Plan Understanding for Mixed-initiative Control of Autonomous systems (PUMA)

Future naval operations in the littoral environment will make use of unmanned vehicles to support a range of operations, including intelligence, surveillance, and reconnaissance (ISR) and mine warfare. Many challenges that arise in pursuing such capabilities are rooted in the need for effective communication between and among human operators and autonomous mission planning/execution systems, such that human operators can effectively manage complex, interdependent mission planning and execution by heterogeneous teams of unmanned systems. To address this need, we propose an iterative design, development, and evaluation process focused on Plan Understanding for Mixed-initiative control of Autonomous systems (PUMA). Our technical approach includes: 1) a structured operational analysis and cognitive task analysis process that elucidates the technical requirements for mixed-initiative operations; 2) a suite of advanced visualization and interactive analysis tools supporting intuitive interactions between operators and autonomous systems; 3) enhanced mixed-initiative interaction mechanisms that support the operator’s role as collaborative mission monitor in a manner that does not degrade situation awareness nor introduce cognitive overload; 4) development of a simulation-based testbed enabling the injection of advanced mixed-initiative capabilities into a flexible human-in-the-loop evaluation environment; and 5) a structured evaluation process based on cognitive walkthroughs of PUMA features by subject matter experts.