Reproduce “Towards AI-controlled FES-restoration of arm movements: Controlling for progressive muscular fatigue with Gaussian state-space models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Nat Wannawas, A.Aldo Faisal
The authors introduce RL-GSSM, an RNN-based Gaussian state-space model that gives a reinforcement-learning controller a probabilistic summary of observation history for simulated electrical-stimulation control of a two-joint arm. It uses recent movement clues as fatigue changes muscle response, rather than relying on current observations alone. In a 60-second simulated trajectory, tracking RMSE was 6.84°, slightly better than vanilla RL; this result is not human evidence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.