Safe POMDP Online Planning among Dynamic Agents via Adaptive Conformal Prediction

TL;DR

This paper introduces a safe POMDP online planning method that uses adaptive conformal prediction to provide probabilistic safety guarantees in environments with multiple dynamic agents, enhancing decision-making under uncertainty.

Contribution

It presents a novel approach combining trajectory prediction with adaptive conformal prediction to ensure safety in POMDP planning amidst dynamic agents.

Findings

Effectively maintains safety guarantees in dynamic environments.

Handles environments with hundreds of dynamic agents.

Outperforms existing methods in safety and efficiency.

Abstract

Online planning for partially observable Markov decision processes (POMDPs) provides efficient techniques for robot decision-making under uncertainty. However, existing methods fall short of preventing safety violations in dynamic environments. This work presents a novel safe POMDP online planning approach that maximizes expected returns while providing probabilistic safety guarantees amidst environments populated by multiple dynamic agents. Our approach utilizes data-driven trajectory prediction models of dynamic agents and applies Adaptive Conformal Prediction (ACP) to quantify the uncertainties in these predictions. Leveraging the obtained ACP-based trajectory predictions, our approach constructs safety shields on-the-fly to prevent unsafe actions within POMDP online planning. Through experimental evaluation in various dynamic environments using real-world pedestrian trajectory data, the proposed approach has been shown to effectively maintain probabilistic safety guarantees while accommodating up to hundreds of dynamic agents.