Aug 2026· Frontiers in Robotics and AI· Vol 13· 0 citations· 43 references
Medicine
TL;DR
The results demonstrate that the proposed framework improves contact transition safety, force regulation accuracy, and task adaptability at the control-performance level, providing a feasible basis for further development of robotic physiotherapy systems.
Abstract
Robot-assisted physiotherapy has attracted increasing attention for its potential to provide repeatable, stable, and controllable physical interaction during rehabilitation-oriented therapy. However, contact-rich physiotherapy tasks remain challenging because the robot must reproduce therapist-demonstrated massage skills while adapting to non-planar and deformable body surfaces, suppressing impact during contact transition, and maintaining stable force regulation. This paper proposes a contact-aware robot-assisted physiotherapy framework that integrates task-space skill generalization, contact state estimation, dynamic velocity adjustment, force-error compensation, and bounded variable impedance control. Therapist-guided demonstrations are encoded using Dynamic Movement Primitives (DMPs) to construct a physiotherapy skill library, enabling typical massage skills, including kneading, patting, pushing, and pressing, to be generalized to new start and goal points in the robot Cartesian task space. During execution, force/torque feedback is used to estimate the contact point and surface normal, update the local task frame, regulate the approach velocity, and compensate for force-tracking errors. Experimental validation was conducted on a silicone abdominal model and in a preliminary healthy-volunteer back physiotherapy test. The results show that the proposed dynamic contact strategy suppresses excessive impact during contact transition, avoiding the 165.86 N peak impact observed under high-speed contact. The force compensation strategy reduces the force-tracking RMSE from 0.835 N to 0.395 N , corresponding to a 52.69% improvement. In addition, the bounded variable impedance strategy improves motion-force coordination compared with fixed-stiffness control. These results demonstrate that the proposed framework improves contact transition safety, force regulation accuracy, and task adaptability at the control-performance level, providing a feasible basis for further development of robotic physiotherapy systems.
Results demonstrate that DRL-based methods, particularly when combined with traditional controllers, improve both force reduction and motion stability over conventional control strategies.
Mohammad Sahandi, G. Vossoughi, H. Zohoor et al.· IEEE Access· 0 citations
Safe and intuitive human robot interaction (HRI) requires precise regulation of contact forces and torques while adapting to dynamic and uncertain human behavior. Traditional impedance and admittance control strategies rely on fixed parameters and accurate system modeling, which often limit their performance in unstructured or collaborative environments. This paper presents an AI-enabled force and torque control framework that integrates machine learning techniques with conventional control methods to enhance adaptability, compliance, and safety in physical human robot interaction. The proposed approach employs deep neural networks and reinforcement learning to learn human intent and interaction dynamics directly from multi-modal sensor data, including force torque sensors, joint encoders, and inertial measurements. By continuously adjusting control gains in real time, the system achieves stable interaction while minimizing excessive contact forces and undesired torques. Experimental evaluations conducted on a collaborative robotic platform demonstrate significant improvements over classical control schemes, including reduced interaction force peaks, smoother torque profiles, and improved task execution efficiency during cooperative manipulation tasks. The results indicate that AI-driven force and torque control can substantially improve robustness, adaptability, and user comfort in human robot collaboration, making it a promising solution for applications in rehabilitation robotics, assistive devices, and industrial cobots.
Vishal Khanna· i-manager's Journal on Augme...· 0 citations
To address the coupling between ambiguous sEMG-based intention recognition and mechanical safety constraints in cable-driven lower-limb rehabilitation, this study proposes a multimodal perception-based adaptive admittance control framework. Mechanical, interaction, and physiological indicators, including stiffness, end-effector position, coupling force, velocity, joint motion, and sEMG, were fused to estimate active participation, passive/flaccid tracking, and spasticity risk. The identified state was then used to adjust admittance parameters online, while an RBFNN-SMC inner loop improved trajectory tracking. Experiments showed high-damping, low-stiffness protection during spasticity bursts and milder responses during passive conditions. Compared with PID, RBFNN-SMC reduced tracking errors, supporting safer adaptive rehabilitation control.
Yanzhuo Wang, Keyi Wang, Lan Wang et al.· 2026 IEEE International Conf...· 0 citations
A novel assist-as-needed control framework that integrates reinforcement learning with a fuzzy supervisor and a force field-based tunnel for upper-limb three-dimensional reaching tasks and demonstrates the feasibility of the proposed adaptive impedance modulation and supervisory assistance architecture in healthy-subject human-robot interaction.
Knee rehabilitation robots can effectively assist the recovery of patients with lower limb motor dysfunction. This paper presents a lightweight single-drive adaptive knee rehabilitation robot for supine training. The robot consists of a waist support, a thigh mechanism, and a shank-foot mechanism, and provides continuous adjustment of thigh length, shank length, and foot support angle to improve geometric matching for users with different body sizes and postures. To reduce the influence of the device’s self-weight on training, a gravity compensation method based on kinematic coupling is developed, and a sensorless interaction torque estimation method based on motor current feedback is introduced. Using only a single encoder and motor current feedback, the system achieves passive, active-assistive, and resistive behaviors within a unified control framework, without explicit mode switching. Experimental results show that, in active-assist mode, the initial response delay is about 240.0 ms, the trajectory correlation coefficient reaches 0.9960, and the maximum position error is 13.48 mm. In admittance-based interaction control mode, the estimated interaction torque agrees well with the measured torque, with a Pearson correlation coefficient of 0.954, and the average volunteer rating under six impedance levels remains above 3.7/5. These results demonstrate that the proposed robot achieves good adaptability, stable tracking, and reliable human-robot interaction, providing a practical solution for low-cost and integrated knee rehabilitation.
Mei Feng, Xiang Chen, Chao Han et al.· 2026 IEEE International Conf...· 0 citations
Assist-as-needed (AAN) assistance can encourage active participation during human walking. However, individuals exhibit diverse walking patterns, which makes it challenging for exoskeleton to provide personalized assistance. This paper presents an innovative adaptive AAN control strategy with hybrid torque fusion, including two modules of hybrid torque fusion estimation and adaptive control to promote voluntary participation. Specifically, the hybrid torque fusion module fuses torque estimated from surface electromyography (sEMG) signals with dynamic model estimation using regularized particle filter fusion (RPFF) algorithm to evaluate the human’s active participation. The control module incorporates a globally continuous extended assistance level function (EALF) that integrates joint motion tracking error, human-robot interaction force, and voluntary deficit to quantify subject performance and enable smooth transitions between four training modes, thereby continuously adjusts the torque output. Comprehensive comparisons with existing AAN strategies under multiple scenarios demonstrate that the proposed method improves trajectory tracking accuracy by approximately 16.1% and reduces human-robot interaction force by 4.01% during slope walking and simulated gait impairment. NASA-TLX and Likert scale assessments further validate the method’s effectiveness in enhancing active participation and wearing comfort. Note to Practitioners—To address insufficient active participation and unsmooth assistance in walking rehabilitation using ankle exoskeleton, caused by incomplete quantification of human motor ability, this study introduces a human active torque fusion mechanism. We developed a personalized human-robot collaboration model and proposed an AAN control algorithm based on an assistance function. This algorithm can potentially be transferred or extended to other rehabilitation robotic platforms. Although the system demonstrates promising application potential, this study acknowledges certain limitations, such as a small sample size and insufficient exploration of diverse patient population needs. Future research can build on this work by integrating additional sensing technologies, optimizing control strategies to enhance system adaptability, and exploring more efficient adaptive or online learning methods to simplify the parameter calibration process before training. This study offers the potential to significantly improve daily living for individuals with mobility limitations, laying the groundwork for more personalized and effective rehabilitation solutions.
Quan Liu, Siyuan Wang, Chang Zhu et al.· IEEE Transactions on Automat...· 0 citations
