Path Planning in Dynamic Environments using Generative RNNs and Monte Carlo Tree Search
Stuart Eiffert,He Kong,Navid Pirmarzdashti,Salah Sukkarieh,Stuart Eiffert,He Kong,Navid Pirmarzdashti,Salah Sukkarieh
State of the art methods for robotic path planning in dynamic environments, such as crowds or traffic, rely on hand crafted motion models for agents. These models often do not reflect interactions of agents in real world scenarios. To overcome this limitation, this paper proposes an integrated path planning framework using generative Recurrent Neural Networks within a Monte Carlo Tree Search (MCTS...
