Hybrid Path Planning Based On Particle Swarm Optimization And Improved Ant Colony Algorithm For Robot

Gas explosions,permeable water,and roof-falling disasters often occur during coal mining.Using robots to detect the environment of disaster mines can prevent mine secondary disasters from causing damage to trapped miners and rescuers,and create conditions for efficient rescue work.Post-disaster mine environment is complex.Falling roofs will prevent the robot from moving in the tunnel.In order to enable the robot to quickly enter the deep mine to detect dangerous environmental information,it is of great significance to carry out research on robot path planning.This topic was supported by the Thirteenth Five-Year National Key R&D Project which called “Coal Mine Catastrophe Environmental Information Detection and Storage Technology and Equipment”(2016YFC0801808).The main work is as follows:Firstly,the grid method is used to model the mobile robot working environment.Because the concave obstacles will lead to premature convergence of the path planning algorithm,the erosion and expansion pretreatment of the concave obstacles in the grid map is necessary.Transforming the concave obstacles into a regular rectangular obstacle avoids the algorithm falling into a local optimal trap.Secondly,The particle swarm algorithm is used to solve robot global path planning.This paper proposes to combine simulated annealing algorithm which has strong global search ability with particle swarm optimization algorithm to solve the problem of premature convergence and poor path quality for path planning of basic particle swarm optimization algorithm.Through simulation experiments in simple and complex environments,it is proved that the improved particle swarm algorithm can jump out of the local optimal solution and the path quality is improved.Then,the improved ant colony algorithm is applied to the local path planning of the robot.Considering the shortcomings of the basic ant colony algorithm such as poor obstacle avoidance ability and slow convergence rate,this paper proposes an improved ant colony algorithm.The algorithm introduces obstacle rejection weights and adds new path heuristic factors in the path selection probability formula to improve obstacle avoidance capabilities.By optimizing the updating of local and global pheromone in the path,the algorithm improves the convergence speed and path quality of the algorithm.Non-linear optimization of ants in the iterative process improves global search capabilities.A linear prediction model is used to predict the trajectories of dynamic obstacles,and corresponding obstacle avoidance strategies are adopted for different collision types.Simulation experiments show that the improved ant colony algorithm is more effective than the basic ant colony algorithm to avoid obstacles and the planned path is better.Finally,this paper proposes a hybrid path algorithm that combines particle swarm optimization with improved ant colony algorithm.An improved particle swarm optimization algorithm is used for global path planning.The mobile robot moves along the global optimal path and applies improved ant colony algorithm to avoid obstacles.The mobile robot continue to move along the global optimal path after obstacle avoidance.Through simulation,the mobile robot can effectively avoid static and dynamic obstacles which are temporarily added and reach the target point.