Design and Validation of a Robotic Knee Exoskeleton with Musculoskeletal Simulation-Derived Biological Torque Control
Design and Validation of a Robotic Knee Exoskeleton with Musculoskeletal Simulation-Derived Biological Torque Control
This paper presents an open-source robotic knee exoskeleton built from off-the-shelf components, featuring a biological torque controller derived entirely from simulation. By using a muscle-driven imitation policy trained on an open biomechanics dataset to reproduce squatting motions, the system distills knee moments into an estimator that relies solely on onboard sensors, eliminating the need for device-specific data collection. Validation with seven able-bodied participants showed that assistance reduced peak biological knee extension moment by 21.5% and peak vastus medialis activation by 26.7% during squatting compared to unassisted squatting (p<0.05). The results demonstrate successful transfer of a simulation-derived controller to physical hardware, enabling research groups to train and compare controllers on shared hardware without additional data collection overhead.
The study validates a knee exoskeleton controller derived from simulation that transfers to physical hardware without requiring new data collection on the device, demonstrating a reduction in peak knee extension moment and vastus medialis activation during squatting across seven participants.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
peak biological knee extension moment reduction
21.5
Reported trials
View original evidence
ven imitation policy reproduces squatting motions from an open biomechanics dataset, and the resulting knee moments are distilled into an estimator that uses only onboard sensors, so no training data are recorded on the device. In seven able-bodied participants, assistance reduced peak biological knee extension moment by 21.5% and peak vastus medialis activation by 26.7% during squatting, relative to squatting withou
Open source S4peak vastus medialis activation reduction
26.7
Reported trials
View original evidence
ven imitation policy reproduces squatting motions from an open biomechanics dataset, and the resulting knee moments are distilled into an estimator that uses only onboard sensors, so no training data are recorded on the device. In seven able-bodied participants, assistance reduced peak biological knee extension moment by 21.5% and peak vastus medialis activation by 26.7% during squatting, relative to squatting withou
Open source S4
- paper: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ven imitation policy reproduces squatting motions from an open biomechanics dataset, and the resulting knee moments are distilled into an estimator that uses only onboard sensors, so no training data are recorded on the device. In seven able-bodied participants, assistance reduced peak biological knee extension moment by 21.5% and peak vastus medialis activation by 26.7% during squatting, relative to squatting withou
Open source S4
t the exoskeleton (p<0.05). Our results demonstrate that a biological torque controller derived from simulation can transfer to physical hardware without device-specific data collection. Because the hardware and training pipeline are released together, research groups can train and compare knee exoskeleton controllers on shared hardware without additional data collection overhead.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org