A Human–Robot Collaboration Control Framework for Supernumerary Robotic Limbs

In this paper, a novel human–robot collaboration (HRC) framework is proposed to enhance the capability of Supernumerary Robotic Limbs (SRLs). The proposed framework consists of three key modules: human motion intention recognition, disturbance rejection control, and obstacle avoidance, all of which are crucial for SRLs in the process of HRC. First, a motion intention method based on the autoregressive model is proposed to predict human motion, to improve task execution during HRC. Second, a control strategy based on a Tanh‐type Barrier Lyapunov function is introduced to ensure bounded outputs and smooth operation in physical interactions with environment. Third, to enhance the collaboration between SRL and humans, dynamic obstacle avoidance based on human skeleton recognition and inverse kinematics is incorporated into the framework. The proposed framework is demonstrated by the human‐SRL collaborative task, and the experimental results indicated that the performances can be improved with our framework.