Anytime Probabilistically Constrained Provably Convergent Online Belief Space Planning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 26 references that are in the map. First posted on arXiv 11 Nov 2024.
Builds on
11 of 26 references.
References · 11
- 2017Online algorithms for POMDPs with continuous state, action, and observation spacescited by 84
- 2020Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functionscited by 33
- 2022Optimality Guarantees for Particle Belief Approximation of POMDPscited by 20
- 2022Safe Output Feedback Motion Planning from Images via Learned Perception Modules and Contraction Theorycited by 19
- 2024ConstrainedZero: Chance-Constrained POMDP Planning using Learned Probabilistic Failure Surrogates and Adaptive Safety Constraintscited by 8
- 2022Online Planning for Constrained POMDPs with Continuous Spaces through Dual Ascentcited by 5
- 2022Shielding in Resource-Constrained Goal POMDPscited by 4
- 2023Simplified Continuous High Dimensional Belief Space Planning with Adaptive Probabilistic Belief-dependent Constraintscited by 4
- 2022Risk Aware Adaptive Belief-dependent Probabilistically Constrained Continuous POMDP Planningcited by 3
- 2023Recursively-Constrained Partially Observable Markov Decision Processescited by 2
- 2023Constrained Hierarchical Monte Carlo Belief-State Planningcited by 1
Built on by
Not cited yet.