AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

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

Yingyan Li, Yuqi Wang, Yang Liu, Jiawei He, Lue Fan, Zhaoxiang Zhang

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 118 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add trajectory evaluation (reward model on current state only) (ablation)TransFuser baseline · NAVSIM test (ablation, 20 epochs)PDMS: 81.0 -> 83.2Improved
add BEV world model future states to reward model (ablation)WoTE · NAVSIM test (ablation, 20 epochs)PDMS: 83.2 -> 85.6Improved
add simulation rewards to imitation reward (ablation)WoTE · NAVSIM test (ablation, 20 epochs)PDMS: 83.5 -> 85.6Improved
add imitation reward to simulation rewards (ablation)WoTE · NAVSIM test (ablation, 20 epochs)PDMS: 83.6 -> 85.6Improved
predict future recurrently with 2s step (0s->2s->4s) instead of one 4s step (ablation)WoTE · NAVSIM test (ablation, 20 epochs)PDMS: 84.0 -> 85.6Improved
increase trajectories from 64 to 128 (ablation)WoTE · NAVSIM test (ablation, 20 epochs)PDMS: 84.5 -> 85.4Improved
increase trajectories from 128 to 256 (ablation)WoTE · NAVSIM test (ablation, 20 epochs)PDMS: 85.4 -> 85.6Improved
increase trajectories from 64 to 256 (ablation)WoTE · NAVSIM test (ablation, 20 epochs)Latency: 17.2 ms -> 18.7 msHurt
use 1024 unseen trajectory anchors at test time (trained on 256) (ablation)WoTE · NAVSIM test (ablation, 20 epochs)PDMS: 84.0 -> 85.3Improved
feed refined trajectories to world model instead of raw anchors (ablation)WoTE · NAVSIM test (ablation, 20 epochs)PDMS: 84.0 -> 85.6Improved
model-based trajectory evaluation instead of model-free (Hydra-MDP)WoTE · NAVSIM testPDMS: 86.5 -> 88.3Improved
add WoTE trajectory evaluation to TCPTCP · Bench2DriveDriving Score: 59.90 -> 61.71Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy