Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning
Safety and liveness assurance is critical for autonomous robotic systems as the task is often specified with reaching certain goal conditions while staying clear of unacceptable failure modes. How can we obtain these guarantees in complex dynamics and environments?
@inproceedings{hsu2021safety,
author = {Kai-Chieh Hsu and Vicenç Rubies-Royo and Claire J. Tomlin and Jaime F. Fisac},
title = {Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning},
booktitle = {Proceedings of Robotics: Science and Systems},
year = {2021},
address = {Virtual},
month = {7},
doi = {10.15607/RSS.2021.XVII.077}}
