Iterative learning of human partner's desired trajectory for proactive human-robot collaboration

A period-varying iterative learning control scheme is proposed for a robotic manipulator to learn a target trajectory that is planned by a human partner but unknown to the robot, which is a typical scenario in many applications. The proposed method updates the robot’s reference trajectory in an iterative manner to minimize the interaction force applied by the human. Although a repetitive human–robot collaboration task is considered, the task period is subject to uncertainty introduced by the human. To address this issue, a novel learning mechanism is proposed to achieve the control objective. Theoretical analysis is performed to prove the performance of the learning algorithm and robot controller. Selective simulations and experiments on a robotic arm are carried out to show the effectiveness of the proposed method in human–robot collaboration.