A framework for an adaptive human-robot collaboration approach through perception-based real-time adjustments of robot behavior in industry

In this paper, a framework for a system that will supervise the robot's action and behavior in the human-robot shared workspace is proposed. The function of the robot supervision system is to adaptively control the robot motion based on the human actions in order to optimize the productivity of a task while ensuring human safety. The real-time perception of the human action and environment will be done using a motion capture setup. The inspiration for the framework based on a human behavior model is explained. The aspect of human-robot interaction in an industrial setup is also discussed. An evaluation criteria of the proposed system in terms of safety, performance and productivity is also presented.