Reproduce “A Risk-Sensitive and Uncertainty-Aware Decision-Making and Control Framework for Safe and Robust Autonomous Driving” 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

Zhuoren Li, Ran Yu, Weiqi Zhang, Ming Liu, Lu Xiong, Chen Sun, Bo Leng

RUDC-T adapts a safety controller for autonomous vehicles navigating dense, unsignalized left turns by estimating policy risk and uncertainty, then adjusting constraint slack; it also predicts barrier residuals. In simulation, it achieved 86.3% success and 7.9% violations, versus 81.6% and 16.5% for USL, while moving more slowly. A fixed-filter ablation had fewer violations but frequent freezing, limiting claims to simulated intersections.

Summary by alphaXiv.

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