Reproduce “Automatic Calibration for an Open-source Magnetic Tactile Sensor” 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
Lowiek Van den Stockt, Remko Proesmans, Francis wyffels
An open-source magnetic tactile sensor features an automatic, in situ, and gripper-agnostic calibration method, demonstrating an average R² of 0.83 and an MSE of 0.97 N² for force prediction.
Key insights
- Combining an open-source design with an automatic, in situ calibration strategy significantly reduces financial and technical barriers to adopting advanced tactile sensing.
- The polynomial force prediction models derived from magnetic field data offer practical accuracy for robotic applications.
- Mechanical hysteresis in the resin domes is identified as a factor influencing dynamic response, pointing to a specific area for future material and design improvements.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.