant colony algorithm; S6. Determine whether the ant colony algorithm has reached the maximum number of iterations. If so, execute step S8. If not, perform a global pheromone update and return to step S3. S7. Select the final optimal path based on the iterated state transition probabilities; S8. Smoothing the final optimal path to obtain the final path for the mobile robot to perform trajectory tracking.

2. The method for mobile robot path planning in an unmanned building materials testing laboratory according to claim 1, characterized in that: In step S1, a grid method is used to create an environment map, and the environment map is divided into a number of grids of the same size.

3. The method for mobile robot path planning in an unmanned building materials testing laboratory according to claim 1, characterized in that: Step S2 includes the following steps: S2-1. Initialize the ant colony algorithm parameters and determine the number of ants , maximum number of iterations , heuristic function heuristic factor , pheromone-inducing factors and the starting grid and target grid of the ant colony in the environment map; S2-2. will include Place the ant colony of ants into the starting grid.

4. The method for mobile robot path planning in an unmanned building materials testing laboratory according to claim 1, characterized in that: Step S3 includes the following steps: S3-1. Through the formula Calculated Moment Ants from the current Grid to Heuristic function for mesh transfer , , where is the adaptive adjustment factor, , is the current iteration number, is a natural constant, is the distance weight coefficient, For the Ants from the current Grid to The distance between the grids, For the The ant from the grid to target grid the distance between them; S3-2. Through the formula Calculated Moment The influence of an ant turning , where is the path smoothing factor, for Moment Ants from the previous grid To the current The direction of the grid, for Moment Ants from the current Grid to The direction of the grid; S3-3. Through the formula Calculated Moment The state transition probability of an ant , for Moment The grid and The pheromone concentration on the path composed of grids is is the weight of influence, For the The set of grids that ants are waiting to visit.

5. The method for mobile robot path planning in an unmanned building materials testing laboratory according to claim 4, characterized in that: The value range is between 0 and 1.

6. The method for mobile robot path planning in an unmanned building material testing laboratory according to claim 3, characterized in that: Step S4 includes the following steps: S4-1. Comparison The state transition probability of each ant is selected, and the path of the ant with the largest state transition probability value is selected as the optimal path in the environment; S4-2. The ant with the largest state transition probability value is regarded as the elite ant.

7. The method for mobile robot path planning in an unmanned building material testing laboratory according to claim 4, characterized in that: Step S6 includes the following steps: S6-1. Determine whether the ant colony algorithm has reached the maximum number of iterations ; S6-2. If the maximum number of iterations is reached Then execute step S8; S6-3. If the maximum number of iterations is not reached Then through the formula Calculate the updated global information elements Moment The grid and The pheromone concentration on the path composed of grids , where is the global pheromone volatility coefficient, For the Ant At the moment The grid and The pheromone concentration on the path composed of grids, , is the pheromone enhancement coefficient, For this iteration The ant passed by The grid and The length of the path formed by the grid, is the path smoothing coefficient, For the The grid and The number of turns in the path composed of grids, The elite ants pass through the first The grid and Whether the pheromone concentration after the path formed by the grid is , is the optimal path of the environment in the current iteration, is the information weight coefficient of the elite ant, , where is the length of the optimal path in the current iteration, for The length of the optimal path in the moment history; S6-4. Alternative Then return to step S3.

8. The method for mobile robot path planning in an unmanned building materials testing laboratory according to claim 1, characterized in that: In step S7, the comparison of the iterative The state transition probability of each ant is calculated, and the path of the ant with the largest state transition probability value is selected as the final optimal path in the environment.

9. The method for mobile robot path planning in an unmanned building materials testing laboratory according to claim 1, characterized in that: In step S8, the final optimal path is smoothed using a cubic Bezier curve to obtain the final path for the mobile robot to track.

Images