A Scalable Command and Control System for Human-Machine Work Systems

The emergence of complex work systems has yielded new challenges for efficient and reliable collaboration between humans and machines. Robots are now working autonomously beside human counterparts to accomplish critical tasks; however fully autonomous robot action is still considered unreliable. This paper examines an approach to increasing the robustness, reliability, and efficiency of human-machine work systems by dynamically establishing dynamic control relationships between humans and robots as well as altering the effective autonomy manifested by each robot. The process involves workload estimation to determine the parameters of the system, workload optimization to analyze and modify system parameters, and workload mitigation to enact these modifications in a non-intrusive manner. Furthermore, heuristic approaches to approximating an optimal system configuration for real-time environments are also addressed and simulated.