⌁ Awesome World Model Hub Papers · Datasets · Projects
中文 GitHub
← Back to papers

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

ICCV 25 2025 56.8 method, application

TLDR

Proposes WoTE, an end-to-end driving framework using a BEV world model for online trajectory evaluation, achieving SOTA on simulated benchmarks.

Reasoning

The paper introduces a novel BEV world model for trajectory evaluation, demonstrating latency efficiency and strong performance on NAVSIM and Bench2Drive benchmarks. However, it lacks real-world validation and does not address generative or interactive aspects explicitly.

Read-first score

Read-first score 56.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 24.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Reproducibility 25%
81

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=True; dataset=False; markers=code,github

Methodology quality 25%
60

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,evaluation

Topical relevance 42%
34.3

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Field roles

FrontierReproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 519.

Keyword Scores

world model
10
world dynamics prediction
8
world simulator
2
model-based reinforcement learning world model
2
generative world model
1
interactive world model
1
video world model
0

Deep Analysis

Innovations

  • Proposes WoTE, an end-to-end driving framework that leverages a BEV world model for online trajectory evaluation
  • BEV world model is latency-efficient compared to image-level world models
  • Seamless supervision using off-the-shelf BEV-space traffic simulators

Methodology

WoTE uses a BEV world model to predict future BEV states for trajectory evaluation within an end-to-end differentiable framework. The model is trained with supervision from BEV-space traffic simulators and evaluated on NAVSIM and closed-loop Bench2Drive benchmarks.

Key Results

Achieves state-of-the-art performance on both the NAVSIM benchmark and the closed-loop Bench2Drive benchmark based on the CARLA simulator.

Resources

PaperCode

Tags