Trusted Distributed Human-Machine Teaming for Safe and Effective Space-based Missions

Trusted Distributed Human-Machine Teaming for Safe and Effective Space-based Missions Trusted Distributed Human-Machine Teaming for Safe and Effective Space-based Missions Trusted Distributed Human-Machine Teaming for Safe and Effective Space-based Missions - Year Two Option Year 1 Summary A challenge of space-based missions is effective teaming in a geographically and temporally (i.e., spatio-temporal) distributed environment. The geographic distribution of teammates coupled with the variable communication latency challenges effective teamwork. This challenge is exacerbated by the team complexity in a heterogeneous multiteam system composed of humans, robots, and Artificial Intelligent (AI) agents. The long-term objective of this research is to develop an AI agent that monitors distributed human machine teams (HMTs) in space-based missions to identify potential team states (e.g., fatigued, conflict, trust) and intervene when needed to improve teamwork and team effectiveness. In the first year of this effort our goal was to demonstrate initial capability for AI monitoring and assessment for effective space HMTs. The Year 1 work had five objectives: 1) Identify unique space HMT issues (e.g., variable latency) and example scenarios that reflect those issues through interviews with subject matter experts; 2) Implement one or more scenarios in the distributed HMT testbed; 3) Identify sensors (communication channels, physiological sensors, equipment sensors) to provide signals for the layered dynamics in the scenarios, including sensors that can be used to identify cognitive state; 4) Collect demonstration data (using ourselves as participants) in the testbed; and 5) Analyze data to evaluate capability to assess team state and effectiveness. To accomplish these objectives, we leveraged transdisciplinary collaboration among experts in space missions, human-machine teaming and robotics, machine learning, and dynamical systems methodology. Year 2 Objectives I. Obtain subject matter expert feedback on the scenario developed in Year 1. Specifically identify scenario activities or interactions that are problematic (e.g., not realistic, not technically feasible) and identify challenges not addressed in current scenario. II. Identify the sensors that generated the data most predictive of teaming challenges and possible new sensors. III. Develop 2-3 new scenarios that take into account the issues identified in Objectives numbers 1 and 2 and implement the scenarios in the distributed human-machine teaming testbed. IV. Collect demonstration data (using ourselves as participants) in the testbed. V. Analyze data to evaluate new capability to assess team state and effectiveness.