Previous Knowledge Utilization In Non-Parametric Online Belief Space Planning

Online planning under uncertainty remains a critical challenge in robotics and autonomous systems. While tree search techniques are commonly employed to construct partial future trajectories within computational constraints, most existing methods discard information from previous planning sessions. This study presents a novel, computationally efficient approach that leverages historical planning data in current decision-making processes in a partially observable setting. We provide theoretical foundations for our information reuse strategy and introduce an algorithm based on Monte Carlo Tree Search (MCTS) that implements this approach.
Experimental results demonstrate that our method significantly reduces computation time while maintaining high performance levels. Our findings suggest that integrating historical planning information can substantially improve the efficiency of online decision-making in uncertain environments, paving the way for more responsive and adaptive autonomous systems.

The work is towards M.Sc. degree under the supervision of Associate Professor, Vadim Indelman, Head of the Autonomous Navigation and Perception Lab, Department of Aerospace Engineering, Technion – Israel Institute of Technology