Reproduce “Neuromechanics-based Deep Reinforcement Learning of Neurostimulation Control in FES cycling” 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, Mahendran Subramanian, A. Aldo Faisal
The authors train a reinforcement-learning controller in a fatigue-aware virtual cyclist to select stimulation patterns and intensity for six muscles. In simulation, it tracks cadences of 5, 8, and 3 rad/s with the lowest root mean square cadence-tracking error and shortest response time among tested controllers. However, it received privileged fatigue information, and the comparison tested only PID and fuzzy logic.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.