Several upper-limb exoskeleton robots have been developed for stroke rehabilitation, but their rather low level of individualized assistance typically limits their effectiveness and practicability. Individualized assistance involves an upper-limb exoskeleton robot continuously assessing feedback from a stroke patient and then meticulously adjusting interaction forces to suit specific conditions and online changes. This paper describes the development of a new upper-limb exoskeleton robot with a novel online generative capability that allows it to provide individualized assistance to support the rehabilitation training of stroke patients. Specifically, the upper-limb exoskeleton robot exploits generative models to customize the fine and fit trajectory for the patient, as medical conditions, responses, and comfort feedback during training generally differ between patients. This generative capability is integrated into the two working modes of the upper-limb exoskeleton robot: an active mirroring mode for patients who retain motor abilities on one side of the body and a passive following mode for patients who lack motor ability on both sides of the body. In addition, the upper-limb exoskeleton robot has three other attractive features. First, it has six degrees of freedom (DoFs), namely five active DoFs and one passive DoF, to assist the shoulder and the elbow joints and cover the full range of upper-limb movement. Second, most of its active joints are driven by series elastic actuators (SEAs) and a cable mechanism, which absorb energy and have low inertia. These compliantly driven high DoFs provide substantial flexibility and ensure hardware safety but require an effective controller. Thus, based on the singular perturbation approach, a model-based impedance controller is proposed to fully exploit the advantages of the hardware. Third, the safety of the upper-limb exoskeleton robot is guaranteed by its hardware and software. Regarding hardware, its SEAs are tolerant to impacts and have high backdrivability. Regarding software, online trajectory refinement is performed to regulate the assistance provided by the upper-limb exoskeleton robot, and an anomaly detection network is constructed to detect and relax physical conflicts between the upper-limb exoskeleton robot and the patient. The performance of the upper-limb exoskeleton robot was illustrated in experiments involving healthy subjects and stroke patients.
Albu-SchäfferAOttCHirzingerG (2007) A unified passivity-based control framework for position, torque and impedance control of flexible joint robots. The International Journal of Robotics Research26(1): 23–39.
2.
ChenTCasasRLumPS (2019) An elbow exoskeleton for upper limb rehabilitation with series elastic actuator and cable-driven differential. IEEE Transactions on Robotics: A Publication of the IEEE Robotics and Automation Society35(6): 1464–1474.
3.
ChenYChenGYeJ, et al. (2023) Safe and individualized motion planning for upper-limb exoskeleton robots using human demonstration and interactive learning. arXiv preprint arXiv:2309.08178.
4.
ChenYMiaoSChenG, et al. (2024) Learning to assist different wearers in multitasks: efficient and individualized human-in-the-loop adaptation framework for lower-limb exoskeleton. IEEE Transactions on Robotics40: 4699–4718.
5.
ClarkGAmorHB (2022) Learning ergonomic control in human–robot symbiotic walking. IEEE Transactions on Robotics39(1): 327–342.
6.
De WitCCOlssonHAstromKJ, et al. (1995) A new model for control of systems with friction. IEEE Transactions on Automatic Control40(3): 419–425.
7.
EbrahimiAGröningerDSingerR, et al. (2017) Control parameter optimization of the actively powered upper body exoskeleton using subjective feedbacks. In: 2017 3rd International conference on control, automation and robotics (ICCAR), Nagoya, Japan, 22–24 April 2017. IEEE, 432–437.
8.
FranksPWBryanGMReyesR, et al. (2022) The effects of incline level on optimized lower-limb exoskeleton assistance: a case series. IEEE Transactions on Neural Systems and Rehabilitation Engineering: A publication of the IEEE Engineering in Medicine and Biology Society30: 2494–2505.
9.
Fugl-MeyerARJääsköLLeymanI, et al. (1975) A method for evaluation of physical performance. Scandinavian Journal of Rehabilitation Medicine7(1): 13–31.
10.
GullMABaiSBakT (2020) A review on design of upper limb exoskeletons. Robotics9(1): 16.
11.
HanSWangHYuH (2023) Human–robot interaction evaluation-based aan control for upper limb rehabilitation robots driven by series elastic actuators. IEEE Transactions on Robotics39(5): 3437–3451.
12.
HoJJainAAbbeelP (2020) Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems33: 6840–6851.
13.
HuangVSKrakauerJW (2009) Robotic neurorehabilitation: a computational motor learning perspective. Journal of NeuroEngineering and Rehabilitation6: 1–13.
14.
HuangJHuoWXuW, et al. (2015) Control of upper-limb power-assist exoskeleton using a human-robot interface based on motion intention recognition. IEEE Transactions on Automation Science and Engineering12(4): 1257–1270.
15.
JauBM (1988) Anthropomorhic exoskeleton dual arm/hand telerobot controller. In: IEEE international workshop on intelligent robots. IEEE, 715–718.
16.
JezernikSColomboGMorariM (2004) Automatic gait-pattern adaptation algorithms for rehabilitation with a 4-dof robotic orthosis. IEEE Transactions on Robotics and Automation20(3): 574–582.
17.
KagawaTIshikawaHKatoT, et al. (2015) Optimization-based motion planning in joint space for walking assistance with wearable robot. IEEE Transactions on Robotics31(2): 415–424.
18.
KalitaBNarayanJDwivedySK (2021) Development of active lower limb robotic-based orthosis and exoskeleton devices: a systematic review. International Journal of Social Robotics13: 775–793.
19.
KimTYChoSB (2019) Predicting residential energy consumption using cnn-lstm neural networks. Energy182: 72–81.
20.
KimBDeshpandeAD (2017) An upper-body rehabilitation exoskeleton harmony with an anatomical shoulder mechanism: design, modeling, control, and performance evaluation. The International Journal of Robotics Research36(4): 414–435.
21.
KimHMillerLMBylN, et al. (2012) Redundancy resolution of the human arm and an upper limb exoskeleton. IEEE Transactions on Biomedical Engineering59(6): 1770–1779.
22.
LanotteFMcKinneyZGraziL, et al. (2021) Adaptive control method for dynamic synchronization of wearable robotic assistance to discrete movements: validation for use case of lifting tasks. IEEE Transactions on Robotics37(6): 2193–2209.
23.
LeeSHParkGChoDY, et al. (2020) Comparisons between end-effector and exoskeleton rehabilitation robots regarding upper extremity function among chronic stroke patients with moderate-to-severe upper limb impairment. Scientific Reports10(1): 1806.
24.
LenziTDe RossiSMMVitielloN, et al. (2012) Intention-based emg control for powered exoskeletons. IEEE Transactions on Biomedical Engineering59(8): 2180–2190.
25.
LiXPanYChenG, et al. (2017) Multi-modal control scheme for rehabilitation robotic exoskeletons. The International Journal of Robotics Research36(5–7): 759–777.
26.
LiXLiuYYuH (2018a) Iterative learning impedance control for rehabilitation robots driven by series elastic actuators. Automatica90: 1–7.
27.
LiXLiuYHYuH (2018b) Iterative learning impedance control for rehabilitation robots driven by series elastic actuators. Automatica90: 1–7.
28.
LiXZhangXLiX, et al. (2021) Bear-h: an intelligent bilateral exoskeletal assistive robot for smart rehabilitation. IEEE Robotics and Automation Magazine29(3): 34–46.
29.
LiNYangYLiG, et al. (2022) Multi-sensor fusion-based mirror adaptive assist-as-needed control strategy of a soft exoskeleton for upper limb rehabilitation. IEEE Transactions on Automation Science and Engineering29: 1–13.
30.
LiHGuoSBuD, et al. (2023a) Subject-independent estimation of continuous movements using cnn-lstm for a home-based upper limb rehabilitation system. IEEE Robotics and Automation Letters8(10): 1–8.
31.
LiZLiQHuangP, et al. (2023b) Human-in-the-loop adaptive control of a soft exo-suit with actuator dynamics and ankle impedance adaptation. IEEE Transactions on Cybernetics53(12): 7920–7932.
32.
LongYDuZJWangWD, et al. (2018) Human motion intent learning based motion assistance control for a wearable exoskeleton. Robotics and Computer-Integrated Manufacturing49: 317–327.
33.
MaoYAgrawalSK (2012) Design of a cable-driven arm exoskeleton (carex) for neural rehabilitation. IEEE Transactions on Robotics28(4): 922–931.
34.
MartinezJANgPLuS, et al. (2013) Design of wrist gimbal: a forearm and wrist exoskeleton for stroke rehabilitation. In: 2013 IEEE 13th International conference on rehabilitation robotics (ICORR), Seattle, WA, 24–26 June 2013. IEEE, 1–6.
35.
MartinezALawsonBDurroughC, et al. (2018) A velocity-field-based controller for assisting leg movement during walking with a bilateral hip and knee lower limb exoskeleton. IEEE Transactions on Robotics35(2): 307–316.
36.
MohammadiAMarquezHJTavakoliM (2017) Nonlinear disturbance observers: design and applications to euler? Lagrange systems. IEEE Control Systems37(4): 50–72.
37.
NasrABellSMcPheeJ (2023) Optimal design of active-passive shoulder exoskeletons: a computational modeling of human-robot interaction. Multibody System Dynamics57(1): 73–106.
38.
PanYWangHLiX, et al. (2017) Adaptive command-filtered backstepping control of robot arms with compliant actuators. IEEE Transactions on Control Systems Technology26(3): 1149–1156.
39.
PanJAstaritaDBaldoniA, et al. (2022) Nesm-γ: an upper-limb exoskeleton with compliant actuators for clinical deployment. IEEE Robotics and Automation Letters7(3): 7708–7715.
40.
ParaschosADanielCPetersJR, et al. (2013) Probabilistic movement primitives. In: Advances in neural information processing systems. Cambridge, MA: MIT Press.
PrattGAWilliamsonMM (1995) Series elastic actuators. In: Proceedings 1995 IEEE/RSJ international conference on intelligent robots and systems. Human robot interaction and cooperative robots, Pittsburgh, PA, 05–09 August 1995. IEEE, 399–406.
43.
QiuSGuoWCaldwellD, et al. (2020) Exoskeleton online learning and estimation of human walking intention based on dynamical movement primitives. IEEE Transactions on Cognitive and Developmental Systems13(1): 67–79.
44.
QuigleyMConleyKGerkeyB, et al. (2009) Ros: an open-source robot operating system. In: ICRA workshop on open source software. Japan: Kobe, 5.
45.
SaidRRHeyatMBBSongK, et al. (2022) A systematic review of virtual reality and robot therapy as recent rehabilitation technologies using eeg-brain–computer interface based on movement-related cortical potentials. Biosensors12(12): 1134.
46.
SalzmannTIvanovicBChakravartyP, et al. (2020) Trajectron++: dynamically-feasible trajectory forecasting with heterogeneous data. In: Computer vision–ECCV 2020: 16th European conference, Glasgow, UK, 23–28 August 2020, Proceedings, Part XVIII 16. Springer, 683–700.
47.
SambhusRGokceAWelchS, et al. (2023) Real-time model-free deep reinforcement learning for force control of a series elastic actuator. In: 2023 IEEE/RSJ international conference on intelligent robots and systems (IROS), Detroit, MI, 1–5 October 2023. IEEE, 5645–5652.
48.
SladePKochenderferMJDelpSL, et al. (2022) Personalizing exoskeleton assistance while walking in the real world. Nature610(7931): 277–282.
49.
SommerhalderMZimmermannYSimovicL, et al. (2023) Trajectory optimization framework for rehabilitation robots with multi-workspace objectives and constraints. IEEE Robotics and Automation Letters8(10): 6819–6826.
SpongMW (1987) Modeling and control of elastic joint robots. Journal of Dynamic Systems, Measurement, and Control109: 310–318.
52.
TiboniMBorboniAVéritéF, et al. (2022) Sensors and actuation technologies in exoskeletons: a review. Sensors22(3): 884.
53.
TikhonovAN (1952) Systems of differential equations containing small parameters in the derivatives. Matematicheskii sbornik73(3): 575–586.
54.
WangYZahediAZhaoY, et al. (2022) Extracting human-exoskeleton interaction torque for cable-driven upper-limb exoskeleton equipped with torque sensors. IEEE/ASME Transactions on Mechatronics27(6): 4269–4280.
55.
WilliamsGWagenerNGoldfainB, et al. (2017) Information theoretic mpc for model-based reinforcement learning. In: 2017 IEEE international conference on robotics and automation (ICRA), Singapore, 29 May–3 June 2017. IEEE, 1714–1721.
56.
WuQWangXDuF (2016) Development and analysis of a gravity-balanced exoskeleton for active rehabilitation training of upper limb. Proceedings of the Institution of Mechanical Engineers - Part C: Journal of Mechanical Engineering Science230(20): 3777–3790.
57.
WyattJLeachASchmonSM, et al. (2022) Anoddpm: anomaly detection with denoising diffusion probabilistic models using simplex noise. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 650–656.
58.
XuJXuLLiY, et al. (2020) A multi-channel reinforcement learning framework for robotic mirror therapy. IEEE Robotics and Automation Letters5(4): 5385–5392.
59.
XuMZhouZWangZ, et al. (2023) Bio-inspired cable-driven actuation system for wearable robotic devices: design, control and characterization. IEEE Transactions on Robotics40: 520–539.
60.
ZhangJFiersPWitteKA, et al. (2017) Human-in-the-loop optimization of exoskeleton assistance during walking. Science356(6344): 1280–1284.
61.
ZhangJXieYPangG, et al. (2020) Viral pneumonia screening on chest x-rays using confidence-aware anomaly detection. IEEE Transactions on Medical Imaging40(3): 879–890.
62.
ZhangQNalamVTuX, et al. (2022a) Imposing healthy hip motion pattern and range by exoskeleton control for individualized assistance. IEEE Robotics and Automation Letters7(4): 11126–11133.
63.
ZhangSGuanXYeJ, et al. (2022b) Gait deviation correction method for gait rehabilitation with a lower limb exoskeleton robot. IEEE Transactions on Medical Robotics and Bionics4(3): 754–763.
64.
ZhangXShuYChenY, et al. (2023) Multi-modal learning and relaxation of physical conflict for an exoskeleton robot with proprioceptive perception. In: 2023 IEEE international conference on robotics and automation (ICRA). London, United Kingdom: IEEE, 10490–10496.
65.
ZhuLWangZNingZ, et al. (2020) A novel motion intention recognition approach for soft exoskeleton via imu. Electronics9(12): 2176.
66.
ZhuHNeslerCDivekarN, et al. (2021) Design principles for compact, backdrivable actuation in partial-assist powered knee orthoses. IEEE/ASME Transactions on Mechatronics: A Joint publication of the IEEE Industrial Electronics Society and the ASME Dynamic Systems and Control Division26(6): 3104–3115.
67.
ZimmermannYKüçüktabakEBFarshidianF, et al. (2020) Towards dynamic transparency: robust interaction force tracking using multi-sensory control on an arm exoskeleton, In: 2020 IEEE/RSJ international conference on intelligent robots and systems (IROS). Las Vegas, NV: IEEE, 7417–7424.
68.
ZimmermannYSommerhalderMWolfP, et al. (2023a) Anyexo 2.0: a fully actuated upper-limb exoskeleton for manipulation and joint-oriented training in all stages of rehabilitation. IEEE Transactions on Robotics39(3): 2131–2150.
69.
ZimmermannYSongJDeguelleC, et al. (2023b) Human–robot attachment system for exoskeletons: design and performance analysis. IEEE Transactions on Robotics39(4): 3087–3105.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
