Estimation of human impedance and motion intention for constrained human–robot interaction

In this paper, a complete framework for safe and efficient physical human-robot interaction (pHRI) is developed for robot by considering both issues of adaptation to the human partner and ensuring the motion constraints during the interaction. We consider the robot's learning of not only human motion intention, but also the human impedance. We employ radial basis function neural networks (RBFNNs) to estimate human motion intention in real time, and least square method is utilized in robot learning of human impedance. When robot has learned the impedance information about human, it can adjust its desired impedance parameters by a simple tuning law for operative compliance. An adaptive impedance control integrated with RBFNNs and full-state constraints is also proposed in our work. We employ RBFNNs to compensate for uncertainties in the dynamics model of robot and barrier Lyapunov functions are chosen to ensure that full-state constraints are not violated in pHRI. Results in simulations and experiments show the better performance of our proposed framework compared with traditional methods.