Intelligent agents capable of learning and adapting to new data and changing contexts on the fly will require humans to fluidly adapt with their autonomous team members. Individualized, socio-emotionally intelligent technologies that continuously promote the emergence of team cohesion in novel groups of humans and intelligent agents are necessary to maximize collective adaption to rapidly evolving environmental demands. Here, we describe a virtual reality framework for the design and evaluation of operator-aware intelligent agents that can: prepare humans to work with autonomous technologies; train artificial intelligence to understand and evolve symbiotically with humans; and discover methods for enhancing performance of heterogenous multi-human multi-agent teams. Networked virtual reality clients allow human users to collaborate on tasks in an immersive, physics-based simulation environment. Integration of physiological monitoring devices enables biometrics to be collected and analyzed in real-time to provide individualized feedback and support. Combined with individual and group performance measures, objective metrics provide a basis for evaluating the impact and adaptability of artificial intelligence capabilities. To demonstrate this framework, we have developed a dismounted soldier squad combat scenario. Combat simulations are used to train algorithms to detect and track threats, predict outcomes, and provide feedback to coordinate squad tactics based on individual and group factors. Integration of these artificial intelligence capabilities into the virtual reality environment enable human-in-the-loop evaluation of their impact on multi-human multi-agent teamwork.
Keywords
ADAPTABILITY,AGENT-BASED SIMULATION,AUGMENTED AND VIRTUAL REALITY (AR/VR),HUMAN FACTORS,HUMAN PERFORMANCE
Additional Keywords