From Space to Time: Enabling Adaptive Safety with Learned Value Functions via Disturbance Recasting

Sander Tonkens, Nikhil Uday Shinde, Azra Begzadić, Michael C. Yip, Jorge Cortes, Sylvia Lee Herbert

Keywords: Disturbance-aware safety, Reachability analysis, OOD Reliability

Abstract:

The wide 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 prior knowledge of all possible sources of model mismatch, in the form of disturbances, in the environment -- information that is typically unavailable 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 spatially varying disturbances as temporal variations, allowing 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.

Submission Number: 29