On Specifying for Trustworthiness

Abstract

As autonomous systems are becoming part of our daily lives, ensuring their trustworthiness is crucial. There are a number of techniques for demonstrating trustworthiness. Common to all these techniques is the need to articulate specifications. In this paper, we take a broad view of specification, concentrating on top-level requirements including but not limited to functionality, safety, security and other non-functional properties. The main contribution of this article is a set of high-level intellectual challenges for the autonomous systems community related to specifying for trustworthiness. We also describe unique specification challenges concerning a number of application domains for autonomous systems.

Elicitation of trustworthiness requirements for highly dexterous teleoperation systems with signal latency

“…There are several definitions of trust and trustworthiness reported in the literature with respect to human-robot teams (Abeywickrama et al, 2023 ). In this work, we have used the following definitions:…”

“…It is hard to gain, can easily be lost, and is subsequently far more difficult to regain (Lee and See, 2004 ). In contrast, trustworthiness is an inherent quality of a system which must be demonstrated to the user (Abeywickrama et al, 2023 ).…”

“…While a system might be technically safe and effective, it will not be put to use unless the users perceive it to be trustworthy (Abeywickrama et al, 2023 ). Despite trust being an evolving, subjective variable, we can identify the conditions under which a user will place their trust in a system, i.e., what is required for the system to be worthy of the user's trust.…”

“…Despite trust being an evolving, subjective variable, we can identify the conditions under which a user will place their trust in a system, i.e., what is required for the system to be worthy of the user's trust. Provided we have accurately captured what is required to make a system trustworthy, we can demonstrate that systems meet these requirements to ensure they are verifiably trustworthy (Abeywickrama et al, 2023 ).…”