Intelligent Soft Wearable Robots for Rehabilitation: A Review of Bioelectronic Sensing, Multimodal Sensor Fusion, and AI-Driven Control

Soft wearable robots transmit assistance through compliant actuators, textiles and body-conforming interfaces, offering opportunities for rehabilitation and the support of residual motor function. Their clinical value depends on the integration of deformable mechanics with reliable sensing, timely state estimation and appropriate control. Structured Scopus and Europe PMC searches informed purposive assessment of selected primary reports. This critical narrative review examines bioelectronic sensing, multimodal sensor fusion and artificial intelligence (AI) within the sensing–estimation–control–feedback loop of soft wearable rehabilitation robots. Upper- and lower-limb architectures, actuation and attachment mechanisms are considered alongside neuromuscular, kinematic, mechanical and physiological measurements. Fusion methods and AI models are assessed in relation to intention recognition, continuous movement estimation, physiological assessment, personalisation and real-time implementation. A five-level control framework distinguishes fixed, sensor-triggered, AI-informed, adaptive intelligent and human–robot co-adaptive assistance, while a complementary evidence framework records integration, population, study design, exposure, deployment setting and assisted or unassisted outcome as separate attributes. Direct soft-wearable evidence is distinguished from supporting work in other rehabilitation robots, prostheses and wearable sensing. Reported advances support selected assisted and training outcomes, but reliable repeated-session operation and retained functional benefit remain unevenly demonstrated. Key barriers include garment-dependent measurement changes, biosignal variability, synchronisation, model generalisation, actuator hysteresis, energy demand, usability and clinical validation. The review identifies priorities for uncertainty-aware fusion, bounded adaptation, local inference, representative benchmarks and longitudinal evaluation, linking technical progress to safe, practical and clinically meaningful rehabilitation.

Authors

Institutions

Publication Details

Journal
Electronics
Published
2026-11-17
DOI
https://doi.org/10.3390/electronics15225355
Primary Topic
Prosthetics and Rehabilitation Robotics
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Intelligent Soft Wearable Robots for Rehabilitation: A Review of Bioelectronic Sensing, Multimodal Sensor Fusion, and AI-Driven Control

Jung-Hoon Sul, Zhenglin Wang, Lasitha Piyathilaka, Diluka Moratuwage et al.
2 links
Electronics
Prosthetics and Rehabilitation Robotics
article

Intelligent Soft Wearable Robots for Rehabilitation: A Review of Bioelectronic Sensing, Multimodal Sensor Fusion, and AI-Driven Control

Jung-Hoon Sul, Zhenglin Wang, Lasitha Piyathilaka, Diluka Moratuwage, Amal Jayawardena, Jaliya L. Wijayaraja
article en

Abstract

Soft wearable robots transmit assistance through compliant actuators, textiles and body-conforming interfaces, offering opportunities for rehabilitation and the support of residual motor function. Their clinical value depends on the integration of deformable mechanics with reliable sensing, timely state estimation and appropriate control. Structured Scopus and Europe PMC searches informed purposive assessment of selected primary reports. This critical narrative review examines bioelectronic sensing, multimodal sensor fusion and artificial intelligence (AI) within the sensing–estimation–control–feedback loop of soft wearable rehabilitation robots. Upper- and lower-limb architectures, actuation and attachment mechanisms are considered alongside neuromuscular, kinematic, mechanical and physiological measurements. Fusion methods and AI models are assessed in relation to intention recognition, continuous movement estimation, physiological assessment, personalisation and real-time implementation. A five-level control framework distinguishes fixed, sensor-triggered, AI-informed, adaptive intelligent and human–robot co-adaptive assistance, while a complementary evidence framework records integration, population, study design, exposure, deployment setting and assisted or unassisted outcome as separate attributes. Direct soft-wearable evidence is distinguished from supporting work in other rehabilitation robots, prostheses and wearable sensing. Reported advances support selected assisted and training outcomes, but reliable repeated-session operation and retained functional benefit remain unevenly demonstrated. Key barriers include garment-dependent measurement changes, biosignal variability, synchronisation, model generalisation, actuator hysteresis, energy demand, usability and clinical validation. The review identifies priorities for uncertainty-aware fusion, bounded adaptation, local inference, representative benchmarks and longitudinal evaluation, linking technical progress to safe, practical and clinically meaningful rehabilitation.

ElectronicsVol. 15(22)
University of Kelaniya (LK), Central Queensland University (AU)
Good health and well-being
Prosthetics and Rehabilitation Robotics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon