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

OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model

arXiv 2026 39 method, system, application

TLDR

OWMDrive uses a 4D occupancy world model for multi-step forecasting to guide diffusion-based planning, improving autonomous driving safety in occluded scenarios.

Reasoning

Strengths: explicit modeling of temporal causal dynamics and future rollouts for robust planning. Weaknesses: abstract lacks details on real-world validation and comparison to baselines; limited explanation of the occupancy world model architecture.

Read-first score

Read-first score 39, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 41.

Recency 6%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 18%
60

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

Topical relevance 29%
58.6

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

Reproducibility 18%
30

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Citation impact 18%
0

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 12%
0

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 231.

Keyword Scores

world model
9
generative world model
8
world dynamics prediction
8
video world model
6
world simulator
5
model-based reinforcement learning world model
3
interactive world model
2

Deep Analysis

Innovations

  • Occupancy World Model for multi-step 3D occupancy forecasting as a conditional prior
  • Diffusion-based planning conditioned on predicted future states
  • Causality-aware end-to-end driving via explicit modeling of future scene evolution and spatiotemporal dependencies

Methodology

OWMDrive is a generative end-to-end framework that uses an Occupancy World Model to forecast multi-step 3D occupancy, providing a conditional prior for a diffusion-based planner. The planner iteratively refines trajectory candidates conditioned on current observations and predicted future states to generate a driving trajectory.

Key Results

OWMDrive significantly improves planning reliability and safety, especially in challenging and partially observable driving scenarios.

Resources

Paper

Tags