Abstract:In order to improve the adaptability of an exoskeleton robot and the safety of human-exoskeleton interaction, an online gait trajectory planning method based on kernelized movement primitives (KMPs) is proposed, which can adjust the gait trajectory in real time according to the user's gait state. The algorithm is demonstrated on a knee joint exoskeleton. The result shows that the proposed algorithm can adjust the shape parameters online according to a few training samples, to ensure that the predicted trajectory is similar to the original trajectory. It can also generate a trajectory according to user's state change by detecting gait phase in real time and adjusting the gait trajectory online at the desired point.
[1] 彭亮,侯增广,王晨,等.康复辅助机器人及其物理人机交互方法[J].自动化学报, 2018, 44(11):2000-2010. Peng L, Hou Z G, Wang C, et al. Physical interaction methods for rehabilitation and assistive robots[J]. Acta Automatica Sinica, 2018, 44(11):2000-2010. [2] Chen G, Guo Z, Yu H Y. Mechanical design and evaluation of a novel knee-ankle-foot robot for rehabilitation[C]//ASME 2015 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. New York, USA:ASME, 2016. DOI:10.1115/DETC2015-46229. [3] 张玉明,吴青聪,陈柏,等.下肢软质康复外骨骼机器人的模糊神经网络阻抗控制[J].机器人, 2020, 42(4):477-484,493. Zhang Y M, Wu Q C, Chen B, et al. Fuzzy neural network impedance control of soft lower limb rehabilitation exoskeleton robot[J]. Robot, 2020, 42(4):477-484,493. [4] Yu H Y, Huang S N, Chen G, et al. Human-robot interaction control of rehabilitation robots with series elastic actuators[J]. IEEE Transactions on Robotics, 2015, 31(5):1089-1100. [5] 赵新刚,谈晓伟,张弼.柔性下肢外骨骼机器人研究进展及关键技术分析[J].机器人, 2020, 42(3):365-384. Zhao X G, Tan X W, Zhang B. Development of soft lower extremity exoskeleton and its key technologies:A survey[J]. Robot, 2020, 42(3):365-384. [6] 孙定阳,沈浩,郭朝,等.绳驱动柔性上肢外骨骼机器人设计与控制[J].机器人, 2019, 41(6):834-841. Sun D Y, Shen H, Guo Z, et al. Design and control of the cable driven compliant upper limb exoskeleton robot[J]. Robot, 2019, 41(6):834-841. [7] Banala S K, Kim S H, Agrawal S K, et al. Robot assisted gait training with active leg exoskeleton (ALEX)[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2009, 17(1):2-8. [8] 贾山,韩亚丽,路新亮,等.基于人体特殊步态分析的下肢外骨骼机构设计[J].机器人, 2014, 36(4):392-401,410. Jia S, Han Y L, Lu X L, et al. Design of lower extremity exoskeleton based on analysis on special human gaits[J]. Robot, 2014, 36(4):392-401,410. [9] Li Z J, Huang Z C, He W, et al. Adaptive impedance control for an upper limb robotic exoskeleton using biological signals[J]. IEEE Transactions on Industrial Electronics, 2017, 64(2):1664-1674. [10] 罗林聪,侯增广,王卫群,等.一种基于非线性振荡器的步态轨迹自适应算法[J].自动化学报, 2016, 42(12):1951-1959. Luo L C, Hou Z G, Wang W Q, et al. A gait trajectory adaptation algorithm based on nonlinear oscillator[J]. Acta Automatica Sinica, 2016, 42(12):1951-1959. [11] Chen G, Qi P, Guo Z, et al. Gait-event-based synchronization method for gait rehabilitation robots via a bioinspired adaptive oscillator[J]. IEEE Transactions on Biomedical Engineering, 2017, 64(6):1345-1356. [12] Ruiz Garate V, Parri A, Yan T, et al. Experimental validation of motor primitive-based control for leg exoskeletons during continuous multi-locomotion tasks[J]. Frontiers in Neurorobotics, 2017, 11. DOI:10.3389/fnbot.2017.00015. [13] Ijspeert A J, Nakanishi J, Hoffmann H, et al. Dynamical movement primitives:Learning attractor models for motor behaviors[J]. Neural Computation, 2013, 25(2):328-373. [14] 黄瑞.下肢助力外骨骼层级交互式学习控制算法研究[D]. 成都:电子科技大学, 2018. Huang R. Hierarchical interactive learning for control of a human-powered augmentation lower exoskeleton[D]. Chengdu:University of Electronic Science and Technology of China, 2018. [15] Huang R, Peng Z N, Cheng H, et al. Learning-based walking assistance control strategy for a lower limb exoskeleton with hemiplegia patients[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2018:2280-2285. [16] 甘地.基于动态基元与强化学习算法的下肢外骨骼康复机器人步行研究[D].广州:华南理工大学, 2018. Gan D. Walking research on lower extremity exoskeleton rehabilitation robot based on dynamic motion primitive with reinforcement learning[D]. Guangzhou:South China University of Technology, 2018. [17] Yuan Y X, Li Z J, Zhao T, et al. DMP-based motion generation for a walking exoskeleton robot using reinforcement learning[J]. IEEE Transactions on Industrial Electronics, 2020, 67(5):3830-3839. [18] Huang Y L, Rozo L, Silvério J, et al. Kernelized movement primitives[J]. International Journal of Robotics Research, 2019, 38(7):833-852. [19] Chinimilli P T, Qiao Z, Sorkhabadi S M R, et al. Automatic virtual impedance adaptation of a knee exoskeleton for personalized walking assistance[J]. Robotics and Autonomous Systems, 2019, 114:66-76. [20] 黄艳龙,徐德,谭民.机器人运动轨迹的模仿学习综述[J/OL]. 自动化学报, (2021-05-08)[2021-06-18]. http://kns.cnki.net/kcms/detail/11.2109.TP.20210507.1806.002.html. Huang Y L, Xu D, Tan M. On imitation learning of robot movement trajectories:A survey[J/OL]. Acta Automatica Sinica, (2021-05-08)[2021-06-18]. http://kns.cnki.net/kcms/detail/11.2109.TP.20210507.1806.002.html. [21] Ding S, Ouyang X P, Liu T, et al. Gait event detection of a lower extremity exoskeleton robot by an intelligent IMU[J]. IEEE Sensors Journal, 2018, 18(23):9728-9735.