Research On Path Planning Of Mine Environment Detecting Robot After Disaster

Once a safety incident occurs in the coal mining process,the mine environment will become intricate.The mine environment detection robot can replace the rescue personnel to enter the complex and dangerous post-disaster scene quickly,and complete the environmental detection and the task that search survivors.The path planning of robots is the key technology to the search of underground blind areas.It is of great significance to carry out in-depth research on robot path planning.Based on the special environmental characteristics of mines and the needs of robot control,this paper studies on the path planning method of mine environment detection robots.This project is supported by the “13th Five-Year” National Key R&D Program “Coal Disaster Environment Information Detection and Storage Technology and Equipment”(2016YFC0801800).The main research work is summarized as follows:(1)The common methods of path planning are analyzed,these methods are generally divided into two categories: traditional planning methods and intelligent planning methods.According to the research and comparison of these algorithms,the advantages and disadvantages of each algorithm are obtained,which are provided for the selection of the later algorithms.(2)A grid map is used to construct and simulate a mine environment.At present,many methods such as raster map method,view of figure method,free space method and topological map used to construct the mine environment are studied in this paper.In order to facilitate subsequent research,this paper chooses the raster map method.(3)The application of genetic algorithm in path planning is improved in this paper.Through in-depth exploration of genetic algorithms,the advantages and disadvantages of genetic algorithms are found in the application of path planning.Although the genetic algorithm has strong global search ability,it has blindness to a certain extant,because of the random initial solution.In order to solve this problem,the artificial potential field method is used to generate the initial path,so that the initial solution has a certain direction.In order to speed up the convergence of the algorithm and increase the diversity of the population,this paper adopts an adaptive adjustment strategy to change the probability of crossover and mutation,and set the upper and lower limits of the probability.(4)In this paper,an improved genetic ant colony fusion algorithm is proposed for path planning of detection robot in complex mine environment.The ant colonyalgorithm is derived from the behavior of ant foraging.This feature has natural similarity with the path planning of robots.Therefore,the traditional ant colony algorithm and the common improved ant colony algorithm are analyzed in detail.Because the early search ability of the ant colony algorithm is poor,the improved genetic algorithm is used to plan the path of the robot,and then the path of the early planning is transformed into the distribution of the initial pheromone.The initial pheromone is the smooth application of the late ant colony algorithm.Preconditions are provided,which is also the bond of the two.The simulation results show that the algorithm can automatically avoid obstacles and plan a reasonable path while ensuring the calculation speed and convergence performance.