Certifiable Trust in Autonomous Systems: Making the Intractable Tangible

This article discusses verification and validation (V&V) of autonomous systems, a concept that will prove to be difficult for systems that were designed to execute decision initiative. V&V of such systems should include evaluations of the trustworthiness of the system based on transparency i...

Full description

Saved in:
Bibliographic Details
Published in:The AI magazine 2017-09, Vol.38 (3), p.37-49
Main Authors: Lyons, Joseph B., Clark, Matthew A., Wagner, Alan R., Schuelke, Matthew J.
Format: Article
Language:English
Subjects:
Access control
Artificial intelligence
Authentication
Authentication (Identity)
Behavior
Certification
Computer engineering
Computer science
Decision making
Design
Human-computer interaction
Intelligent devices
Intelligent machines
Methods
Robotics
Software
Systems analysis
Training
Trust
Trust (Psychology)
Trustworthiness
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article discusses verification and validation (V&V) of autonomous systems, a concept that will prove to be difficult for systems that were designed to execute decision initiative. V&V of such systems should include evaluations of the trustworthiness of the system based on transparency inputs and scenario‐based training. Transparency facets should be used to establish shared awareness and shared intent among the designer, tester, and user of the system. The transparency facets will allow the human to understand the goals, social intent, contextual awareness, task limitations, analytical underpinnings, and team‐based orientation of the system in an attempt to verify its trustworthiness. Scenario‐based training can then be used to validate that programming in a variety of situations that test the behavioral repertoire of the system. This novel method should be used to analyze behavioral adherence to a set of governing principles coded into the system.
ISSN:0738-4602
2371-9621
DOI:10.1609/aimag.v38i3.2717