Online Adaptive Probabilistic Safety Certificate with Language Guidance

TL;DR

This paper introduces a language-guided adaptive safety framework for autonomous systems that guarantees long-term safety under uncertainty while accommodating human preferences.

Contribution

It presents a novel probabilistic safety certificate framework that integrates natural language inputs and Bayesian estimators for adaptive, personalized safety guarantees.

Findings

Enhanced safety-performance trade-offs demonstrated in simulations.

Framework adapts to changing environments and user preferences.

Code available at https://github.com/hoshino06/adaptive_lane_keeping.

Abstract

Achieving long-term safety in uncertain/extreme environments while accounting for human preferences remains a fundamental challenge for autonomous systems. Existing methods often trade off long-term guarantees for fast real-time control and cannot adapt to variability in human preferences or risk tolerance. To address these limitations, we propose a language-guided adaptive probabilistic safety certificate (PSC) framework that guarantees long-term safety for stochastic systems under environmental uncertainty while accommodating diverse human preferences. The proposed framework integrates natural-language inputs from users and Bayesian estimators of the environment into adaptive safety certificates that explicitly account for user preferences, system dynamics, and quantified uncertainties. Our key technical innovation leverages probabilistic invariance--a generalization of forward invariance to a probability space--to obtain myopic safety conditions with long-term safety guarantees. We validate the framework through numerical simulations of autonomous lane-keeping with human-in-the-loop guidance under uncertain and extreme road conditions, demonstrating enhanced safety-performance trade-offs, adaptability to changing environments, and personalization to different user preferences. Code is available at https://github.com/hoshino06/adaptive_lane_keeping.