Anytime Probabilistically Constrained Provably Convergent Online Belief Space Planning

TL;DR

This paper introduces an anytime Monte Carlo Tree Search method for online belief space planning that guarantees safety and improves action quality in continuous domains without requiring search convergence.

Contribution

It presents a novel anytime MCTS algorithm for belief space planning that ensures safety and convergence in probability, with extensive simulation validation.

Findings

The method guarantees safety at any time during search.

It outperforms baselines in safety and objective metrics.

The approach effectively revises search tree values after pruning.

Abstract

Taking into account future risk is essential for an autonomously operating robot to find online not only the best but also a safe action to execute. In this paper, we build upon the recently introduced formulation of probabilistic belief-dependent constraints. We present an anytime approach employing the Monte Carlo Tree Search (MCTS) method in continuous domains. Unlike previous approaches, our method assures safety anytime with respect to the currently expanded search tree without relying on the convergence of the search. We prove convergence in probability with an exponential rate of a version of our algorithms and study proposed techniques via extensive simulations. Even with a tiny number of tree queries, the best action found by our approach is much safer than the baseline. Moreover, our approach constantly finds better than the baseline action in terms of objective. This is because we revise the values and statistics maintained in the search tree and remove from them the contribution of the pruned actions.