A Gaussian Mixture Framework for Co-Operative Rehabilitation Therapy in Assistive Impedance-Based Tasks

Rehabilitation robots can aid patients to practice activities of daily living in order to enhance muscle strength and recover motor functions. In this paper, we focus on robot-assisted rehabilitation for co-operative therapy tasks that elicit impedance-based behaviors from the patient. For instance, if the rehabilitation robot is controlled to behave as a self-closing door and if pulling this simulated door open is the therapy task the patient needs to complete, the patient's hand should display a minimum required impedance to complete the task. When a patient is unable to complete the task, determining the minimum assistance to be provided to the patient by the rehabilitation robot such that the task can be accomplished is of interest. In this paper, we compare the impedance behavior of a therapist in multiple trials of the task with that of the patient using a learning from demonstration (LfD) technique that utilizes Gaussian mixture models. First and during the demonstration phase, the therapist performs the tasks individually so that the robot gains insight into how a healthy person would perform the task. Next and during the reproduction phase, the robot will co-operate with the patient in the therapist's absence and provide him/her with adaptive external assistance on a patient-specific and as-needed basis so that the task can be completed. To encourage active participation, provision of assistance to the patient is coupled to the variability observed in the therapist's behavior across various trials of the task. Therefore, the presented framework transfers the constraints and underlying characteristics of a given impedance-based task to the rehabilitation robot leading to co-operative interaction between the robot and the patient where the robot provides just-enough assistance. Experimental results involving 1-D and 2-D impedance-based tasks show that the proposed framework effectively provides the patient with assistance as needed during co-operative therapy.

[1]  Oussama Khatib,et al.  A unified approach for motion and force control of robot manipulators: The operational space formulation , 1987, IEEE J. Robotics Autom..

[2]  Jiping He,et al.  Cooperative and active assistance based interactive therapy , 2010, IEEE/ICME International Conference on Complex Medical Engineering.

[3]  W. Wong,et al.  On ψ-Learning , 2003 .

[4]  Joel W. Burdick,et al.  Assist-as-needed training paradigms for robotic rehabilitation of spinal cord injuries , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

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

[6]  Jun Nakanishi,et al.  Movement imitation with nonlinear dynamical systems in humanoid robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[7]  Ali Utku Pehlivan,et al.  A Subject-Adaptive Controller for Wrist Robotic Rehabilitation , 2015, IEEE/ASME Transactions on Mechatronics.

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

[9]  Darwin G. Caldwell,et al.  Handling of multiple constraints and motion alternatives in a robot programming by demonstration framework , 2009, 2009 9th IEEE-RAS International Conference on Humanoid Robots.

[10]  Philippe Fraisse,et al.  Experimental study on haptic communication of a human in a shared human-robot collaborative task , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Stephen Paul Buerger,et al.  Stable, high-force, low-impedance robotic actuators for human-interactive machines , 2005 .

[12]  Masayuki Inaba,et al.  Intent imitation using wearable motion capturing system with on-line teaching of task attention , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[13]  M. Popovic,et al.  Relationship between clinical assessments of function and measurements from an upper-limb robotic rehabilitation device in cervical spinal cord injury , 2022 .

[14]  L. Sucheston.  Modern Probability Theory and its Applications. , 1961 .

[15]  Antonio Frisoli,et al.  An EMG-Controlled Robotic Hand Exoskeleton for Bilateral Rehabilitation , 2015, IEEE Transactions on Haptics.

[16]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[17]  Aude Billard,et al.  Dynamical System Modulation for Robot Learning via Kinesthetic Demonstrations , 2008, IEEE Transactions on Robotics.

[18]  Stefan Schaal,et al.  Biologically-inspired dynamical systems for movement generation: Automatic real-time goal adaptation and obstacle avoidance , 2009, 2009 IEEE International Conference on Robotics and Automation.

[19]  Nikolaos G. Tsagarakis,et al.  Statistical dynamical systems for skills acquisition in humanoids , 2012, 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012).

[20]  Darwin G. Caldwell,et al.  Learning force and position constraints in human-robot cooperative transportation , 2014, The 23rd IEEE International Symposium on Robot and Human Interactive Communication.

[21]  Haiying She.  Programming by demonstration in the application of rehabilitation robots , 2005 .

[22]  Hyunchul Kim,et al.  Kinematic Data Analysis for Post-Stroke Patients Following Bilateral Versus Unilateral Rehabilitation With an Upper Limb Wearable Robotic System , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[23]  Aude Billard,et al.  On Learning, Representing, and Generalizing a Task in a Humanoid Robot , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[24]  Marcia Kilchenman O'Malley,et al.  Adaptive control of a serial-in-parallel robotic rehabilitation device , 2013, 2013 IEEE 13th International Conference on Rehabilitation Robotics (ICORR).

[25]  Alon Wolf,et al.  An Adaptive Home-Use Robotic Rehabilitation System for the Upper Body , 2014, IEEE Journal of Translational Engineering in Health and Medicine.

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

[27]  Carme Torras,et al.  Learning Collaborative Impedance-Based Robot Behaviors , 2013, AAAI.