Leader–follower: Human-centered intention-guided controller for novel SuperLimb with application to load-carrying scenarios

Supernumerary robotic arms (SuperLimb) are a new type of wearable robot that works closely with humans as a third hand to augment human operation capability. Accurate conveyance of wearers’ intentions, allocation of roles, and human-centered interaction considerations are the key points in the process of human–SuperLimb collaboration. This paper proposes a human-centered intention-guided leader–follower controller that relies on the dynamic modeling of SuperLimb with application to load-carrying scenarios. The proposed leader–follower controller takes the human as the leader and the SuperLimb as the follower, achieving effective information communication, autonomous coordination, and good force compliance between SuperLimb, humans, and the environment under human safety assurance. First, the human–SuperLimb dynamic system is modeled to achieve force interaction with the environment and wearer. Second, to achieve the precise intention extraction of humans, pose data from five visual odometry sensors are fused to capture the human state, the generalized position, the velocity of hands, and the surface electromyography signals from two myoelectric bracelets sensors are processed to recognize the natural hand gestures during load-carrying scenarios by a designed Swin transformer network. Then, based on the real-time distance detection between human and mechanical limbs, the security assurance and force-compliant interaction of the human–SuperLimb system are realized. Finally, the human hand muscle intention recognition, human–robot safety strategy verification, and comparative load-carrying experiments with and without the proposed method are conducted on the SuperLimb prototype. Results showed that the task parameters are well estimated to produce more reasonable planning trajectories, and SuperLimb could well understand the wearer’s intentions to switch different SuperLimb actions. The proposed sensor-based human–robot communication framework motivates future studies of other collaboration scenes for SuperLimb applications.