Adaptive Modeling and Control of an Upper-Limb Rehabilitation Robot Using RBF Neural Networks
Robot-assisted rehabilitation following neurological injury is most successful when subject participation is maximized in the training tasks. Developing control strategies that can provide subject-specific assistance is accordingly an active area of research. For robot-assisted rehabilitation training, it is challenging to adapt the robotic assistance to each patient’s impairment, and model-based control methods in previous studies are difficult to implement because of the computational complexity of human-robot interaction dynamics and changes of human active efforts during rehabilitation exercises. This study implements adaptive modeling and control for an two-DOF upper-limb rehabilitation robot by combining an RBF-based feedforward controller with a feedback impedance controller. Simulation and experiment results show that, the RBF neural network is able to adaptively establish the human-robot dynamics as well as estimating the human efforts, and the impedance controller guarantees compliant human-robot interaction and regulates the maximal tolerated tracking error. Besides, the proposed controller is defined in the robot workspace, thus is easy to be generalized to be used for multi-DOFs exoskeleton-type rehabilitation robots.
KeywordsRehabilitation robot Adaptive control RBF neural networks Assist-as-needed
- 6.Prange, G.B., Jannink, M.J., Groothuis-Oudshoorn, C.G., Hermens, H.J., IJzerman, M.J.: Systematic review of the effect of robot-aided therapy on recovery of the hemiparetic arm after stroke. J. Rehabil. Res. Dev. 43(2), 171 (2006)Google Scholar
- 7.Reinkensmeyer, D.J., Wolbrecht, E., Bobrow, J.: A computational model of human-robot load sharing during robot-assisted arm movement training after stroke. In: Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 4019–4023 (2007)Google Scholar
- 12.Peng, L., Hou, Z.G., Peng, L., Wang, W.: Design of CASIA-ARM: a novel rehabilitation robot for upper limbs. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5611–5616 (2015)Google Scholar
- 16.Peng, L., Hou, Z.G., Wang, W.: Dynamic modeling and control of a parallel upper-limb rehabilitation robot. In: Proceedings of IEEE International Conference on Rehabilitation Robotics (ICORR), pp. 532–537 (2015)Google Scholar