A Survey on Trust Metrics for Autonomous Robotic Systems

TL;DR

This survey reviews trust metrics for autonomous robotic systems, emphasizing the need for holistic security assessment that integrates multiple trust aspects to evaluate complex AI-enabled robots.

Contribution

It provides a comprehensive overview of existing trust metrics and discusses how to extend them for holistic system-level trust evaluation in autonomous robotics.

Findings

Existing trust metrics are fragmented and focus on subsets of system aspects.

A need exists for unified trust models that incorporate hardware, software, and cognitive factors.

Frameworks for extending trust metrics to holistic system assessment are proposed.

Abstract

This paper surveys the area of Trust Metrics related to security for autonomous robotic systems. As the robotics industry undergoes a transformation from programmed, task oriented, systems to Artificial Intelligence-enabled learning, these autonomous systems become vulnerable to several security risks, making a security assessment of these systems of critical importance. Therefore, our focus is on a holistic approach for assessing system trust which requires incorporating system, hardware, software, cognitive robustness, and supplier level trust metrics into a unified model of trust. We set out to determine if there were already trust metrics that defined such a holistic system approach. While there are extensive writings related to various aspects of robotic systems such as, risk management, safety, security assurance and so on, each source only covered subsets of an overall system and did not consistently incorporate the relevant costs in their metrics. This paper attempts to put this prior work into perspective, and to show how it might be extended to develop useful system-level trust metrics for evaluating complex robotic (and other) systems.