Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Survey of Generative AI for Intelligent Transportation Systems: Road Transportation Perspective

Huan Yan, Yong Li

TL;DR

This review systematically investigates the relevant literature on generative AI techniques in addressing key issues in different types of tasks in ITS tailored specifically for road transportation, and systematically illustrates how generative AI techniques addresses key issues in these four different types of tasks.

Abstract

Intelligent transportation systems are vital for modern traffic management and optimization, greatly improving traffic efficiency and safety. With the rapid development of generative artificial intelligence (Generative AI) technologies in areas like image generation and natural language processing, generative AI has also played a crucial role in addressing key issues in intelligent transportation systems (ITS), such as data sparsity, difficulty in observing abnormal scenarios, and in modeling data uncertainty. In this review, we systematically investigate the relevant literature on generative AI techniques in addressing key issues in different types of tasks in ITS tailored specifically for road transportation. First, we introduce the principles of different generative AI techniques. Then, we classify tasks in ITS into four types: traffic perception, traffic prediction, traffic simulation, and traffic decision-making. We systematically illustrate how generative AI techniques addresses key issues in these four different types of tasks. Finally, we summarize the challenges faced in applying generative AI to intelligent transportation systems, and discuss future research directions based on different application scenarios.

A Survey of Generative AI for Intelligent Transportation Systems: Road Transportation Perspective

TL;DR

This review systematically investigates the relevant literature on generative AI techniques in addressing key issues in different types of tasks in ITS tailored specifically for road transportation, and systematically illustrates how generative AI techniques addresses key issues in these four different types of tasks.

Abstract

Intelligent transportation systems are vital for modern traffic management and optimization, greatly improving traffic efficiency and safety. With the rapid development of generative artificial intelligence (Generative AI) technologies in areas like image generation and natural language processing, generative AI has also played a crucial role in addressing key issues in intelligent transportation systems (ITS), such as data sparsity, difficulty in observing abnormal scenarios, and in modeling data uncertainty. In this review, we systematically investigate the relevant literature on generative AI techniques in addressing key issues in different types of tasks in ITS tailored specifically for road transportation. First, we introduce the principles of different generative AI techniques. Then, we classify tasks in ITS into four types: traffic perception, traffic prediction, traffic simulation, and traffic decision-making. We systematically illustrate how generative AI techniques addresses key issues in these four different types of tasks. Finally, we summarize the challenges faced in applying generative AI to intelligent transportation systems, and discuss future research directions based on different application scenarios.
Paper Structure (42 sections, 7 figures, 6 tables)

This paper contains 42 sections, 7 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Fundamental Generative AI Technologies
  3. Key Technologies
  4. VAE
  5. GAN
  6. Normalizing Flows
  7. Energy-Based Models
  8. Diffusion Probabilistic Model
  9. Generative Models from Physical Process
  10. Generative Pre-trained Transformer
  11. Comparative Analysis of Generative AI Techniques
  12. Important Generation Tasks
  13. Text Generation
  14. Image Generation
  15. Video Generation
  16. ...and 27 more sections

Figures (7)

  • Figure 1: An overview of generative AI in intelligent transportation systems.
  • Figure 2: The history of generative AI techniques.
  • Figure 3: The relation between different generation tasks in ITS.
  • Figure 4: The relation between different topics in generative AI for traffic perception research.
  • Figure 5: The relation between different topics in generative AI for traffic prediction research.
  • ...and 2 more figures