Bayesian Estimation of Human Impedance and Motion Intention for Human–Robot Collaboration

This article proposes a Bayesian method to acquire the estimation of human impedance and motion intention in human–robot collaborative task. Combining with prior knowledge stiffness, estimated stiffness obeying Gaussian distribution is obtained by estimation, can be also estimated. An adaptive control strategy employed track target model neural networks are used compensate for uncertainties robotic dynamics. Comparative simulation results carried out verify effectiveness emphasize advantages proposed strategy. The experiment, performed on Baxter robot platform, illustrates good system performance.