A human motion prediction algorithm based on HSMM for SIAT's exoskeleton

Getting the exoskeleton pilot's motion intent is very important for exoskeleton control. In this paper, a new approach to predict human motion is proposed. The prediction method is based on Hidden Semi-Markov Models. The orientation of the pilot's segment is collected by the Inertial Measurement Unit. The Adaptive Boosting algorithm is adopted to classify the orientation data into labels. The sequence of motion labels is inputted into Hidden Semi-Markov Models for motion prediction. The experimental data validate the proposed method.

[1]  Shunzheng Yu,et al.  Practical implementation of an efficient forward-backward algorithm for an explicit-duration hidden Markov model , 2006, IEEE Transactions on Signal Processing.

[2]  H. Kazerooni,et al.  Biomechanical design of the Berkeley lower extremity exoskeleton (BLEEX) , 2006, IEEE/ASME Transactions on Mechatronics.

[3]  Trevor Hastie,et al.  Multi-class AdaBoost ∗ , 2009 .

[4]  Jun Morimoto,et al.  Extraction of latent kinematic relationships between human users and assistive robots , 2012, 2012 IEEE International Conference on Robotics and Automation.

[5]  Yasuhisa Hasegawa,et al.  Sit-to-Stand and Stand-to-Sit Transfer Support for Complete Paraplegic Patients with Robot Suit HAL , 2010, Adv. Robotics.

[6]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[7]  Yoshiyuki Sankai,et al.  Voluntary motion support control of Robot Suit HAL triggered by bioelectrical signal for hemiplegia , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[8]  Ephrahim Garcia,et al.  解説 Exoskeletons for Human Performance Augmentation(EHPA): A Program Summary (特集 ウェアラブルロボティクス) , 2002 .

[9]  J. Edward Colgate,et al.  A 1-DOF assistive exoskeleton with virtual negative damping: effects on the kinematic response of the lower limbs , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Xinyu Wu,et al.  A human motion prediction algorithm for Non-binding Lower Extremity Exoskeleton , 2015, 2015 IEEE International Conference on Information and Automation.

[11]  H. Kazerooni,et al.  Hybrid Control of the Berkeley Lower Extremity Exoskeleton (BLEEX) , 2005 .