Reproduce “Leveraging Haptic Feedback to Improve Data Quality and Quantity for Deep Imitation Learning 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
Catie Cuan, Allison Okamura, Mohi Khansari
The authors test whether haptic feedback during teleoperation changes demonstrations and policies for latch-door opening. Wrist forces drive vibrations in the controller, while policies use images, not force readings. After curation, 36% of Haptic data remained, versus 30% of Non-Haptic data. Policy performance rose by 11% on average, but right-only policies performed similarly; gains were concentrated in left-only and combined conditions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.