Reproduce “DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for 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
Shuzheng Wang, Haoxuan Li, Shengzhen Li, Chenxi Wu, Yajing Sun, Lu Hou, Wenyu Liu, Xinggang Wang
DriveWLA plans driving trajectories by combining a World Expert for future scene dynamics, a Language Expert for scene semantics, and an Action Expert for trajectory generation. World and Language exchange representations, while Action reads both without feeding information back. On NAVSIM v1 navtest, it scores 92.3 PDMS, above SimWAM’s 91.5; this is benchmark evidence, not public-road validation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.