Despite advances in robot-assisted rehabilitation, existing control strategies often lack real-time personalization to account for subject-specific physiological capabilities, limiting the effectiveness of assist-as-needed interventions. Moreover, there is a further need to account for the patient’s physiological functional capacity (PFC) in the design of such assistive technology. Here, an attempt has been made to create an Assist-as-Needed (AAN) Controller that works in collaboration with a Smart Avatar. The Smart Avatar mimics the patient’s capabilities by learning in real-time and informing the controller. To efficiently predict the subject’s level of involvement, a Reinforcement Learning (RL) based Inverse Dynamics model has been designed. Additionally, the controller for the Avatar has been appended with an Energy Map for modifying the reference trajectories and making the system energy efficient. The human torque estimated by the Smart Avatar assists the Assist-as-Needed (AAN) controller in providing the optimum robot torque to guide the subject’s wrist along the modified trajectories. The developed algorithm was validated on five healthy participants. The system achieved trajectory tracking errors in the range of 0.01–0.04 rad across wrist motions. Subject- and axis-dependent differences in interaction torque were examined using descriptive statistics and torque profiles, supporting the feasibility of adaptive assistance under the tested conditions.
HussainSJamwalPKVan VlietP, et al. State-of-the-art robotic devices for wrist rehabilitation: design and control aspects. IEEE Trans Hum Mach Syst2020; 50: 361–372. https://doi.org/10.1109/thms.2020.2976905
2.
GuptaAO’MalleyMKPatogluV, et al. Design, control and performance of ricewrist: a force feedback wrist exoskeleton for rehabilitation and training. Int J Rob Res2008; 27: 233–251. https://doi.org/10.1177/0278364907084261
3.
BuongiornoDSotgiuELeonardisD, et al. WRES: a novel 3 DoF WRist ExoSkeleton with tendon-driven differential transmission for neuro-rehabilitation and teleoperation. IEEE Robot Autom Lett2018; 3: 2152–2159. https://doi.org/10.1109/lra.2018.2810943
4.
RahmanMHRahmanMJCristobalOL, et al. Development of a whole arm wearable robotic exoskeleton for rehabilitation and to assist upper limb movements. Robotica2015; 33: 19–39. https://doi.org/10.1017/s0263574714000034
5.
KrebsHIVolpeBTWilliamsD, et al. Robot-aided neurorehabilitation: a robot for wrist rehabilitation. IEEE Trans Neural Syst Rehabil Eng2007; 15: 327–335. https://doi.org/10.1109/TNSRE.2007.903899
6.
SqueriVMasiaLGiannoniP, et al. Wrist rehabilitation in chronic stroke patients by means of adaptive, progressive robot-aided therapy. IEEE Trans Neural Syst Rehabil Eng2014; 22: 312–325. https://doi.org/10.1109/TNSRE.2013.2250521
7.
KuchinkeL-MBenderB. Technical view on requirements for future development of hand-held rehabilitation devices. In: 2016 6th IEEE international conference on biomedical robotics and biomechatronics (BioRob), 2016, pp.804–809. IEEE.
8.
GoyalTHussainSMartinez-MarroquinE, et al. Stiffness-observer-based adaptive control of an intrinsically compliant parallel wrist rehabilitation robot. IEEE Trans Hum Mach Syst2023; 53: 65–74. https://doi.org/10.1109/THMS.2022.3211164
9.
HoganN. Impedance control: an approach to manipulation: part i—theory. J Dyn Syst Meas Control1985; 107: 1–7. https://doi.org/10.1115/1.3140702
10.
FitzsimonsKKalinowskaADewaldJP, et al. Task-based hybrid shared control for training through forceful interaction. Int J Rob Res2020; 39: 1138–1154. https://doi.org/10.1177/0278364920933654
11.
LanotteFMcKinneyZGraziL, et al. Adaptive control method for dynamic synchronization of wearable robotic assistance to discrete movements: validation for use case of lifting tasks. IEEE Trans Robot2021; 37: 2193–2209. https://doi.org/10.1109/tro.2021.3073836
12.
DiazMAVosMDillenA, et al. Human-in-the-loop optimization of wearable robotic devices to improve human-robot interaction: a systematic review. IEEE Trans Cybern2023; 53: 7483–7496. https://doi.org/10.1109/TCYB.2022.3224895
MichaudBBaillyFCharbonneauE, et al. Bioptim, a Python framework for musculoskeletal optimal control in biomechanics. IEEE Trans Syst Man Cybern Syst2023; 53: 321–332. https://doi.org/10.1109/tsmc.2022.3183831
LiGLiZSuCY, et al. Active human-following control of an exoskeleton robot with body weight support. IEEE Trans Cybern2023; 53: 7367–7379. https://doi.org/10.1109/TCYB.2023.3253181
18.
SharifiMTripathiSChenY, et al. Reinforcement learning methods for assistive and rehabilitation robotic systems: a survey. IEEE Trans Syst Man Cybern Syst2025; 55: 4534–4551. https://doi.org/10.1109/tsmc.2025.3555598
19.
PeternelLPetričTOztopE, et al. Teaching robots to cooperate with humans in dynamic manipulation tasks based on multi-modal human-in-the-loop approach. Auton Robots2014; 36: 123–136. https://doi.org/10.1007/s10514-013-9361-0
20.
GoyalT. Human-robot interaction control of an intrinsically compliant parallel wrist rehabilitation robot. University of Canberra, 2023.
21.
MerletJP. Parallel robots. Springer Science & Business Media, 2006.
JamwalPXieSQHussainS, et al. Modeling pneumatic muscle actuators: artificial intelligence approach. Int J Inf Acquis2011; 07: 151–164. https://doi.org/10.1142/s0219878910002130
24.
WenYSiJBrandtA, et al. Online Reinforcement Learning Control for the Personalization of a Robotic Knee Prosthesis. IEEE Trans Cybern2020; 50: 2346–2356. https://doi.org/10.1109/TCYB.2019.2890974
25.
JagodnikKMThomasPSvan den BogertAJ, et al. Training an actor-critic reinforcement learning controller for arm movement using human-generated rewards. IEEE Trans Neural Syst Rehabil Eng2017; 25: 1892–1905. https://doi.org/10.1109/TNSRE.2017.2700395
26.
IbarzJTanJFinnC, et al. How to train your robot with deep reinforcement learning: lessons we have learned. Int J Rob Res2021; 40: 698–721. https://doi.org/10.1177/0278364920987859
27.
WuWSaulKRHuangHH. Using reinforcement learning to estimate human joint moments from electromyography or joint kinematics: an alternative solution to musculoskeletal-based biomechanics. J Biomech Eng2021; 143: 0445021–0445029. https://doi.org/10.1115/1.4049333
28.
AhnSGFoxJ. Immersive virtual environments, avatars, and agents for health. Oxford University Press, 2017.
29.
CuiXChenWJinX, et al. Design of a 7-DOF Cable-Driven Arm Exoskeleton (CAREX-7) and a controller for dexterous motion training or assistance. IEEE/ASME Trans Mechatron2017; 22: 161–172. https://doi.org/10.1109/tmech.2016.2618888
30.
ShiKSongALiY, et al. A cable-driven three-DOF wrist rehabilitation exoskeleton with improved performance. Front Neurorobot2021; 15: 664062. https://doi.org/10.3389/fnbot.2021.664062
31.
AiQLiuZMengW, et al. Machine learning in robot-assisted upper limb rehabilitation: a focused review. IEEE Trans Cogn Dev Syst2023; 15: 2053–2063. https://doi.org/10.1109/tcds.2021.3098350
LachnerJAllmendingerFHobertE, et al. Energy budgets for coordinate invariant robot control in physical human–robot interaction. Int J Rob Res2021; 40: 968–985. https://doi.org/10.1177/02783649211011639
34.
ChenMGeSSHowBV. Robust adaptive neural network control for a class of uncertain MIMO nonlinear systems with input nonlinearities. IEEE Trans Neural Netw2010; 21: 796–812. https://doi.org/10.1109/TNN.2010.2042611
35.
WangJZuoGZhangJ, et al. [Research on assist-as-needed control strategy of wrist function-rehabilitation robot]. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi2020; 37: 129–135. https://doi.org/10.7507/1001-5515.201902023
36.
VogelJHaddadinSJarosiewiczB, et al. An assistive decision-and-control architecture for force-sensitive hand–arm systems driven by human–machine interfaces. Int J Rob Res2015; 34: 763–780. https://doi.org/10.1177/0278364914561535
37.
Krasny-PaciniAEvansJ. Single-case experimental designs to assess intervention effectiveness in rehabilitation: a practical guide. Ann Phys Rehabil Med2018; 61: 164–179. https://doi.org/10.1016/j.rehab.2017.12.002
38.
GoyalTHussainSMartinez-MarroquinE, et al. Learning Koopman embedding subspaces for system identification and optimal control of a wrist rehabilitation robot. IEEE Trans Ind Electron2023; 70: 7092–7101. https://doi.org/10.1109/tie.2022.3203760
