28 July 2022 in IEEE Transactions on Medical Robotics and Bionics
Dynamic control of an intrinsically compliant robot is paramount to ensuring safe and synergistic assistance to the patient. This paper presents an impedance controller for the rehabilitation of stroke patients with compromised wrist motor functions. The control design employs a Koopman operator-based autodidactic system identification model to predict the anatomical stiffness of the wrist joint during its various degrees of rotational motion. The proposed impedance controller, perceiving the level of the subjects’ participation from their joint stiffness, can modify the applied force. The end-effector robot has a parallel structure that uses four biomimetic muscle actuators as parallel links between the end-effector and the base platform. The controller performance is corroborated by testing the end-effector robot with three healthy subjects.
10 October 2022 in IEEE Transactions on Human-Machine Systems
Disability from injuries and diseases is a global problem affecting a large population; however, due to a lack of therapists and labor-intensive procedures, only a few benefits from rehabilitation. Robots can assist therapists in treating many patients simultaneously, but the existing solutions need improvements in their mechanism, actuation, and control. This article presents a four-link parallel end-effector robot for wrist joint rehabilitation. The proposed robot employs biomimetic muscle actuators (BMA) that provide intrinsic compliance to the robotic system. A fuzzy-based model is developed to identify the nonlinear nature of BMAs. The stiffness-observer learns subject-specific stiffness, which is used to modify the robot reference trajectories. An adaptive controller uses the fuzzy model and stiffness-observer and simultaneously controls the four BMAs to provide three degrees of rotational freedom to the robot end-effector. The feasibility of the robot mechanism and the controller was evaluated through proof of concept experiments conducted with three unimpaired human subjects. It was found that the controller was able to guide the robot–human system on the commanded trajectories in the presence of parallel actuation of compliant and nonlinear BMAs. Furthermore, the controller was also able to modify the commanded trajectories in the higher stiffness regions of the wrist workspace.
9 September 2022 in IEEE Transactions on Industrial Electronics
Rehabilitation robots have proven their usefulness in assisting with physical therapy. This article presents a trajectory tracking controller for a wrist rehabilitation robot with three degrees of freedom. The nonlinearity of the human-robot interaction dynamics has been defined as the Koopman linear system in terms of nonlinear observable functions of the state variables. Koopman operators are learned using linear regression to encode the states into object-centric embedding space for a linear approximation of a nonlinear dynamical system. The learned Koopman operators ascertain the system dynamics applied to design the wrist robot's trajectory tracking task controller. This is a data-driven approach that yields an explicit control-oriented model. The efficiency and feasibility of the controller were evaluated through experiments with three healthy human subjects. The experiments demonstrated the ability of the controller to guide the subject's wrist along the reference trajectory.
11 December 2024 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Advancements in robotic neurorehabilitation have made it imperative to enhance the safety and personalization of physical human-robot interactions (pHRI). Estimation and management of energy transfer between humans and robots is essential for enhancing safety during the rehabilitation. Traditional control methods, which rely on coordinate-based monitoring of robot velocity and external forces, often fail in unstructured environments due to their susceptibility to sensor noise and limited adaptability to individual patient needs. This paper introduces the concept of transactive energy, a coordinate-invariant entity that captures the energy dynamics between the human and the robot during robot-assisted rehabilitation and can be used for personalized robot control. However, estimation of such energy transfer is a complex process and therefore, we have developed a transformer-based model to predict the transactive potential energy. The proposed model is implemented on an ankle rehabilitation robot which is a compliant parallel robot and provides the required three rotational degrees of freedom (DOF). The model learns from the data obtained from the experiments carried out using the ankle robot with five stroke patients on two types of controllers: an impedance controller operated in zero impedance control mode and a trajectory tracking controller. This study provides a baseline, for future research on energy-based control mechanisms in pHRI applications, by utilizing the advanced deep learning models.
18 April 2025 in IEEE Transactions on Medical Robotics and Bionics
Robotic-assisted rehabilitation for wrist movements demands adaptive systems capable of balancing patient autonomy with robotic support. The integration of artificial intelligence (AI) into robotic-assisted rehabilitation offers transformative potential in delivering personalized, dynamic, and effective therapeutic interventions. This study introduces a novel neuromechanical control framework integrating a passivity observer with Quantum-Enhanced Deep Reinforcement Learning (QDRL) for adaptive impedance scaling in wrist rehabilitation robotics. The passivity observer continuously monitors energy exchanges to classify patient states into passive (patient requiring robotic assistance) and non-passive (patient actively participating) categories, dynamically guiding the robot’s impedance adjustments. Experiments were conducted with ten unimpaired human subjects (eight male and two female), who were instructed to simulate rehabilitation scenarios, focusing on three key wrist movements, flexion/extension (FL/EX), abduction/adduction (AB/AD), and pronation/supination (PR/SU). Experimental results showed high correlations ( > 0.83 ) between energy-based and electromyography (EMG)-based passivity classifications, confirming the reliability of the proposed approach. Furthermore, the designed QDRL model significantly outperformed traditional reinforcement learning methods, achieving superior adaptability, stability, and higher average rewards during robotic impedance control. The framework offers advancement in optimizing robotic assistance during motor recovery, promoting personalized rehabilitation by tailoring interventions to the specific needs of each patient.
15 July 2025 in Robotics and Autonomous Systems