End-to-End Driving with Online Trajectory Evaluation via BEV World Model

Yuqi Wang, Yingyan Li

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• liyingyanucas/wote — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

End-to-end autonomous driving has achieved remarkable progress by integrating perception, prediction, and planning into a fully differentiable framework. Yet, to fully realize its potential, an effective online trajectory evaluation is indispensable to ensure safety. By forecasting the future outcomes of a given trajectory, trajectory evaluation becomes much more effective. This goal can be achieved by employing a world model to capture environmental dynamics and predict future states. Therefore, we propose an endto-end driving framework WoTE, which leverages a BEV World model to predict future BEV states for Trajectory Evaluation. The proposed BEV world model is latencyefficient compared to image-level world models and can be seamlessly supervised using off-the-shelf BEV-space traffic simulators. We validate our framework on both the NAVSIM benchmark and the closed-loop Bench2Drive benchmark based on the CARLA simulator, achieving state-of-the-art performance. Code is released at https://github. com/liyingyanUCAS/WoTE.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2504.01941")
get_code_for_paper("2504.01941")
have("2504.01941")

Connect an agent — have() is free.