DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving
Lists
Only you see this
Abstract
Most end-to-end autonomous driving methods rely on imitation learning from single expert demonstrations, often leading to conservative and homogeneous behaviors that limit generalization in complex real-world scenarios. In this work, we propose DIVER, an end-to-end driving framework that integrates reinforcement learning with diffusion-based generation to produce diverse and feasible trajectories. At the core of DIVER lies a reinforced diffusion-based generation mechanism. First, the model conditions on map elements and surrounding agents to generate multiple reference trajectories from a single ground-truth trajectory, alleviating the limitations of imitation learning that arise from relying solely on single expert demonstrations. Second, reinforcement learning is employed to guide the diffusion process, where reward-based supervision enforces safety and diversity constraints on the generated trajectories, thereby enhancing their practicality and generalization capability. Furthermore, to address the limitations of L2-based open-loop metrics in capturing trajectory diversity, we propose a novel Diversity metric to evaluate the diversity of multi-mode predictions.Extensive experiments on the closed-loop NAVSIM and Bench2Drive benchmarks, as well as the open-loop nuScenes dataset, demonstrate that DIVER significantly improves trajectory diversity, effectively addressing the mode collapse problem inherent in imitation learning.
BibTeX
@misc{song2025diver,
author = {Ziying Song and Lin Liu and Hongyu Pan and Bencheng Liao and Mingzhe Guo and Lei Yang and Yongchang Zhang and Shaoqing Xu and Caiyan Jia and Yadan Luo},
title = {{DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving}},
year = {2025},
eprint = {2507.04049},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2507.04049},
}Loading related content...