Impedance Control of Exoskeleton Suit Based on Adaptive RBF Neural Network

Abstract—Exoskeleton suit is a typical human-machine system. Control the exoskeleton suit to track the pilot’s moving trajectory as well as to minimize the human-machine interaction force. The suit will help decrease the pilot’s power consumption and assist the pilot to carry heavy load. Impedance control was introduced to the control of exoskeleton suit. As the control laws that based on the dynamic model without model uncertainty compensation will increase the human-machine force, a RBF neural network with adaptive learning algorithm was used to compensate the model uncertainty. The stability analysis of the control law was given and the simulation results show the feasibility and validity of the proposed control law.

[1]  H. van der Kooij,et al.  Design of a series elastic- and Bowden cable-based actuation system for use as torque-actuator in exoskeleton-type training , 2005, 9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005..

[2]  Homayoon Kazerooni,et al.  Control and system identification for the Berkeley lower extremity exoskeleton (BLEEX) , 2006, Adv. Robotics.

[3]  Bruno Siciliano,et al.  Robot Force Control , 2000 .

[4]  Lihua Huang,et al.  On the Control of the Berkeley Lower Extremity Exoskeleton (BLEEX) , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[5]  Zhiyong Yang,et al.  Simulation Research of Exoskeleton Suit Based on Sensitivity Amplification Control , 2007, 2007 IEEE International Conference on Automation and Logistics.

[6]  Yoshiyuki Sankai,et al.  Power Assist System HAL-3 for Gait Disorder Person , 2002, ICCHP.

[7]  Yoshiyuki Sankai,et al.  Power assist control for walking aid with HAL-3 based on EMG and impedance adjustment around knee joint , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.