# Safe POMDP Online Planning among Dynamic Agents via Adaptive Conformal Prediction

arXiv: https://arxiv.org/abs/2404.15557 · HTML: https://mlsanity.com/paper/2404.15557/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2024.

## Built on by (most cited first, 8 of 8)

- [MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving](https://mlsanity.com/paper/2512.03795/) (2025)
- [Adaptive Shielding for Safe Reinforcement Learning under Hidden-Parameter Dynamics Shifts](https://mlsanity.com/paper/2506.11033/) (2025)
- [Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation](https://mlsanity.com/paper/2510.26026/) (2025)
- [When Environments Shift: Safe Planning with Generative Priors and Robust Conformal Prediction](https://mlsanity.com/paper/2602.12616/) (2026)
- [DoublyAware: Dual Planning and Policy Awareness for Temporal Difference Learning in Humanoid Locomotion](https://mlsanity.com/paper/2506.12095/) (2025)
- [Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed](https://mlsanity.com/paper/2601.21094/) (2026)
- [Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning](https://mlsanity.com/paper/2605.25267/) (2026)
- [Multi-Agent Deferred-Decision Trajectory Optimization with Anytime-Valid Target Retention for Moving Candidates](https://mlsanity.com/paper/2610.17003/) (2026)

## Abstract (arXiv)

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.