Stop,Collaborate,and. . . Lessons Learned from Collaborative Human-AI System Development

Abstract

The U.S. military is procuring systems for complex joint fighting, requiring novel teaming approaches that maximize the capabilities of humans, artificial intelligence (AI), and autonomy. This case study describes a research effort to support aerial reconnaissance and target acquisition with crewed and uncrewed platforms. This effort integrated human factors with cutting-edge AI techniques, using Decision-Centered Design to identify requirements of the reconnaissance work and multiple AI development approaches. Lessons learned include the following. First, the team applied Roth and colleagues’ macrocognitive synthesized framework of decision making. Its emphasis on integrated human and AI sensemaking capabilities, as well as interfaces to facilitate common ground, facilitated cross-discipline collaboration. Second, the team collaborated on the goals and data of underlying AI features in parallel with human-AI interaction development. Third, scenario-based design was valuable to facilitate co-design activities. Embedding cognitive requirements within scenario storyboards made complex military work accessible to the full engineering team.