The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems
This work addresses safety-critical control for autonomous robots, but it is incremental as it provides a review and unification of existing techniques rather than introducing new methods.
The paper tackles the challenge of ensuring safe operation in autonomous systems by reviewing safety filter approaches, proposing a unified framework to integrate model-based and data-driven methods, and highlighting connections to improve scalability and robustness.
Recent years have seen significant progress in the realm of robot autonomy, accompanied by the expanding reach of robotic technologies. However, the emergence of new deployment domains brings unprecedented challenges in ensuring safe operation of these systems, which remains as crucial as ever. While traditional model-based safe control methods struggle with generalizability and scalability, emerging data-driven approaches tend to lack well-understood guarantees, which can result in unpredictable catastrophic failures. Successful deployment of the next generation of autonomous robots will require integrating the strengths of both paradigms. This article provides a review of safety filter approaches, highlighting important connections between existing techniques and proposing a unified technical framework to understand, compare, and combine them. The new unified view exposes a shared modular structure across a range of seemingly disparate safety filter classes and naturally suggests directions for future progress towards more scalable synthesis, robust monitoring, and efficient intervention.