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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tonkens, Sander, Shinde, Nikhil Uday, Begzadić, Azra, Yip, Michael C., Cortés, Jorge, Herbert, Sylvia L.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914053694160896
author Tonkens, Sander
Shinde, Nikhil Uday
Begzadić, Azra
Yip, Michael C.
Cortés, Jorge
Herbert, Sylvia L.
author_facet Tonkens, Sander
Shinde, Nikhil Uday
Begzadić, Azra
Yip, Michael C.
Cortés, Jorge
Herbert, Sylvia L.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Space to Time: Enabling Adaptive Safety with Learned Value Functions via Disturbance Recasting
Tonkens, Sander
Shinde, Nikhil Uday
Begzadić, Azra
Yip, Michael C.
Cortés, Jorge
Herbert, Sylvia L.
Robotics
Systems and Control
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.
title From Space to Time: Enabling Adaptive Safety with Learned Value Functions via Disturbance Recasting
topic Robotics
Systems and Control
url https://arxiv.org/abs/2509.19597