Similar articles

Abstract: As a wearable robot, an exoskeleton provides a direct transfer of mechanical power to assist or augment the wearer’s movement with an anthropomorphic configuration. When an exoskeleton is used to facilitate the wearer’s movement, a motion generation process often plays an important role in high-level control. One of the main challenges in this area is to generate in real time a reference trajectory that is parallel with human intention and can adapt to different situations. In this paper, we first describe a novel motion modeling method based on probabilistic movement primitive (ProMP) for a lower limb exoskeleton, which is a new and powerful representative tool for generating motion trajectories. To adapt the trajectory to different situations when the exoskeleton is used by different wearers, we propose a novel motion learning scheme based on black-box optimization (BBO) PI^BB combined with ProMP. The motion model is first learned by ProMP offline, which can generate reference trajectories for use by exoskeleton controllers online. PI^BB is adopted to learn and update the model for online trajectory generation, which provides the capability of adaptation of the system and eliminates the effects of uncertainties. Simulations and experiments involving six subjects using the lower limb exoskeleton HEXO demonstrate the effectiveness of the proposed methods.

针对下肢外骨骼机器人的基于概率运动基元的黑盒优化运动学习

[1]Al-Shuka HFN, Corves B, Zhu WH, et al., 2016. Multi-level control of zero-moment point-based humanoid biped robots: a review. Robotica, 34(11):2440-2466.

[2]Colombo G, Joerg M, Schreier R, et al., 2000. Treadmill training of paraplegic patients using a robotic orthosis. J Rehabil Res Dev, 37(6):693-700.

[3]d’Avella A, Bizzi E, 2005. Shared and specific muscle synergies in natural motor behaviors. Proc Nat Acad Sci USA, 102(8):3076-3081.

[4]Deng MD, Li ZJ, Kang Y, et al., 2020. A learning-based hierarchical control scheme for an exoskeleton robot in human-robot cooperative manipulation. IEEE Trans Cybern, 50(1):112-125.

[5]Esquenazi A, Talaty M, Packel A, et al., 2012. The ReWalk powered exoskeleton to restore ambulatory function to individuals with thoracic-level motor-complete spinal cord injury. Am J Phys Med Rehabil, 91(11):911-921.

[6]Fu CL, Chen K, 2008. Gait synthesis and sensory control of stair climbing for a humanoid robot. IEEE Trans Ind Electron, 55(5):2111-2120.

[7]Guizzo E, Goldstein H, 2005. The rise of the body bots [robotic exoskeletons]. IEEE Spectr, 42(10):50-56.

[8]Hassan M, Kadone H, Suzuki K, et al., 2014. Wearable gait measurement system with an instrumented cane for exoskeleton control. Sensors, 14(1):1705-1722.

[9]He W, Li ZJ, Chen CLP, 2017. A survey of human-centered intelligent robots: issues and challenges. IEEE/CAA J Autom Sin, 4(4):602-609.

[10]Huang R, Cheng H, Guo H, et al., 2018. Hierarchical learning control with physical human-exoskeleton interaction. Inform Sci, 432:584-595.

[11]Huang R, Cheng H, Qiu J, et al., 2019. Learning physical human-robot interaction with coupled cooperative primitives for a lower exoskeleton. IEEE Trans Autom Sci Eng, 16(4):1566-1574.

[12]Ijspeert AJ, Nakanishi J, Schaal S, 2002. Movement imitation with nonlinear dynamical systems in humanoid robots. Proc IEEE Int Conf on Robotics and Automation, p.1398-1403.

[13]Ijspeert AJ, Nakanishi J, Hoffmann H, et al., 2013. Dynamical movement primitives: learning attractor models for motor behaviors. Neur Comput, 25(2):328-373.

[14]Jenison RL, Fissell K, 1995. A comparison of the von Mises and Gaussian basis functions for approximating spherical acoustic scatter. IEEE Trans Neur Netw, 6(5):1284-1287.

[15]Kagawa T, Ishikawa H, Kato T, et al., 2015. Optimization-based motion planning in joint space for walking assistance with wearable robot. IEEE Trans Rob, 31(2):415-424.

[16]Kazemi J, Ozgoli S, 2019. Real-time walking pattern generation for a lower limb exoskeleton, implemented on the exoped robot. Rob Auton Syst, 116:1-23.

[17]Kazerooni H, Steger R, 2006. The Berkeley lower extremity exoskeleton. J Dynam Syst Meas Contr, 128(1):14-25.

[18]Komura T, Nagano A, Leung H, et al., 2005. Simulating pathological gait using the enhanced linear inverted pendulum model. IEEE Trans Biomed Eng, 52(9):1502-1513.

[19]Krüger V, Kragic D, Ude A, et al., 2007. The meaning of action: a review on action recognition and mapping. Adv Rob, 21(13):1473-1501.

[20]Kulić D, Ott C, Lee D, et al., 2012. Incremental learning of full body motion primitives and their sequencing through human motion observation. Int J Rob Res, 31(3):330-345.

[21]Lee SW, Yi T, Jung JW, et al., 2015. Design of a gait phase recognition system that can cope with EMG electrode location variation. IEEE Trans Autom Sci Eng, 14(3):‍1429-1439.

[22]Paraschos A, Daniel C, Peters J, et al., 2013. Probabilistic movement primitives. Proc 26^th Int Conf on Neural Information Processing Systems, p.2616-2624.

[23]Paraschos A, Daniel C, Peters J, et al., 2018. Using probabilistic movement primitives in robotics. Auton Rob, 42(3):529-551.

[24]Sankai Y, 2010. HAL: hybrid assistive limb based on cybernics. In: Kaneko M, Nakamura Y (Eds.), Robotics Research. Springer, Berlin, Heidelberg, p.25-34.

[25]Sanz-Merodio D, Cestari M, Arevalo JC, et al., 2014. Generation and control of adaptive gaits in lower-limb exoskeletons for motion assistance. Adv Rob, 28(5):329-338.

[26]Schaal S, Ijspeert A, Billard A, 2003. Computational approaches to motor learning by imitation. Phil Trans R Soc B Biol Sci, 358(1431):537-547.

[27]Schaal S, Peters J, Nakanishi J, et al., 2005. Learning movement primitives. 11^th Int Symp on Robotics Research, p.561-572.

[28]Schmidhuber J, 2015. Deep learning in neural networks: an overview. Neur Netw, 61:85-117.

[29]Spiegelhalter DJ, Best NG, Carlin BP, et al., 2002. Bayesian measures of model complexity and fit. J R Stat Soc Ser B (Stat Methodol), 64(4):583-639.

[30]Strausser KA, Kazerooni H, 2011. The development and testing of a human machine interface for a mobile medical exoskeleton. Proc IEEE/RSJ Int Conf on Intelligent Robots and Systems, p.4911-4916.

[31]Stulp F, Sigaud O, 2012. Policy Improvement Methods: Between Black-Box Optimization and Episodic Reinforcement Learning. https://hal.‍archives-ouvertes.‍fr/hal-00738463 [Accessed on Jan. 12, 2021]

[32]Theodorou E, Buchli J, Schaal S, 2010. A generalized path integral control approach to reinforcement learning. J Mach Learn Res, 11:3137-3181.

[33]Todorov E, Jordan MI, 2002. Optimal feedback control as a theory of motor coordination. Nat Neurosci, 5(11):1226-1235.

[34]Tucker MR, Olivier J, Pagel A, et al., 2015. Control strategies for active lower extremity prosthetics and orthotics: a review. J Neuroeng Rehabil, 12(1):1.

[35]Veneman JF, Kruidhof R, Hekman EEG, et al., 2007. Design and evaluation of the LOPES exoskeleton robot for interactive gait rehabilitation. IEEE Trans Neur Syst Rehabil Eng, 15(3):379-386.

[36]Vukobratović M, Borovac B, 2004. Zero-moment point—thirty five years of its life. Int J Human Rob, 1(1):157-173.

[37]Walsh CJ, Endo K, Herr H, 2007. A quasi-passive leg exoskeleton for load-carrying augmentation. Int J Human Rob, 4(3):487-506.

[38]Xu B, Sun FC, 2018. Composite intelligent learning control of strict-feedback systems with disturbance. IEEE Trans Cybern, 48(2):730-741.

[39]Yan TF, Cempini M, Oddo CM, et al., 2015. Review of assistive strategies in powered lower-limb orthoses and exoskeletons. Rob Auton Syst, 64:120-136.

[40]Yang CG, Chen CZ, Wang N, et al., 2019. Biologically inspired motion modeling and neural control for robot learning from demonstrations. IEEE Trans Cogn Dev Syst, 11(2):281-291.

[41]Yuan YX, Li ZJ, Zhao T, et al., 2020. DMP-based motion generation for a walking exoskeleton robot using reinforcement learning. IEEE Trans Ind Electron, 67(5):‍3830-3839.

[42]Zoss AB, Kazerooni H, Chu A, 2006. Biomechanical design of the Berkeley lower extremity exoskeleton (BLEEX). IEEE/ASME Trans Mechatr, 11(2):128-138.