Wavenet control of a CyberForce system with human dynamic on passive haptic guidance tasks

Abstract

The human-robot physical interaction systems (HRpI), are platforms designed for the transmission of knowledge, from contact between a human kinesthetic, and a robotic device with inertial dynamic and tribological low. The dynamic of contact for the robotic system is modified to the inertial, gravitational forces and tribology (friction and mechanical vibrations); that represent uncertainty in the cooperative scheme the human operator responds differently in different experimental events. The robot control strategies are remarkably insufficient stabilization classical systems (conventional PID control), or nonlinear robust controls where no significant changes in the control gains based on the dynamic of interaction. In this research, the design and implementation of a Wavenet control (Multiresolution PID control based on Wavelet neural networks of second generation as a identification scheme) and first time is evaluated in a device with high technological performance Cyberforce) designed for positioning an exoskeleton CyberGrasp with the human operator in the loop.