Global Path Planning of Substation Intelligent Inspection Robot Based on Improved Dijkstra Algorithm

Abstract

With the rapid development of artificial intelligence, unattended substations are developing in a large-scale and complex situation, which makes the traditional manual inspection methods of substations face huge challenges. In the global optimal path planning of intelligent inspection robots in substations, there is a problem of solving the shortest path between any two pairs of contacts. And there is a problem of solving the optimal combination of all docking points. Therefore, the Voronoi environment modeling method is studied. The Dijkstra algorithm is improved by limiting the search area to search for the shortest path between any two nodes. Then simulated annealing algorithm is used to search for the optimal combination of all necessary docking points. Finally, the solution of the global optimal route is achieved. The research results show that the DS algorithm only needs to iterate 17 times to generate the optimal path, which is 30.23m, and the average accuracy of the DS algorithm is 97.83%. In summary, the proposed DS algorithm has excellent performance and can be well applied to the global path planning of substation intelligent inspection robots.