Trustworthy Autonomy: A Roadmap to Assurance Part 1: System Effectiveness
Abstract
The Department of Defense (DoD) has invested significant effort over the past decade considering the role of artificial intelligence and autonomy in national security (e.g., Defense Science Board, 2012, 2016; Deputy Secretary of Defense, 2012; Endsley, 2015; Executive Order No. 13859, 2019; US Department of Defense, 2011, 2019; Zacharias, 2019a). However, these efforts were broadly scoped and only partially touched on how the DoD will certify the safety and performance of these systems. More recent work has done this big-picture thinking for the test and evaluation (T and E) community (e.g., Ahner and Parson, 2016;Haugh, Sparrow, and Tate, 2018; Porter et al., 2018; Sparrow, Tate, Biddle, Kaminski, and Madhavan, 2018; Zacharias, 2019b). In parallel, individual programs have been generating their own working-level solutions for their own particular use-cases and challenges. The framework proposed in the current work bridges the gap between the big picture policy recommendations already made and individual program needs. It is meant to serve as a roadmap framework that the T and E community can follow in order to provide evidence that artificial intelligence (AI)-enabled and autonomous systems function as intended. At times we echo broad policy recommendations made by others as they will also enable T and E activities. In other places we make more specific recommendations relating to test planning and analysis.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 2020
- Accession Number
- AD1131283
Entities
People
- Chad Bieber
- Daniel Porter
- Michael O McAnally
Organizations
- Institute for Defense Analyses