A Survey on Future Physical World Generation for Autonomous Driving

MMAsia 25 2025 50.9 survey, application

TLDR

A survey on generative models and simulation-oriented world models for autonomous driving, covering evaluation and deployment challenges.

Reasoning

The paper provides a comprehensive overview of future physical world generation techniques for autonomous driving, but as a survey it lacks original experiments or real-world validation. Its strengths lie in organizing existing work and identifying gaps, while weaknesses include no empirical contributions.

Read-first score

Read-first score 50.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 48.

Recency 6%

86.7

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

Methodology quality 18%

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

Topical relevance 29%

68.6

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

Citation impact 18%

45.1

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.45101548

Reproducibility 18%

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

Citation velocity 12%

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

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 415.

Keyword Scores

world model

generative world model

world simulator

video world model

world dynamics prediction

interactive world model

model-based reinforcement learning world model

Deep Analysis

Innovations

Comprehensive survey of future physical world generation for autonomous driving
Taxonomy of generative models and simulation-oriented world models
Analysis of evaluation needs and deployment challenges for driving scenarios

Methodology

The paper conducts a systematic literature review, categorizing existing approaches into generative models and simulation-oriented world models, and discusses evaluation metrics and deployment challenges for autonomous driving scenarios.

Key Results

The survey provides a structured overview of current methods, identifies key challenges in evaluation and deployment, and outlines future research directions.

Resources

Paper