Generative AI for Autonomous Driving: A Review

2025-05-21

AI Summary

This paper systematically reviews the application of generative artificial intelligence (GenAI) in autonomous driving (AD), focusing on four core tasks: static map construction, dynamic scene generation, trajectory prediction, and motion planning. To address the challenges of safety, interpretability, and real-time performance, we propose a novel three-dimensional evaluation framework and corresponding technical solutions. We conduct the first comprehensive assessment of variational autoencoders (VAEs), generative adversarial networks (GANs), invertible neural networks (INNs), generative Transformers, and diffusion models—evaluating their adaptability, performance limits, and potential fusion strategies in AD contexts. The study clarifies inherent trade-offs among accuracy, robustness, and computational efficiency, establishes an engineering-oriented multi-dimensional benchmarking system, synthesizes open datasets and fundamental research questions, and delivers the first GenAI-driven AD technology roadmap. This work provides both theoretical foundations and practical guidance for developing safe, reliable, and deployable GenAI-AD systems.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Generative AI (GenAI) is rapidly advancing the field of Autonomous Driving (AD), extending beyond traditional applications in text, image, and video generation. We explore how generative models can enhance automotive tasks, such as static map creation, dynamic scenario generation, trajectory forecasting, and vehicle motion planning. By examining multiple generative approaches ranging from Variational Autoencoder (VAEs) over Generative Adversarial Networks (GANs) and Invertible Neural Networks (INNs) to Generative Transformers (GTs) and Diffusion Models (DMs), we highlight and compare their capabilities and limitations for AD-specific applications. Additionally, we discuss hybrid methods integrating conventional techniques with generative approaches, and emphasize their improved adaptability and robustness. We also identify relevant datasets and outline open research questions to guide future developments in GenAI. Finally, we discuss three core challenges: safety, interpretability, and realtime capabilities, and present recommendations for image generation, dynamic scenario generation, and planning.

Problem

• Enhancing automotive tasks with generative models
• Comparing generative approaches for autonomous driving
• Addressing safety, interpretability, and realtime challenges

Innovation

• Generative models enhance automotive tasks
• Hybrid methods improve adaptability and robustness
• Address safety, interpretability, and realtime challenges