Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods
This is an incremental survey paper that synthesizes existing methods for improving safety and transparency in robotics control, targeting researchers and practitioners in the field.
The paper surveys techniques for learning certificates alongside control policies to provide safety and stability guarantees for learning-enabled control systems in robotics, addressing the trade-off between performance and lack of guarantees.
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 techniques have emerged to provide these guarantees by learning certificates alongside control policies -- these certificates provide concise, data-driven proofs that guarantee the safety and stability of the learned control system. These methods not only allow the user to verify the safety of a learned controller but also provide supervision during training, allowing safety and stability requirements to influence the training process itself. In this paper, we provide a comprehensive survey of this rapidly developing field of certificate learning. We hope that this paper will serve as an accessible introduction to the theory and practice of certificate learning, both to those who wish to apply these tools to practical robotics problems and to those who wish to dive more deeply into the theory of learning for control.