Adaptive regulation of assistance ‘as needed’ in robot-assisted motor skill learning and neuro-rehabilitation

We propose a general adaptive procedure to select the appropriate degree of assistance based on a Bayesian mechanism used to estimate psychophysical thresholds. This technique does not need an accurate model of learning and recovery processes. This procedure is validated in the context of a motor skill learning problem (control of a virtual object), in which the controller is used to gradually increase task difficulty as learning proceeds. These automatic adjustments of task difficulty or the degree of assistance can be used to promote not only motor skill learning but also neuromotor recovery.

[1]  P. Morasso,et al.  Braccio di Ferro: a new haptic workstation for neuromotor rehabilitation. , 2006, Technology and health care : official journal of the European Society for Engineering and Medicine.

[2]  P. Morasso,et al.  Bilateral robot therapy based on haptics and reinforcement learning: Feasibility study of a new concept for treatment of patients after stroke. , 2009, Journal of rehabilitation medicine.

[3]  J. Burdick,et al.  Implications of Assist-As-Needed Robotic Step Training after a Complete Spinal Cord Injury on Intrinsic Strategies of Motor Learning , 2006, The Journal of Neuroscience.

[4]  Christopher D Mah,et al.  Manipulating objects with internal degrees of freedom: evidence for model-based control. , 2002, Journal of neurophysiology.

[5]  F. Mussa-Ivaldi,et al.  Experimentally confirmed mathematical model for human control of a non-rigid object. , 2004, Journal of neurophysiology.

[6]  J. Patton,et al.  Can Robots Help the Learning of Skilled Actions? , 2009, Exercise and sport sciences reviews.

[7]  N. Hogan,et al.  Motions or muscles? Some behavioral factors underlying robotic assistance of motor recovery. , 2006, Journal of rehabilitation research and development.

[8]  Abhishek Gupta,et al.  Shared Control in Haptic Systems for Performance Enhancement and Training , 2006 .

[9]  A. Watson,et al.  Quest: A Bayesian adaptive psychometric method , 1983, Perception & psychophysics.

[10]  Robert Riener,et al.  A novel paradigm for patient-cooperative control of upper-limb rehabilitation robots , 2007, Adv. Robotics.

[11]  Timothy D. Lee,et al.  Motor Control and Learning: A Behavioral Emphasis , 1982 .

[12]  Jian-Hua Zhang,et al.  A nonlinear adaptive fuzzy approximator technique with its application to prediction of non-stationary EEG dynamics and estimation of single-sweep evoked potentials. , 2005, Technology and health care : official journal of the European Society for Engineering and Medicine.

[13]  Maura Casadio,et al.  Modeling the dynamics of the recovery process in robot therapy , 2009, 2009 Virtual Rehabilitation International Conference.

[14]  C. A. Trombly,et al.  Occupational Therapy for Physical Dysfunction , 1989 .

[15]  R A Scheidt,et al.  Persistence of motor adaptation during constrained, multi-joint, arm movements. , 2000, Journal of neurophysiology.

[16]  D.J. Reinkensmeyer,et al.  Optimizing Compliant, Model-Based Robotic Assistance to Promote Neurorehabilitation , 2008, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[17]  D. Reinkensmeyer,et al.  The effect of haptic guidance, aging, and initial skill level on motor learning of a steering task , 2009, Experimental Brain Research.

[18]  D. Reinkensmeyer,et al.  Human-robot cooperative movement training: Learning a novel sensory motor transformation during walking with robotic assistance-as-needed , 2007, Journal of NeuroEngineering and Rehabilitation.

[19]  R A Scheidt,et al.  Learning to move amid uncertainty. , 2001, Journal of neurophysiology.

[20]  M. Guadagnoli,et al.  Challenge Point: A Framework for Conceptualizing the Effects of Various Practice Conditions in Motor Learning , 2004, Journal of motor behavior.

[21]  Raul Benitez,et al.  Motor adaptation as a greedy optimization of error and effort. , 2007, Journal of neurophysiology.

[22]  Reza Shadmehr,et al.  Quantifying Generalization from Trial-by-Trial Behavior of Adaptive Systems that Learn with Basis Functions: Theory and Experiments in Human Motor Control , 2003, The Journal of Neuroscience.

[23]  S. Micera,et al.  On the use of divergent force fields in robot-mediated neurorehabilitation , 2008, 2008 2nd IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics.

[24]  Marcia K. O'Malley,et al.  On the Efficacy of Haptic Guidance Schemes for Human Motor Learning , 2009 .

[25]  P. Morasso,et al.  Self-adaptive robot training of stroke survivors for continuous tracking movements , 2010, Journal of NeuroEngineering and Rehabilitation.

[26]  Terence D. Sanger,et al.  Failure of Motor Learning for Large Initial Errors , 2004, Neural Computation.

[27]  D. Reinkensmeyer,et al.  Review of control strategies for robotic movement training after neurologic injury , 2009, Journal of NeuroEngineering and Rehabilitation.

[28]  Michael A. Arbib,et al.  Stroke Rehabilitation Reaches a Threshold , 2008, PLoS Comput. Biol..

[29]  David J. Reinkensmeyer,et al.  Haptic Guidance Can Enhance Motor Learning of a Steering Task , 2008, Journal of motor behavior.

[30]  N. Hogan,et al.  Robot-aided sensorimotor arm training improves outcome in patients with chronic stroke , 2003, Neurology.

[31]  Reza Shadmehr,et al.  Learning of action through adaptive combination of motor primitives , 2000, Nature.

[32]  Hermano Igo Krebs,et al.  Rehabilitation Robotics: Performance-Based Progressive Robot-Assisted Therapy , 2003, Auton. Robots.

[33]  Maura Casadio,et al.  Minimally assistive robot training for proprioception enhancement , 2009, Experimental Brain Research.