Reproduce “Prognostic Framework for Robotic Manipulators Operating Under Dynamic Task Severities” 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
Ayush Mohanty, Jason Dekarske, Stephen K. Robinson, Sanjay Joshi, Nagi Gebraeel
Researchers from Georgia Institute of Technology developed a prognostic framework to predict the Remaining Useful Life (RUL) of robotic manipulators by modeling degradation under dynamic task severities. The framework achieved prediction errors as low as 2.9% for planar robots and 3.3% for spatial robots closer to failure, offering a computationally efficient closed-form solution for RUL estimation.
Key insights
- The proposed framework accurately predicts RUL under dynamic task severities, showing superior performance compared to models neglecting varying operational loads.
- A novel closed-form solution for RLD offers significant computational efficiency over Monte Carlo simulations, making it suitable for real-time applications and "what-if" analyses.
- The periodic calibration task scheme effectively addresses data heterogeneity, enabling robust degradation modeling for diverse robotic operations.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.