Reinforcement Learning for Risk Adaptation via Differentiable CVaR Barrier Functions

TL;DR

This paper introduces a reinforcement learning framework with differentiable CVaR barrier functions for risk-aware crowd navigation, enabling efficient and safe robot movement in uncertain, crowded environments.

Contribution

It presents an end-to-end risk adaptation method combining RL with a CVaR safety layer, explicitly enforcing probabilistic safety constraints in dynamic environments.

Findings

Outperforms existing methods in safety, efficiency, and generalization.

Enables context-aware risk adaptation in crowded, uncertain environments.

Demonstrates robustness across different obstacle densities and robot models.

Abstract

Planning through crowded environments under uncertain obstacle motions remains difficult, as stochastic interactions often induce overly conservative behavior or reduced efficiency. To address this challenge, we propose an end-to-end risk adaptation framework for crowd navigation under obstacle-motion uncertainty modeled by a Gaussian mixture model. The framework combines reinforcement learning~(RL) with a differentiable quadratic-program safety layer based on Conditional Value-at-Risk~(CVaR) barrier functions, jointly learning nominal control input, risk level, and safety margin and enforcing explicit probabilistic safety constraints. This design enables context-aware adaptation, promoting efficient behavior while invoking caution only when necessary. We conduct extensive evaluations in dynamic, uncertain, and crowded environments across varying obstacle densities and robot models, and further assess generalization under three out-of-distribution cases. Comparisons across optimization-based, RL-based, and integrated RL and optimization methods are provided, and the proposed method is shown to deliver the strongest overall performance in safety, efficiency, and generalization under uncertainty.