Reproduce “Learning to Drift with Individual Wheel Drive: Maneuvering Autonomous Vehicle at the Handling Limits” 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

Yihan Zhou, Yiwen Lu, Bo Yang, Jiayun Li, Yilin Mo

The authors train a learned controller in a fast simulator with varied paths, vehicle conditions, and disturbances, then deploy it without fine-tuning on a 1/10-scale car with independently controlled wheels. The policy tracks paths while drifting. On a five-circle course it sustains repeated drift-direction changes; tests show sim-to-real transfer on controlled RC-car courses, not full-size vehicles or public roads.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.