3D Free Reaching Movement Prediction of Upper-limb Based on Deep Neural Networks

Quantitative assessment of motor disorder is one of the main challenges in the field of stroke rehabilitation. This paper proposes a simplified kinematic model for human upper limb(UL) using seven main joints of both the dominant and non-dominant side. With this model, a deep neural network (DNN) is used to predict the 3D free reaching movement of UL of a healthy participant. The experimental results show that the prediction trajectories can achieve high similarities with trajectories of real movements, indicating the promising accuracy in 3D movement estimation of UL achieved by the DNN. With the capability of identifying specific reaching movements in realtime, the trajectories predicted by this data-driven model can be utilized to inform the rehabilitation assessment and training in the future studies as a personalized therapy approach.

[1]  S. Conforto,et al.  A bio-inspired controller of an upper arm model in a perturbed environment , 2007, 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information.

[2]  Rüdiger Dillmann,et al.  Learning Continuous Muscle Control for a Multi-joint Arm by Extending Proximal Policy Optimization with a Liquid State Machine , 2018, ICANN.

[3]  Michael I. Jordan,et al.  Optimal feedback control as a theory of motor coordination , 2002, Nature Neuroscience.

[4]  Natalia Dounskaia,et al.  Strategy of arm movement control is determined by minimization of neural effort for joint coordination , 2016, Experimental Brain Research.

[5]  P. Morasso.  Three dimensional arm trajectories , 1983, Biological Cybernetics.

[6]  Terrence J Sejnowski,et al.  Spectrum of power laws for curved hand movements , 2015, Proceedings of the National Academy of Sciences.

[7]  Bryan Buchholz,et al.  ISB recommendation on definitions of joint coordinate systems of various joints for the reporting of human joint motion--Part II: shoulder, elbow, wrist and hand. , 2005, Journal of biomechanics.

[8]  V. Sanguineti,et al.  Robotic Assessment of Upper Limb Motor Function After Stroke , 2012, American journal of physical medicine & rehabilitation.

[9]  M. Levin,et al.  Reduced Kinematic Redundancy and Motor Equivalence During Whole-Body Reaching in Individuals With Chronic Stroke , 2018, Neurorehabilitation and neural repair.

[10]  T. Flash,et al.  The coordination of arm movements: an experimentally confirmed mathematical model , 1985, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[11]  Rajiv Ranganathan,et al.  Learning to be Lazy: Exploiting Redundancy in a Novel Task to Minimize Movement-Related Effort , 2013, The Journal of Neuroscience.

[12]  Jessica L. Allen,et al.  Neuromechanical Principles Underlying Movement Modularity and Their Implications for Rehabilitation , 2015, Neuron.

[13]  Sahika Genc,et al.  Parametric system identification using deep convolutional neural networks , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[14]  Mindy F Levin,et al.  Upper Limb Coordination in Individuals With Stroke: Poorly Defined and Poorly Quantified , 2017, Neurorehabilitation and neural repair.

[15]  B. Wünsche,et al.  Assessment of movement quality in robot- assisted upper limb rehabilitation after stroke: a review , 2014, Journal of NeuroEngineering and Rehabilitation.

[16]  Jean-Paul Laumond,et al.  The formation of trajectories during goal‐oriented locomotion in humans. II. A maximum smoothness model , 2007, The European journal of neuroscience.

[17]  M. Naghavi.  Global, regional, and national burden of suicide mortality 1990 to 2016: systematic analysis for the Global Burden of Disease Study 2016 , 2019, BMJ.

[18]  C. Atkeson,et al.  Kinematic features of unrestrained vertical arm movements , 1985, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[19]  M. Owolabi,et al.  Stroke: a global response is needed , 2016, Bulletin of the World Health Organization.

[20]  Rong Song,et al.  Kinematic Outcome Measures using Target-Reaching Arm Movement in Stroke , 2017, Annals of Biomedical Engineering.

[21]  Wiebren Zijlstra,et al.  Assessment of motor recovery and decline. , 2002, Gait & posture.

[22]  Wulfram Gerstner,et al.  Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network , 2017, eLife.

[23]  P. Viviani,et al.  The law relating the kinematic and figural aspects of drawing movements. , 1983, Acta psychologica.

[24]  John McGuire,et al.  Bilateral assessment of functional tasks for robot-assisted therapy applications , 2011, Medical & Biological Engineering & Computing.

[25]  M. Kawato,et al.  Formation and control of optimal trajectory in human multijoint arm movement , 1989, Biological Cybernetics.

[26]  Z. Hasan,et al.  Optimized movement trajectories and joint stiffness in unperturbed, inertially loaded movements , 1986, Biological Cybernetics.

[27]  S. Black,et al.  The Fugl-Meyer Assessment of Motor Recovery after Stroke: A Critical Review of Its Measurement Properties , 2002, Neurorehabilitation and neural repair.

[28]  Erin W. Chambers,et al.  Homotopic Fréchet distance between curves or, walking your dog in the woods in polynomial time , 2010, Comput. Geom..

[29]  Chris Eliasmith,et al.  A spiking neural model of adaptive arm control , 2016, Proceedings of the Royal Society B: Biological Sciences.