Distribution-Free Risk-Aware Planning and Control Under Uncertainty Using Conformal Spectral Risk Control

2026-06-02

AI Summary

This work addresses the limitations of traditional risk-aware control in dynamic, uncertain environments, where reliance on precise uncertainty distribution models often leads to failure. The paper proposes a novel distribution-free risk-aware model predictive control (MPC) framework that integrates conformal prediction with general spectral risk measures for the first time, offering statistically rigorous safety guarantees without requiring any assumptions about the underlying uncertainty distribution. By constructing prediction sets that adapt to observed data, the method ensures satisfaction of spectral risk constraints even under distributional misspecification. In vehicle obstacle avoidance simulations, the proposed approach significantly outperforms existing risk-aware MPC baselines, achieving higher safety levels and faster solution times while respecting user-specified risk thresholds.

Abstract

Safe navigation in dynamic and uncertain environments often relies on accurate estimation of, or assumptions about, the true underlying uncertainty. However, accurately characterizing the true uncertainty distribution is often difficult due to limited data or imperfect information. An incorrect understanding of the uncertainty and its associated risk may lead to dangerous decisions even under high levels of risk aversion. To address this issue, we propose a risk-aware model predictive control (RA-MPC) framework that incorporates prediction sets to guarantee risk control below a user-specified threshold without requiring assumptions about the underlying uncertainty distribution. To generate the prediction sets, we develop a distribution-free risk quantification framework that extends conformal risk control (CRC) to general spectral risk measures. We then show that incorporating the prediction sets into the MPC framework provides statistical safety guarantees in terms of spectral risk constraint satisfaction even under uncertainty misspecification. We validate the proposed framework in simulated vehicle obstacle avoidance scenarios, demonstrating improved safety and reduced solve time compared to a baseline RA-MPC framework.

Problem

• uncertainty
• risk-aware control
• distribution-free
• safe navigation
• spectral risk

Innovation

• distribution-free
• conformal risk control
• spectral risk measures
• risk-aware MPC
• prediction sets