Path planning self-learning algorithm for a dynamic chaning environment

摘要: Safe and optimal path planning in a cluttered changing environment for agents’ movement is an area of research, which needs further investigations. The existing methods are able to generated secure trajectories, but they not efficient enough learn from their mistakes, especially when dynamics the concerned. This paper presents advanced version Ant-Air algorithm, can detect changed scenario while keeping lessons learnt previously planned safe trajectory, it then generates by avoiding collisions with obstacles. method presented experience hence improve already trajectories using learned experience. concept developed applicable various domains such as mobile robot, industrial robots, simulation part narrow passages.