Online Adaptive Probabilistic Safety Certificate with Language Guidance

Zhuoyuan Wang, Xiyu Deng, Hikaru Hoshino, Yorie Nakahira
Proceedings of The 8th Annual Learning for Dynamics and Control Conference, PMLR 331:872-903, 2026.

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 that integrate language guidance, model information, and quantified uncertainty. 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v331-wang26a, title = {Online Adaptive Probabilistic Safety Certificate with Language Guidance}, author = {Wang, Zhuoyuan and Deng, Xiyu and Hoshino, Hikaru and Nakahira, Yorie}, booktitle = {Proceedings of The 8th Annual Learning for Dynamics and Control Conference}, pages = {872--903}, year = {2026}, editor = {Sukhatme, Gaurav and Lindemann, Lars and Tu, Stephen and Wierman, Adam and Atanasov, Nikolay}, volume = {331}, series = {Proceedings of Machine Learning Research}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v331/main/assets/wang26a/wang26a.pdf}, url = {https://proceedings.mlr.press/v331/wang26a.html}, 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 that integrate language guidance, model information, and quantified uncertainty. 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.} }
Endnote
%0 Conference Paper %T Online Adaptive Probabilistic Safety Certificate with Language Guidance %A Zhuoyuan Wang %A Xiyu Deng %A Hikaru Hoshino %A Yorie Nakahira %B Proceedings of The 8th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2026 %E Gaurav Sukhatme %E Lars Lindemann %E Stephen Tu %E Adam Wierman %E Nikolay Atanasov %F pmlr-v331-wang26a %I PMLR %P 872--903 %U https://proceedings.mlr.press/v331/wang26a.html %V 331 %X 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 that integrate language guidance, model information, and quantified uncertainty. 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.
APA
Wang, Z., Deng, X., Hoshino, H. & Nakahira, Y.. (2026). Online Adaptive Probabilistic Safety Certificate with Language Guidance. Proceedings of The 8th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 331:872-903 Available from https://proceedings.mlr.press/v331/wang26a.html.

Related Material