Deep Spatial-Temporal Model for rehabilitation gait: optimal trajectory generation for knee joint of lower-limb exoskeleton

Purpose The purpose of this paper is to model and predict suitable gait trajectories of lower-limb exoskeleton for wearer during rehabilitation walking. Lower-limb exoskeleton is widely used for assisting walk in rehabilitation field. One key problem for exoskeleton control is to model and predict suitable gait trajectories for wearer. Design/methodology/approach In this paper, the authors propose a Deep Spatial-Temporal Model (DSTM) for generating knee joint trajectory of lower-limb exoskeleton, which first leverages Long-Short Term Memory framework to learn the inherent spatial-temporal correlations of gait features. Findings With DSTM, the pathological knee joint trajectories can be predicted based on subject’s other joints. The energy expenditure is adopted for verifying the effectiveness of new recovery gait pattern by monitoring dynamic heart rate. The experimental results demonstrate that the subjects have less energy expenditure in new recovery gait pattern than in others’ normal gait patterns, which also means the new recovery gait is more suitable for subject. Originality/value Long-Short Term Memory framework is first used for modeling rehabilitation gait, and the deep spatial–temporal relationships between joints of gait data can obtained successfully.

[1]  Hong Cheng,et al.  Optimisation of Reference Gait Trajectory of a Lower Limb Exoskeleton , 2016, Int. J. Soc. Robotics.

[2]  Hyun-Chul Kim,et al.  Statistical method for prediction of gait kinematics with Gaussian process regression. , 2014, Journal of biomechanics.

[3]  Aaron M. Dollar,et al.  Lower Extremity Exoskeletons and Active Orthoses: Challenges and State-of-the-Art , 2008, IEEE Transactions on Robotics.

[4]  Yin Yang,et al.  5-Link model based gait trajectory adaption control strategies of the gait rehabilitation exoskeleton for post-stroke patients , 2010 .

[5]  Tingfang Yan,et al.  Review of assistive strategies in powered lower-limb orthoses and exoskeletons , 2015, Robotics Auton. Syst..

[6]  Chee-Meng Chew,et al.  Novel Functional Task-Based Gait Assistance Control of Lower Extremity Assistive Device for Level Walking , 2016, IEEE Transactions on Industrial Electronics.

[7]  Jun Morimoto,et al.  Estimating joint movements from observed EMG signals with multiple electrodes under sensor failure situations toward safe assistive robot control , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[8]  Anatol G. Feldman,et al.  Interjoint coordination in lower limbs during different movements in humans , 2002, Experimental Brain Research.

[9]  Khairul Salleh Mohamed Sahari,et al.  Multiple sequence behavior recognition on humanoid robot using long short-term memory (LSTM) , 2014, 2014 IEEE International Symposium on Robotics and Manufacturing Automation (ROMA).

[10]  Wei Meng,et al.  Recent development of mechanisms and control strategies for robot-assisted lower limb rehabilitation , 2015 .

[11]  Mohammad Taghi Karimi,et al.  Sensitivity analysis and comparison of two methods of using heart rate to represent energy expenditure during walking. , 2015, Work.

[12]  Adriano A. G. Siqueira,et al.  Gait Pattern Adaptation for an Active Lower-Limb Orthosis Based on Neural Networks , 2011, Adv. Robotics.

[13]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[14]  Cheong Boon Soh,et al.  Assessment of Foot Trajectory for Human Gait Phase Detection Using Wireless Ultrasonic Sensor Network , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[15]  Yong Du,et al.  Hierarchical recurrent neural network for skeleton based action recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[17]  Xinyu Wu,et al.  Deep rehabilitation gait learning for modeling knee joints of lower-limb exoskeleton , 2016, 2016 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[18]  S. Hesse,et al.  Upper and lower extremity robotic devices for rehabilitation and for studying motor control , 2003, Current opinion in neurology.

[19]  Lihua Huang,et al.  Hybrid Control of the Berkeley Lower Extremity Exoskeleton (BLEEX) , 2006, Int. J. Robotics Res..

[20]  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.

[21]  Lei Ren,et al.  Predictive modelling of human walking over a complete gait cycle. , 2007, Journal of biomechanics.

[22]  R. Laukkanen,et al.  Use of heart rate to predict energy expenditure from low to high activity levels. , 2003, International journal of sports medicine.

[23]  Robert Riener,et al.  Control strategies for active lower extremity prosthetics and orthotics: a review , 2015, Journal of NeuroEngineering and Rehabilitation.

[24]  Michael Goldfarb,et al.  A Preliminary Assessment of Legged Mobility Provided by a Lower Limb Exoskeleton for Persons With Paraplegia , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[25]  Kok-Meng Lee,et al.  Kinematic and dynamic analysis of an anatomically based knee joint. , 2010, Journal of biomechanics.

[26]  Carlo Mazzaferro.  Predicting Protein Binding Affinity With Word Embeddings and Recurrent Neural Networks , 2017, bioRxiv.

[27]  Yasuhiro Akiyama,et al.  Knee Joint Misalignment in Exoskeletons for the Lower Extremities: Effects on User's Gait , 2015, IEEE Transactions on Robotics.

[28]  Paolo Bonato,et al.  Robotically generated force fields for stroke patient pelvic obliquity gait rehabilitation , 2010, 2010 IEEE International Conference on Robotics and Automation.

[29]  Takahiro Kagawa,et al.  Optimization-Based Motion Planning in Joint Space for Walking Assistance With Wearable Robot , 2015, IEEE Transactions on Robotics.

[30]  H. van der Kooij,et al.  Reference Trajectory Generation for Rehabilitation Robots: Complementary Limb Motion Estimation , 2009, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[31]  Xiaohui Xie,et al.  Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks , 2016, AAAI.

[32]  Didier Pradon,et al.  Lower limb coordination patterns in hemiparetic gait: factors of knee flexion impairment. , 2011, Clinical biomechanics.

[33]  Michael Goldfarb,et al.  An Assistive Control Approach for a Lower-Limb Exoskeleton to Facilitate Recovery of Walking Following Stroke , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.