Reproduce “RiSE-Drive: Risk-Sensitive Long-Horizon Candidate Evaluation for End-to-End 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
Yu Zhao, Hongyi Duan, Ming Yin, Hongyuan Zhang, Fan Yang, Hongzhi Wang, Xiubo Liang
RiSE-Drive improves candidate selection for autonomous driving by evaluating proposed routes across multiple modeled future conditions. It propagates each candidate under four learned conditions, estimates a distribution of long-horizon outcomes, and ranks routes by average performance while penalizing downside and variation. On NAVSIM-v2 navhard-two-stage, matched ViT-S RiSE-Drive scores 51.3 EPDMS versus DrivoR’s 48.3; benchmark evidence does not establish real-world safety.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.