Multi-Agent Assisted Shortest Path Planning using Monte Carlo Tree Search
Abhay Singh Bhadoriya, Swaroop Darbha, Sivakumar Rathinam, David W. Casbeer, Steven J. Rasmussen, Satyanarayana G. Manyam · AIAA SCITECH 2023 Forum · 2023
View Video Presentation: https://doi.org/10.2514/6.2023-2655.vid In this article, we propose a Monte Carlo Tree Search (MCTS) based anytime algorithm for the multi-agent Assisted Shortest Path Planning (ASPP) problem. The computation time required by the existing, exact algorithm for the ASPP increases exponentially with the complexity of the instances. The proposed MCTS algorithm can provide a feasible solution within a close range of the optimal cost for a fraction of computation time and can reach the optimal cost given sufficient time. Detailed computational analysis is presented to illustrate the effectiveness of the MCTS algorithm.