Adaptive Human Movement Compensation Control of Supernumerary Robotic Limb for Overhead Support Task With Non-Zero-Sum Differential Game Theory

The supernumerary robotic limb (SRL) mounted on the shoulder has been demonstrated to be able to serve as a third arm to assist human in overhead support task. However, the mechanical connection between the wearer and the SRL means that human operator’s movement will continually disturb the SRL and may lead to instability. Moreover, there may be physical conflicts between SRL and human operator due to their different intentions, which may potentially increase the load on human operator. Therefore, it’s necessary to control SRL to ensure stable supporting and transparent interaction. Here, we propose an adaptive controller for human movement compensation. Firstly, we model the human-SRL coordinative behavior based on non-zero-sum differential game theory aiming to enhance the support stability and reduce the operator’s load, which is a framework capable of dynamically regulating the control strategies between two interacting agents. We then implement an adaptive control strategy that adjusts the SRL’s input optimally responsive to the human operator’s input in the sense of Nash equilibrium to meet predefined control objectives. From experimental results during overhead support task, the proposed controller reduces the peak reaction force from 15.59 N to 4.50 N compared to the state-of-the-art controller that disregards human input while ensuring the stability of support, thereby providing advantage for human-SRL coordination in overhead support task. Note to Practitioners—To ensure optimal overhead assistance, the stability of the support and the safety of the human operator are of paramount importance. Therefore, this study investigates how to provide stable support and transparent interaction through movement compensation. Previous compensation methods lacked the understanding for the wearer and the optimal adjustment for the control of SRL. Consequently, this paper proposes a non-zero-sum differential game to model the desired behaviors between human operator and SRL. Furthermore, it solves for the optimal input to adaptively adjust the control gains of the SRL at the Nash equilibrium. The method proposed in this paper, compared to existing compensation methods, not only ensures the stability of the support but also enhances safety. Moreover, this approach avoids the need for expensive force sensing and precise human modeling, making it easy to implement and integrate into actual production environments.