Recurrent Neural Network and Rapidly-exploring Random Tree Path Planning Adaptable to Environmental Change

We propose a robot path planning method adaptable to environmental change combining RRT and LSTM network. In this method, assuming multiple environments, a large amount of routes are generated by the RRT method and learning is performed using the LSTM network. We also try to adapt to environmental changes by using CAE during learning. By the proposed method, we perform the difficulty of a general random base method, that is, “generate reproducible route” at high speed. In addition, it is possible to generate routes adapted to small environmental changes.