The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems

Kai Chieh Hsu, Haimin Hu, Jaime F. Fisac

Research output: Contribution to journalReview articlepeer-review

6 Scopus citations

Abstract

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 toward more scalable synthesis, robust monitoring, and efficient intervention.

Original languageEnglish (US)
Pages (from-to)47-72
Number of pages26
JournalAnnual Review of Control, Robotics, and Autonomous Systems
Volume7
Issue number1
DOIs
StatePublished - Jul 10 2024
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Engineering (miscellaneous)
  • Human-Computer Interaction
  • Artificial Intelligence

Keywords

  • learning-based control
  • reinforcement learning
  • robot learning
  • robust control
  • runtime assurance
  • safe autonomy
  • safe learning
  • supervisory control

Fingerprint

Dive into the research topics of 'The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems'. Together they form a unique fingerprint.

Cite this