A robust adaptive neural controller to drive a knee joint actuated orthosis

This paper presents a robust adaptive control of an actuated orthosis intended to assist the lower limb movements of dependent persons. The proposed controller, based on a MultiLayer Perception Neural Network (MLPNN) and considered as a black-box, does not require the dynamic model of lower limbs/orthosis. A neural identification is used to extract the principal components of the MLPNN input vector. The MLPNN is used to compensate the dynamic effects arising from the interaction between the human lower limb and the orthosis. MLPNN weights are adjusted online according to an adaption algorithm based on the Lyapunov analysis. Experiments, carried out on a healthy subject, show the good performance of the proposed controller in terms of trajectory tracking and robustness against external disturbances.

[1]  Reymond Clavel,et al.  Cyberthosis: Rehabilitation Robotics With Controlled Electrical Muscle Stimulation , 2007 .

[2]  Yacine Amirat,et al.  Commande Robuste d'un Robot Portable pour l'Assistance aux Mouvements des Membres Inférieurs d'un Sujet Humain , 2012 .

[3]  Frank L. Lewis,et al.  Robot Manipulator Control: Theory and Practice , 2003 .

[4]  Toshio Fukuda,et al.  Neuro-fuzzy control of a robotic exoskeleton with EMG signals , 2004, IEEE Transactions on Fuzzy Systems.

[5]  Roger Weber,et al.  Tools for understanding and optimizing robotic gait training. , 2006, Journal of rehabilitation research and development.

[6]  Frank L. Lewis,et al.  Multilayer neural-net robot controller with guaranteed tracking performance , 1996, IEEE Trans. Neural Networks.

[7]  Sunil K. Agrawal,et al.  Gait Rehabilitation With an Active Leg Orthosis , 2005 .

[8]  Frank L. Lewis,et al.  Neural Network Control Of Robot Manipulators And Non-Linear Systems , 1998 .

[9]  Amar Ramdane-Cherif,et al.  Stable neural network adaptive control of constrained redundant robot manipulators , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Günter Hommel,et al.  A Human--Exoskeleton Interface Utilizing Electromyography , 2008, IEEE Transactions on Robotics.

[11]  Y. Amirat,et al.  Sit-to-Stand movement assistance using an actuated knee joint orthosis , 2012, 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob).

[12]  Yoshiyuki Sankai,et al.  Working posture control of Robot Suit HAL for reducing structural stress , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[13]  Boubaker Daachi,et al.  Adaptive control of a human-driven knee joint orthosis , 2012, 2012 IEEE International Conference on Robotics and Automation.

[14]  D. Reinkensmeyer,et al.  Robotics for Gait Training After Spinal Cord Injury , 2005 .

[15]  Darwin G. Caldwell,et al.  Joint motion control of a powered lower limb orthosis for rehabilitation , 2006, Int. J. Autom. Comput..

[16]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[17]  Keijiro Yamamoto,et al.  Development of Power Assisting Suit for Assisting Nurse Labor , 2002 .

[18]  Jerry E. Pratt,et al.  The RoboKnee: an exoskeleton for enhancing strength and endurance during walking , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[19]  Boubaker Daachi,et al.  A stable neural adaptive force controller for a hydraulic actuator , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[20]  Arab Ali Chérif,et al.  A robust neural adaptive force controller for a C5 parallel robot , 2009, 2009 International Conference on Advanced Robotics.

[21]  Yacine Amirat,et al.  Knee joint movement assistance through robust control of an actuated orthosis , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  Constantinos Mavroidis,et al.  Control of electro-rheological fluid based resistive torque elements for use in active rehabilitation devices , 2007 .

[23]  Frank L. Lewis,et al.  Adaptive Feedback Linearization Using Efficient Neural Networks , 2001, J. Intell. Robotic Syst..

[24]  Yoshiaki Hayashi,et al.  Stairs-ascending/descending assist for a lower-limb power-assist robot considering ZMP , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[25]  Laura Gastaldi,et al.  Pneumatic active gait orthosis , 2001 .

[27]  Thierry Keller,et al.  Sliding mode closed-loop control of FES controlling the shank movement , 2004, IEEE Transactions on Biomedical Engineering.

[28]  Yu Zhang,et al.  Modeling and control of a curved pneumatic muscle actuator for wearable elbow exoskeleton , 2008 .

[29]  Arab Ali Chérif,et al.  A robust adaptive control of a parallel robot , 2010, Int. J. Control.

[30]  Ping Wang,et al.  A subject-based motion generation model with adjustable walking pattern for a gait robotic trainer: NaTUre-gaits , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.