There is no abstract available for this article.
This work was supported by National Key Research and Development Program of China (Grant No. 2017YFB1302300) and National Natural Science Foundation of China (Grant Nos. 61673088, 61503060). Moreover, the authors gratefully acknowledge the contribution of an anonymous reviewer's comments.
Appendixes A–C.
[1] Huang R, Cheng H, Chen Q, et al. Interactive learning for sensitivity factors of a human-powered augmentation lower exoskeleton. In: Proceedings of IEEE International Conference on Intelligent Robots and Systems (IROS), Hamburg, 2015. 6409--6415. Google Scholar
[2] Huang R, Cheng H, Guo H, et al. Hierarchical interactive learning for a human-powered augmentation lower exoskeleton. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), Stockholm, 2016. 257--263. Google Scholar
[3] Huang R, Cheng H, Guo H. Hierarchical learning control with physical human-exoskeleton interaction. Inf Sci, 2018, 432: 584-595 CrossRef Google Scholar
[4] Lillicrap T P, Hunt J J, Pritzel A. Continuous control with deep reinforcement learning. 2015,. arXiv Google Scholar
[5] Grondman I, Busoniu L, Lopes G A D. A Survey of Actor-Critic Reinforcement Learning: Standard and Natural Policy Gradients. IEEE Trans Syst Man Cybern C, 2012, 42: 1291-1307 CrossRef Google Scholar
[6] Kazerooni H, Racine J L, Huang L, et al. On the control of the Berkeley lower extremity exoskeleton (BLEEX). In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), Barcelona, 2005. 4353--4360. Google Scholar
Figure 1
(a) Control diagram of multi-controller consisting of a model-based controller and an auxiliary controller; (b) compensation of convergence time of the cost function