Transformer-Based Trajectory Prescription for sEMG-Optimizing Robot-Mediated Rehabilitation
Transformer-Based Trajectory Prescription for sEMG-Optimizing Robot-Mediated Rehabilitation
This research introduces a personalizable transformer model that maps muscle activations measured via surface electromyography to prescribed contact force trajectories for rehabilitation robots. Using data from 16 healthy participants, the model achieves mean trajectory prediction errors of less than 8% on held-out tasks and users, with effectively instantaneous deterministic inference and sub-second sampling of trajectory distributions. An initial test during live rehabilitation tasks shows participants reaching target neuromotor activations with an average error of just 15%. The work provides a proof of concept for data-driven, activation-targeted trajectory prescription in robot-mediated rehabilitation and establishes a foundation for future validation in clinical populations. Data and code are open-sourced as part of the OpenRobotRehab project on SimTK.
The study presents a transformer-based model that maps surface electromyography signals to contact force trajectories for robot-mediated rehabilitation, achieving mean prediction errors under 8% on held-out tasks and users with sub-second inference.
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.
- Data origin
- Robot trajectoriesOpen source S3
Reported numbers
trajectory tracking tasks
15
Reported trials
View original evidence
specific neuromotor factors, and augments trajectory prediction with flow matching to produce a distribution over plausible prescriptions biased toward the training distribution. Using data from 16 healthy participants completing 15 isometric trajectory tracking tasks, we evaluate generalization across held-out tasks and users, as well as the feasibility of user-specific fine-tuning within a therapy-session timescale
Open source S4
- code: Reported pending Open source S6
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
itation robot behavior, we present a personalizable transformer-based model mapping individuals' muscle activations (as measured via surface electromyography) to prescribed contact force trajectories when interacting with an end-effector rehabilitation robot. The model uses a transformer encoder-decoder leveraging rotary positional embeddings (RoPE) to generate a latent representation of trajectory-relevant and user-
Open source S3
. The model achieves mean trajectory prediction errors of <8% on held out tasks and users, with effectively instantaneous deterministic inference and sub-second sampling of trajectory distributions. An initial test using the model during live rehabilitation tasks demonstrates that, on average, participants reach the target neuromotor activations with just 15% error accumulated throughout the task. These results provi
Open source S5
specific neuromotor factors, and augments trajectory prediction with flow matching to produce a distribution over plausible prescriptions biased toward the training distribution. Using data from 16 healthy participants completing 15 isometric trajectory tracking tasks, we evaluate generalization across held-out tasks and users, as well as the feasibility of user-specific fine-tuning within a therapy-session timescale
Open source S4
arXiv:2611.08295v1 Announce Type: new Abstract: Robot-mediated rehabilitation has the potential to deliver high-intensity, individualized therapy, but existing systems (which have not consistently improved outcomes) typically prescribe kinematic trajectories rather than explicitly targeting the neuromotor activations thought to support recovery. To address this gap, and ultimately enable activation-optimizing rehabil
Open source S2
Transformer-Based Trajectory Prescription for sEMG-Optimizing Robot-Mediated Rehabilitation
Open source S1
de a proof of concept for data-driven, activation-targeted trajectory prescription in robot-mediated rehabilitation and establish a foundation for future validation in clinical populations. Data and code have been open-sourced as part of the OpenRobotRehab project on SimTK.
Open source S6
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Match the buyer’s robot embodiment, action space, sensors and timestamp requirements before planning collection.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org