Velocity control of a Stephenson III six-bar linkage-based gait rehabilitation robot using deep reinforcement learning
Kapsalyamov A. Brown N.A.T. Goecke R. Jamwal P.K. Hussain S.
March 2025Springer Science and Business Media Deutschland GmbH
Neural Computing and Applications
2025#37Issue 75671 - 5682 pp.
Lower limb rehabilitation robots can help to improve the locomotor capabilities of patients experiencing gait impairments and help medical workers by reducing strain on them. However, since commercially available exoskeletons are expensive and there is a lack of number of physiotherapists many patients are still not able to get proper rehabilitation training. The closed-loop linkage mechanisms have recently drawn much attention in the realization of gait rehabilitation robots. Such mechanisms are affordable and capable of providing suitable trajectories for gait training therapy. In this work, we have proposed a fully operational one degree-of-freedom mechanism which can generate complex naturalistic lower limb trajectories. Although in theory, it is assumed that the constant speed applied at the input crank is sufficient to control the system, in reality, the external forces exerted by human legs and the inertia of the links can greatly alter the rotational velocity at the crank, which may negatively affect the training process. Therefore, we have explored the performance of a deep reinforcement learning-based control algorithm designed to regulate the speed of the input crank to reach satisfactory performance needed for gait rehabilitation training. Experimental evaluations with healthy human subjects were conducted to demonstrate that the mechanism is capable of directing lower limbs on naturalistic gait trajectories with a required walking speed.
Deep reinforcement learning , Exoskeleton , Gait rehabilitation , Robot , Stephenson III mechanism , Velocity control
Text of the article Перейти на текст статьи
School of Information Technology and Systems, University of Canberra, Canberra, 2617, ACT, Australia
School of Clinical Sciences, Queensland University of Technology, Brisbane, QLD, Australia
School of Systems and Computing, UNSW, Canberra, ACT, Australia
Department of Electrical and Computer Engineering, Nazarbayev University, Nur-Sultan City, Kazakhstan
School of Information Technology and Systems
School of Clinical Sciences
School of Systems and Computing
Department of Electrical and Computer Engineering
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026