Safe Control With Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction Methods for Robotics and Control

• Published in: IEEE transactions on robotics Vol. 39; no. 3; pp. 1749 - 1767
• Main Authors: Dawson, Charles, Gao, Sicun, Fan, Chuchu
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Asymptotic stability; Certificates; Control systems; Deep learning in robotics and automation; formal methods in robotics and automation; Learning theory; Lyapunov methods; Measurement; neural certificates; robot safety; Robotics; Robots; Safety; Training; Trajectory; Trajectory tracking

Learning-enabled control systems have demonstrated impressive empirical performance on challenging control problems in robotics, but this performance comes at the cost of reduced transparency and lack of guarantees on the safety or stability of the learned controllers. In recent years, new technique...