Multirobot Confidence and Behavior Modeling: An Evaluation of Semiautonomous Task Performance and Efficiency

There is considerable interest in multirobot systems capable of performing spatially distributed, hazardous, and complex tasks as a team leveraging the unique abilities humans automated machines working alongside each other. The limitations human perception cognition affect operators’ ability to integrate information from multiple mobile robots, switch between their spatial frames reference, divide attention among many sensory inputs command outputs. Automation necessary help operator manage increasing demands number robots (and humans) scales up. However, more automation does not necessarily equate better performance. A generalized robot confidence model was developed, which transforms key indicators value for enable robots’ adaptive behaviors. This implemented test platform with commanding trajectories using computer mouse an eye tracker providing gaze data used estimate dynamic attention. human-attention-based dynamically adapted behavior individual response successfully evaluated reveal evidence linking average search task performance efficiency. contributions this work provide essential steps toward effective operation unmanned vehicles perform distributed hazardous environments space exploration, defense, homeland security, rescue, other real-world applications.