From space to time: Enabling adaptive safety with learned value functions via disturbance recasting

arXiv preprint arXiv:2509.19597, 2025

Sander Tonkens, Nikhil Uday Shinde, Azra Begzadić, Michael C Yip, Jorge Cortés, Sylvia L Herbert

ArXiv PDF: https://arxiv.org/pdf/2509.19597

Abstract: The widespread deployment of autonomous systems in safety-critical environments such as urban air mobility hinges on ensuring reliable, performant, and safe operation under varying environmental conditions. One such approach, value function-based safety filters, minimally modifies a nominal controller to ensure safety. Recent advances leverage offline learned value functions to scale these safety filters to high-dimensional systems. However, these methods assume detailed priors on all possible sources of model mismatch, in the form of disturbances in the environment — information that is rarely available in real world settings. Even in well-mapped environments like urban canyons or industrial sites, drones encounter complex, spatially-varying disturbances arising from payload-drone interaction, turbulent airflow, and other environmental factors. We introduce SPACE2TIME, which enables safe and adaptive deployment of offline-learned safety filters under unknown, spatially-varying disturbances. The key idea is to reparameterize spatial variations in disturbance as temporal variations, enabling the use of precomputed value functions during online operation. We validate SPACE2TIME on a quadcopter through extensive simulations and hardware experiments, demonstrating significant improvement over baselines.

Tonkens et al. (2025) From space to time: Enabling adaptive safety with learned value functions via disturbance recasting, arXiv preprint arXiv:2509.19597.