SMAT: Staged Multi-Agent Training for Co-Adaptive Exoskeleton Control
SMAT: Staged Multi-Agent Training for Co-Adaptive Exoskeleton Control
This paper introduces SMAT, a staged multi-agent training framework designed to solve the non-stationary learning problem inherent in human-device co-adaptation.
The study presents a four-stage training curriculum for co-adaptive control of hip exoskeletons, validated in simulation and on five human subjects via treadmill experiments.
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.
- Environment
- SimulationOpen source S4
Reported numbers
mean positive power at 6 Nm RMS torque
13.6
View original evidence
er in an offline setting using open-source gait data, then deployed it to a physical hip exoskeleton for treadmill experiments with five subjects. The resulting policy delivers consistent assistance and predominantly positive mechanical power without the need for any explicitly imposed timing shift (mean positive power: 13.6 W at 6 Nm RMS torque to 23.8 W at 9.3 Nm RMS torque, with minimal negative power) consistentl
Open source S5mean positive power at 9.3 Nm RMS torque
23.8
View original evidence
er in an offline setting using open-source gait data, then deployed it to a physical hip exoskeleton for treadmill experiments with five subjects. The resulting policy delivers consistent assistance and predominantly positive mechanical power without the need for any explicitly imposed timing shift (mean positive power: 13.6 W at 6 Nm RMS torque to 23.8 W at 9.3 Nm RMS torque, with minimal negative power) consistentl
Open source S5mean positive power: 13.6 W at 6 Nm RMS torque to 23.8 W at 9.3 Nm RMS torque
13.6
View original evidence
er in an offline setting using open-source gait data, then deployed it to a physical hip exoskeleton for treadmill experiments with five subjects. The resulting policy delivers consistent assistance and predominantly positive mechanical power without the need for any explicitly imposed timing shift (mean positive power: 13.6 W at 6 Nm RMS torque to 23.8 W at 9.3 Nm RMS torque, with minimal negative power) consistentl
Open source S5mean positive power: 13.6 W at 6 Nm RMS torque to 23.8 W at 9.3 Nm RMS torque
23.8
View original evidence
er in an offline setting using open-source gait data, then deployed it to a physical hip exoskeleton for treadmill experiments with five subjects. The resulting policy delivers consistent assistance and predominantly positive mechanical power without the need for any explicitly imposed timing shift (mean positive power: 13.6 W at 6 Nm RMS torque to 23.8 W at 9.3 Nm RMS torque, with minimal negative power) consistentl
Open source S5
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
s co-adapt with full torque capacity and bidirectional feedback. We implement SMAT in the MyoAssist simulation environment using a 26-muscle lower-limb model and an attached hip exoskeleton. Our musculoskeletal simulations demonstrate that the learned exoskeleton control policy produces an average 10.1% reduction in simulated hip muscle activation relative to the no-assist condition. We validated the learned controll
Open source S4
er in an offline setting using open-source gait data, then deployed it to a physical hip exoskeleton for treadmill experiments with five subjects. The resulting policy delivers consistent assistance and predominantly positive mechanical power without the need for any explicitly imposed timing shift (mean positive power: 13.6 W at 6 Nm RMS torque to 23.8 W at 9.3 Nm RMS torque, with minimal negative power) consistentl
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org