Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Grand Challenges in the Verification of Autonomous Systems

Kevin Leahy, Hamid Asgari, Louise A. Dennis, Martin S. Feather, Michael Fisher, Javier Ibanez-Guzman, Brian Logan, Joanna I. Olszewska, Signe Redfield

TL;DR

This paper highlights viewpoints of the Roadmap Working Group of the IEEE Robotics and Automation Society Technical Committee for Verification of Autonomous Systems, identifying these grand challenges, and providing a vision for future research efforts that will be needed to address them.

Abstract

Autonomous systems use independent decision-making with only limited human intervention to accomplish goals in complex and unpredictable environments. As the autonomy technologies that underpin them continue to advance, these systems will find their way into an increasing number of applications in an ever wider range of settings. If we are to deploy them to perform safety-critical or mission-critical roles, it is imperative that we have justified confidence in their safe and correct operation. Verification is the process by which such confidence is established. However, autonomous systems pose challenges to existing verification practices. This paper highlights viewpoints of the Roadmap Working Group of the IEEE Robotics and Automation Society Technical Committee for Verification of Autonomous Systems, identifying these grand challenges, and providing a vision for future research efforts that will be needed to address them.

Grand Challenges in the Verification of Autonomous Systems

TL;DR

This paper highlights viewpoints of the Roadmap Working Group of the IEEE Robotics and Automation Society Technical Committee for Verification of Autonomous Systems, identifying these grand challenges, and providing a vision for future research efforts that will be needed to address them.

Abstract

Autonomous systems use independent decision-making with only limited human intervention to accomplish goals in complex and unpredictable environments. As the autonomy technologies that underpin them continue to advance, these systems will find their way into an increasing number of applications in an ever wider range of settings. If we are to deploy them to perform safety-critical or mission-critical roles, it is imperative that we have justified confidence in their safe and correct operation. Verification is the process by which such confidence is established. However, autonomous systems pose challenges to existing verification practices. This paper highlights viewpoints of the Roadmap Working Group of the IEEE Robotics and Automation Society Technical Committee for Verification of Autonomous Systems, identifying these grand challenges, and providing a vision for future research efforts that will be needed to address them.

Paper Structure

This paper contains 13 sections, 2 figures.

Table of Contents

  1. Introduction
  2. The Verification Process
  3. What Makes Autonomy Difficult?
  4. Uncertainty
  5. Context
  6. Recommendations
  7. Requirements
  8. Semantics
  9. Operating envelopes
  10. Novel verification techniques
  11. A wider view of verification
  12. Timeline and Conclusion
  13. Acknowledgements

Figures (2)

  • Figure 1: The verification process directs the generation of evidence that will demonstrate the system meets its requirements. It specifies the approach, or combination of approaches, to be followed. These in turn use tools, algorithms, and techniques to generate verification evidence.
  • Figure 2: The recommendations identified in Sec. \ref{['sec:recommendations']}, categorized according to the components of verification identified in Fig. \ref{['fig:verification_process']}, and ordered by how soon they are likely to be able to be put into practice. Items appearing closer to the top are shorter-term objectives than those lower down, but no specific timescale is implied.