4 papers
An Update to the Level Set Theorems in Hamilton-Jacobi Reachability Analysis
Dylan Hirsch, William McEneaney, Jaime Fisac +2
Hamilton-Jacobi Reachability (HJR) is an important framework for controlling safety-critical systems despite uncertainty. Its theoretical underpinnings are rooted in Hamilton-Jacob…
Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination
Duy P. Nguyen, Kai-Chieh Hsu, Wenhao Yu +2
Despite the impressive recent advances in learning-based robot control, ensuring robustness to out-of-distribution conditions remains an open challenge. Safety filters can, in prin…
Human-AI Safety: A Descendant of Generative AI and Control Systems Safety
Andrea Bajcsy, Jaime F. Fisac
Artificial intelligence (AI) is interacting with people at an unprecedented scale, offering new avenues for immense positive impact, but also raising widespread concerns around the…
ISAACS: Iterative Soft Adversarial Actor-Critic for Safety
Kai-Chieh Hsu, Duy Phuong Nguyen, Jaime Fernández Fisac
The deployment of robots in uncontrolled environments requires them to operate robustly under previously unseen scenarios, like irregular terrain and wind conditions. Unfortunately…