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 offers 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) for assessing 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.

翻译：部分可观测马尔可夫决策过程（POMDP）的在线规划为机器人不确定环境下的决策提供了高效技术。然而，现有方法在动态环境中难以防止安全违规行为。本文提出一种新颖的安全POMDP在线规划方法，可在多动态智能体共存环境中提供概率性安全保障。该方法利用动态智能体的数据驱动轨迹预测模型，并采用自适应保形预测（ACP）评估这些预测中的不确定性。基于ACP轨迹预测结果，该方法通过在线构建安全防护盾，防止POMDP在线规划中的不安全动作。利用真实行人轨迹数据在多种动态环境中的实验评估表明，所提方法在容纳多达数百个动态智能体的同时，能有效维持概率性安全保障。