Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving

2026-02-26

AI Summary

This work addresses the limited empirical validation of diffusion models in end-to-end autonomous driving under large-scale real-world conditions. For the first time, it systematically evaluates and optimizes diffusion-based planners in actual urban road environments, establishing key design principles concerning trajectory representation, loss formulation, and data augmentation. To further enhance safety, the authors introduce a reinforcement learning-based post-training strategy. The resulting Hyper Diffusion Planner is evaluated over 200 kilometers of real-world driving across six diverse urban scenarios, demonstrating a tenfold improvement in planning performance over baseline methods. These results substantiate the feasibility and superiority of diffusion models for end-to-end autonomous driving in complex, real-world settings.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Diffusion Models for Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving autonomous driving tasks. However, their applications and evaluations in autonomous driving remain limited to simulation-based or laboratory settings. The full strength of diffusion models for large-scale, complex real-world settings, such as End-to-End Autonomous Driving (E2E AD), remains underexplored. In this study, we conducted a systematic and large-scale investigation to unleash the potential of the diffusion models as planners for E2E AD, based on a tremendous amount of real-vehicle data and road testing. Through comprehensive and carefully controlled studies, we identify key insights into the diffusion loss space, trajectory representation, and data scaling that significantly impact E2E planning performance. Moreover, we also provide an effective reinforcement learning post-training strategy to further enhance the safety of the learned planner. The resulting diffusion-based learning framework, Hyper Diffusion Planner} (HDP), is deployed on a real-vehicle platform and evaluated across 6 urban driving scenarios and 200 km of real-world testing, achieving a notable 10x performance improvement over the base model. Our work demonstrates that diffusion models, when properly designed and trained, can serve as effective and scalable E2E AD planners for complex, real-world autonomous driving tasks.

Problem

• Diffusion Models
• End-to-End Autonomous Driving
• Real-World Deployment
• Autonomous Driving Planning
• Scalability

Innovation

• diffusion models
• end-to-end autonomous driving
• trajectory planning
• real-world deployment
• reinforcement learning post-training