Crawler inspection robot path planning method based on ant colony optimization algorithm

Abstract

The invention relates to a routing inspection robot path planning method based on an ant colony optimization algorithm, and the method specifically comprises the following steps: 1, introducing a self-adaptive adjustment factor into an ant colony pheromone updating rule, and enabling the factor to dynamically change according to the frequency of ants encountering an obstacle; 2, removing redundant stagnation points, performing curve fitting on key nodes, performing smooth transition on paths between adjacent key nodes, and reducing tortuosity and turning angles; meanwhile, a sensor is used for collecting information, unknown static and dynamic obstacles are recognized in real time, a dynamic window method of an improved safety distance evaluation subfunction is adopted for local path planning obstacle avoidance, the method is simple and easy to use and high in precision, the path adaptivity can be effectively enhanced, and the path planning performance can be improved.

Description

Technical Field

[0001] The invention relates to a path planning method for a crawler inspection robot based on an ant colony optimization algorithm, and belongs to the field of special robots. Background Art

[0002] With the booming development of the industrial field, the importance of equipment inspection has become increasingly prominent. The traditional manual inspection method has been unable to meet the needs of modern industry due to its drawbacks such as high work intensity, low efficiency and poor safety. Tracked inspection robots came into being. The tracked design was chosen mainly because it has excellent passability and stability in complex terrain and harsh environments, and can better adapt to various ground conditions in industrial scenarios, such as rugged roads, areas with obstacles, etc. At present, there are many shortcomings in the path planning method of inspection robots. On the one hand, the existing path planning methods have poor adaptability in complex industrial environments and are difficult to cope with changing terrain, numerous obstacles and uncertain environmental factors. On the other hand, the efficiency and accuracy of path planning need to be improved, which may cause the robot to have a long path, frequent detours or even fail to reach the target location during the inspection process, affecting the timeliness and effectiveness of the inspection work.

[0003] The path planning method for tracked inspection robots based on ant colony optimization algorithm proposed in this invention aims to provide an efficient and accurate solution to these shortcomings. By improving and optimizing the algorithm, it can better adapt to complex industrial environments, improve the efficiency and accuracy of path planning, and enable the inspection robot to accurately and quickly plan the optimal path in various complex situations, thereby effectively solving the problems existing in the current inspection robot path planning method and providing more reliable support for industrial equipment inspection. Summary of the invention

[0004] Purpose of the invention: In order to overcome the problems of low efficiency and low accuracy in the inspection process of current tracked inspection robots, the present invention provides a path planning method for a tracked inspection robot based on an ant colony optimization algorithm, so as to realize accurate and efficient autonomous path planning of the tracked inspection robot in a complex industrial environment.

[0005] Technical solution: To solve the above technical problems, the present invention provides a path planning method for a crawler inspection robot based on an ant colony optimization algorithm, which specifically includes the following steps: Step 1: Construct an environmental grid map of the crawler inspection robot, divide the robot's environment into grids of the same size, and set the starting point and target point of the crawler inspection robot; Step 2: Improve the traditional ant colony algorithm and use the improved ant colony optimization algorithm to perform global path planning to obtain the optimal path; Step 3: Identify unknown static and dynamic obstacles in the global map. Collect surrounding environment information with the help of sensors such as LiDAR; Step 4: Process the surrounding environment information data collected in step 3, update the internal environment of the dynamic window, and determine whether there are unknown static and dynamic obstacles. Step 5: If no obstacle is detected, the robot moves along the shortest obstacle-free path; if an obstacle is detected, the robot performs local path planning to avoid the obstacle, and returns to the optimal path to continue driving after completing the obstacle avoidance. Step 6: Use the dynamic window method of the improved safety distance evaluation subfunction to perform local path planning to avoid obstacles. The tracked inspection robot moves along the local planned path. After obstacle avoidance is completed, it returns to the optimal path and determines whether the tracked inspection robot has reached the target point. If it has reached the target point, the algorithm ends, otherwise execute step 4.

[0006] The technical solution of the present invention is further defined as the method for improving the ant colony optimization algorithm, and the specific steps of the method are as follows: S1: Introduce an adaptive weight factor into the path quality evaluation function of the ant colony algorithm. This factor is dynamically adjusted according to the probability of ants encountering obstacles during the search process. When the probability of ants encountering obstacles in a certain area is high, it is reduced to reduce the possibility of the path in this area being selected, prompting the ants to explore other paths more; conversely, when the probability of encountering obstacles is low, it is increased to encourage ants to search more actively in this area. S2: Eliminate all redundant turning points in the path planned in S1 to obtain a smoother and safer path. By eliminating unnecessary turning points, the path design is further optimized to improve the robot's movement between tracks; S3: Perform arc processing on the turning points in S2 and eliminate redundant turning points. By repeating this process, the entire path is optimized to obtain a smoother and safer path, improve the robot's movement efficiency between tracks, and reduce mechanical loss and energy consumption; This circular processing not only reduces the path length, since circular paths are usually shorter than zigzag paths, but also reduces the mechanical stress on the robot when turning.

[0007] Furthermore, in step 6, the dynamic window method of improving the safety distance evaluation sub-function is as follows: let the safety distance evaluation sub-function be D(n), and its calculation method takes multiple factors into consideration to more comprehensively evaluate the safety of the path. D(n)=λ1·d total (n)+λ2·d min (n)+λ3·p(n)+λ4·v(n) Where, d total(n) is the total length of the path from the starting point to the current node n; d min (n) is the shortest distance between the current node n and the surrounding obstacles; p(n) is the safety penalty function, which is calculated as follows: Where p0 is a large constant used to control the intensity of the penalty, d th is a safety threshold distance, d min (n) when less than d th When , the penalty function starts to work, and d min The smaller (n), the greater the penalty, that is, the lower the possibility of the path being selected. This can encourage ants to choose paths farther away from obstacles and improve the safety of path planning; v(n) is the speed evaluation function, which represents the speed of the inspection robot at the current node n; λ1, λ2, λ3, and λ4 are weight coefficients used to adjust the impact of factors such as the inspection robot's movement direction, distance, and speed on the evaluation function results.

[0008] Furthermore, in step 2, the path quality evaluation function is optimized, and the calculation formula is: F(n)=G(n)+H(n) Among them, c i = k·d, In the formula, represents the cumulative moving cost of the ant from the starting point to the current node n. obs (n) is the minimum distance between the current node n and the next node to the nearest obstacle, r safe is the safety radius of the inspection robot, and ω is the safety cost weight. j is a binary indicator variable. When there is an obstacle at the node j that the ant passes through, o j =1, otherwise o j = 0, μ is a weight coefficient used to adjust the importance of the number of obstacles in the actual cost. η is an adaptive weight factor, d est (n) is the estimated distance from the current node n to the target node, d total is the estimated total distance between the start node and the target node, The complexity factor of the path is taken into account. n is the number of nodes that the ant has traversed, N is the total number of nodes between the starting node and the target node, and ξ is a weight coefficient.

[0009] Furthermore, in step 2, the path smoothness optimization index is calculated as follows: Where: m is the number of key nodes on the path (including starting point, turning point and target point, etc.), R iis the curvature radius corresponding to the i-th path. n is the number of turning points on the path, θ j is the turning angle of the jth turning point, α j is the weight coefficient of the turning angle.

[0010] Furthermore, in step 2, it is characterized in that, in S2, the obtained path is smoothed, and the calculation formula is: Where C(t) represents the Bezier curve function, which is used to describe the coordinates of points on the curve. n is the degree of the Bezier curve, which affects the shape complexity of the curve. i represents the control point, which is used to determine the approximate shape of the curve. i,n (t) is the nth-order Bernstein polynomial, which is a function of parameter t and is used to determine the weighted contribution of the control point to the curve. C'(t) is the first-order derivative of the Bezier curve, which is used to indicate the tangent direction of the curve at a certain point. C" (t) is the second-order derivative of the Bezier curve, which is used for calculations related to the curvature of the curve.

[0011] Beneficial Effects In summary, the path planning method for the crawler inspection robot of the present invention has significant advantages. The crawler robot has good passability and stability and can adapt to complex terrain. The improved ant colony optimization algorithm plays a key role in improving the performance of the robot in many aspects. By optimizing the evaluation function and introducing an adaptive weight factor, the path is smoothed. The robot can flexibly respond to environmental changes when searching for the path and quickly and accurately plan the optimal inspection path. This realizes efficient unmanned inspection of factory workshops, and also brings a series of practical benefits by optimizing the path, such as reducing energy consumption, reducing inspection time, etc., which greatly improves the inspection efficiency and quality. DETAILED DESCRIPTION

[0012] The present invention will be further described below.

[0013] The present invention provides a path planning method for a crawler inspection robot based on an ant colony optimization algorithm. The algorithm can be used for global path planning and dynamic obstacle avoidance during movement. The specific steps are as follows: Step 1: Construct an environmental grid map of the crawler inspection robot, divide the robot's environment into grids of the same size, and set the starting point and target point of the crawler inspection robot; Step 2: Improve the traditional ant colony algorithm and use the improved ant colony optimization algorithm to perform global path planning and obtain the optimal path; Step 3: Identify unknown static obstacles and unknown dynamic obstacles on the global map. Collect surrounding environment information with the help of sensors such as LiDAR; Step 4: Process the surrounding environment information data collected in step 3, update the internal environment of the dynamic window, and determine whether there are unknown static and dynamic obstacles; Step 5: If there is no obstacle, continue driving along the shortest obstacle-free path; if there is an obstacle, perform collision prediction and implement obstacle avoidance measures; Step 6: Use the dynamic window method of the improved safety distance evaluation subfunction to perform local path planning to avoid obstacles. The crawler inspection robot moves along the local planned path, returns to the optimal path after obstacle avoidance is completed, and determines whether the crawler inspection robot has reached the target point. If it has reached the target point, the algorithm ends, otherwise execute step 4.

[0014] Furthermore, the improved method of the ant colony optimization algorithm in step 2 is specifically as follows: S1: When obstacles, starting points, target points, and map environment information are known, an adaptive weight factor is introduced into the ant colony algorithm to calculate a new path quality evaluation function. This factor is dynamically adjusted according to the probability of ants encountering obstacles during the search process. When ants explore an area, if the probability of encountering obstacles is high, the adaptive weight factor will decrease accordingly. This makes the ants more inclined to avoid the area when selecting the next node, and instead explore other path directions with a lower probability of encountering obstacles. Conversely, when the probability of ants encountering obstacles in a certain area is low, the adaptive weight factor increases, encouraging the ants to search for forward paths more actively in that area. This dynamic adjustment mechanism is designed to enable the algorithm to quickly adapt to environmental changes and quickly plan the optimal path that best meets the movement requirements of the crawler inspection robot. S2: After searching the path according to the new path quality evaluation function, when the coordinate value of the target point is calculated, determine whether this coordinate point is the final target point. If it is determined that the final target point has been reached, further optimize the planned path, that is, eliminate all redundant turning points in the S1 planned path. By carefully analyzing the node relationship on the path, the path between three consecutive nodes is determined. If the robot can directly reach the third node safely from the first node without colliding with any obstacles, and will not adversely affect subsequent path planning and path planning, then the second node in the middle is identified as a redundant turning point and is eliminated. S3: During the inspection process, when the robot turns at a large angle, drift may occur, which has an adverse effect on the actual control of the robot. Therefore, the turning points in the optimized path in S2 are processed with arcs. For each turning point on the path, the relevant geometric parameters are first calculated based on the position information of its front and rear nodes. Then, a suitable arc radius is determined based on the motion characteristics of the inspection robot and the actual environment requirements. An arc is drawn with the turning point as the center and the determined arc radius as the radius, so that the robot can smoothly transition from the current path segment to the next path segment along this arc.

[0015] Furthermore, in step 6, the dynamic window method of improving the safety distance evaluation sub-function is as follows: let the safety distance evaluation sub-function be D(n), D(n)=λ1·d total (n)+λ2·d min (n)+λ3·p(n)+λ4·v(n) Where, d total (n) is the total length of the path from the starting point to the current node n; d min (n) is the shortest distance between the current node n and the surrounding obstacles; p(n) is the safety penalty function, which is calculated as follows: Where p0 is a large constant used to control the intensity of the penalty, d th is a safety threshold distance, d min (n) when less than d th When , the penalty function starts to work, and d min The smaller (n), the greater the penalty, that is, the lower the possibility of the path being selected. This can encourage ants to choose paths farther away from obstacles and improve the safety of path planning; v(n) is the speed evaluation function, which represents the speed of the inspection robot at the current node n; λ1, λ2, λ3, and λ4 are weight coefficients used to adjust the impact of factors such as the inspection robot's movement direction, distance, and speed on the evaluation function results.

[0016] Furthermore, in step 2, the path quality evaluation function is optimized, and the calculation formula is: F(n)=G(n)+H(n) Among them, c i = k·d, In the formula, represents the cumulative moving cost of the ant from the starting point to the current node n. obs (n) is the minimum distance between the current node n and the next node to the nearest obstacle, r safe is the safety radius of the inspection robot, and ω is the safety cost weight. jis a binary indicator variable. When there is an obstacle at the node j that the ant passes through, o j =1, otherwise o j = 0, μ is a weight coefficient used to adjust the importance of the number of obstacles in the actual cost. η is an adaptive weight factor, d est (n) is the estimated distance from the current node n to the target node, d total is the estimated total distance between the start node and the target node, The complexity factor of the path is taken into account. n is the number of nodes that the ant has traversed, N is the total number of nodes between the starting node and the target node, and ξ is a weight coefficient.

[0017] Furthermore, in step 2, the path smoothness optimization index is calculated as follows: Where: m is the number of key nodes on the path (including starting point, turning point and target point, etc.), R i is the curvature radius corresponding to the i-th path. n is the number of turning points on the path, θ j is the turning angle of the jth turning point, α j is the weight coefficient of the turning angle.

[0018] Furthermore, after a candidate path is generated, we evaluate it according to the above-mentioned smoothness evaluation index J. If the J value is large, it means that the path is not smooth enough and needs to be smoothed. The calculation formula is: Where C(t) represents the Bezier curve function, which is used to describe the coordinates of points on the curve. n is the degree of the Bezier curve, which affects the shape complexity of the curve. i represents the control point, which is used to determine the approximate shape of the curve. i,n (t) is the nth-order Bernstein polynomial, which is a function of parameter t and is used to determine the weighted contribution of the control point to the curve. C'(t) is the first-order derivative of the Bezier curve, which is used to indicate the tangent direction of the curve at a certain point. C" (t) is the second-order derivative of the Bezier curve, which is used for calculations related to the curvature of the curve.

[0019] The tracked inspection robot path planning method based on the ant colony optimization algorithm proposed in the present invention can enable the inspection robot to plan a simple and smooth motion path in a complex industrial environment and have the ability to avoid unknown obstacles.

[0020] For global planning, by introducing adaptive weight factors and safety radius based on the path quality evaluation function of the ant colony optimization algorithm, and optimizing redundant nodes and arc processing on the global path, the algorithm's safety, turning angles, and smoothness are significantly improved, and the path is shorter. For local planning, the kinematic model of the inspection robot is first established, and the dynamic window method of the improved safety distance evaluation subfunction is used to improve the inspection robot's ability to avoid unknown obstacles. By combining the improved ant colony optimization algorithm and the dynamic window method ant colony optimization, the inspection robot has the ability to find the shortest obstacle-free path in a complex industrial environment, enabling the inspection robot to avoid unknown obstacles in real time and meet the requirement of reaching the target point without collision.

[0021] In summary, the path planning method for the crawler inspection robot based on the ant colony optimization algorithm of the present invention is innovative and practical. By improving the ant colony optimization algorithm and the ant colony optimization dynamic window method, the crawler inspection robot can achieve efficient, accurate and autonomous path planning in complex industrial environments, providing strong support for the development of industrial automation and intelligence. In the future, we will continue to study and optimize the algorithm in depth, further improve the performance and application scope of the inspection robot, and make greater contributions to promoting the development of the industrial field.

Claims

1. A path planning method for a tracked inspection robot based on an ant colony optimization algorithm, characterized in that: The following steps are involved: Step 1: Construct an environmental grid map of the crawler inspection robot, divide the robot's environment into grids of the same size, and set the starting point and target point of the crawler inspection robot; Step 2: Improve the traditional ant colony algorithm and use the improved ant colony optimization algorithm to perform global path planning to obtain the optimal path; Step 3: Identify unknown static and dynamic obstacles in the global map. Collect surrounding environment information with the help of sensors such as LiDAR; Step 4: Process the surrounding environment information data collected in step 3, update the internal environment of the dynamic window, and determine whether there are unknown static and dynamic obstacles; Step 5: If no obstacle is detected, the robot moves along the shortest obstacle-free path; if an obstacle is detected, the robot performs local path planning to avoid the obstacle, and returns to the optimal path to continue driving after completing the obstacle avoidance. Step 6: Use the dynamic window method of the improved safety distance evaluation subfunction to perform local path planning to avoid obstacles. The crawler inspection robot moves along the local planned path and returns to the optimal path after completing the obstacle avoidance. And determine whether the crawler inspection robot has reached the target point. If it has, the algorithm ends; otherwise, execute step 4.

2. A path planning method for a tracked inspection robot based on an improved ant colony optimization algorithm according to claim 1, characterized in that: Step 2 improves the traditional ant colony algorithm. The specific method is as follows: S1: Introduce an adaptive adjustment factor into the ant colony pheromone update rule. This factor changes dynamically according to the frequency of obstacles encountered by ants during the path search process. When ants frequently encounter obstacles in a certain area, adjust the pheromone volatilization speed in that area and change the pheromone accumulation amount to guide subsequent ants to explore other feasible paths; S2: Remove all unnecessary stagnation points that appear in the path planned in S1. During the search process of the ant colony algorithm, due to the random exploration characteristics of ants, some unnecessary stagnation points may be generated, which not only increase the path length, but also may affect the operating efficiency of the inspection robot. By backtracking the path, these redundant stagnation points are identified and eliminated to obtain a more concise and efficient path; S3: Perform curve fitting processing on the key nodes on the processed path in S2 to reduce the tortuosity and turning angle of the path, make it more consistent with the kinematic characteristics of the inspection robot, reduce the energy loss and mechanical wear of the robot during driving, and improve the stability and fluency of path planning.

3. According to the path planning method of a crawler inspection robot based on ant colony optimization algorithm as described in claim 1, it is characterized in that: In step 6, the safety distance evaluation subfunction in the ant colony optimization algorithm is improved, and the specific formula is: in, is the azimuth deflection angle evaluation subfunction, which represents the angle difference between the current forward direction of the inspection robot and the direction of the target point; is the safety distance evaluation subfunction, , The shortest distance between the globally known obstacle and the ant’s current location to simulate the next path, The shortest distance between the unknown dynamic obstacle and the ant’s current location to simulate the next path, Simulate the shortest distance between the static obstacle and the ant's current location and the next path; is a safety penalty function. When the path chosen by the ant is too close to an obstacle, Increase to reduce the probability of this path being selected; is the speed evaluation function, which indicates the moving speed of the ant in the current state; , , , It is the weight coefficient, which is used to adjust the influence of factors such as the inspection robot's movement direction, distance and speed on the evaluation function result.

4. According to claim 2, a path planning method for a crawler inspection robot based on an ant colony optimization algorithm is characterized in that: In S2, the path quality evaluation function is optimized, and the calculation formula is: in, From the starting point through the node Cost estimate to reach the destination; is the distance from the starting point to the node in the state space The actual cost includes the cost of the ant moving from the starting point to the current node and the additional cost considering obstacles; For slave nodes The estimated cost of the best path to the goal state; is the safety cost weight, which is used to adjust the impact of obstacles on the path cost; is an adaptive weight factor, and its value is dynamically adjusted according to the obstacles encountered by ants during the search process. When the probability of ants encountering obstacles in a certain area is high, Decrease to increase cautious exploration of paths in the area, increase to encourage a more extensive search; For Ant slave nodes To Node The movement cost (which can be set according to the actual situation, for example, proportional to the distance between the two points); For the current node The minimum distance from the path to the next node to the nearest obstacle; is the safety radius of the inspection robot; From the current node The estimated distance to the target node (which can be estimated using a suitable distance metric such as Euclidean distance); is the estimated total distance between the start node and the target node.

5. A path planning method for a crawler inspection robot based on an ant colony optimization algorithm according to claim 2, characterized in that: In step 2, the path smoothness optimization index is calculated as: in: is the number of key nodes on the path (including starting point, turning point and target point, etc.), For the The radius of curvature corresponding to the path segment. is the number of turning points on the path, For the The turning angle of the turning point, is the weight coefficient of the turning angle.

6. A path planning method for a crawler inspection robot based on an ant colony optimization algorithm according to claim 2, characterized in that: In S2, the obtained path is smoothed, and the calculation formula is: in, Represents a Bezier curve function, which is used to describe the coordinates of points on the curve. The degree of the Bezier curve, which affects the shape complexity of the curve. Represents the control point, which is used to determine the approximate shape of the curve. is a Bernstein polynomial of degree n, a function of parameter t, used to determine the weighted contribution of the control points to the curve. The first derivative of a Bezier curve is used to represent the tangent direction of the curve at a certain point. The second derivative of a Bezier curve, used for calculations related to the curvature of the curve.

Images