Role adaptation of human and robot in collaborative tasks

Abstract

Abstract-In this paper, a role adaptation method is developed for human-robot collaboration based on game theory. This role adaptation is engaged whenever the interaction force changes, causing the proportion of control sharing between human and robot to vary. In one boundary condition, the robot takes full control of the system when there is no human intervention. In the other boundary condition, it becomes a follower when the human exhibits strong intention to lead the task. Experimental results show that the proposed method yields better overall performance than fixed-role interactions.

Decision-Making Model for Adaptive Impedance Control of Teleoperation Systems

“…[18], [24]), but also other scenarios in physical human-robot interaction (consider e.g. a mobility assistant [36], human-robot collaborative manipulation [15], [16], rehabilitation [37]) or training with a haptic aid [38]. While in our considered scenario we assume the path to be known to the assistance, in reality this can be easily realized using a path planning algorithm and a map of the environment.…”

“…This function, commonly noted as α, estimates the assistance level based on metrics of task performance [1], interaction with the user [9], [21] or any other task information [6], [14], [17]. Recently, concepts borrowed from game theory have been proposed in [15] to give the robot a more human-like reaction.…”

“…In [15] authors formulate a common cost function for task performance and an optimal control law for position and force based on Nash's equilibria. When human and robot disagree, the control law is adapted to minimize the error between the force exerted by the user and the optimal force, which allows the system to adapt to unexpected situations.…”

“…Haptic assistance has been successfully implemented in many areas of physical human-machine interaction, including computer games [3], [4] or driver assistance systems [5]. Haptic assistance has been also implemented in mobile robots commanded at distance [6], [7], [8], [9], teleoperation interfaces [10], [11], haptic devices for training [12], [13], [14], and joint human-robot object transportation [15], [16], [17].…”

Control sharing in human-robot team interaction

“…[68]. Recently, the arbitration based on the estimation of human trust and self-confidence has been validated.…”