X-Tokenizer creates semantic action tokens via asymmetric residual quantization and contrastive pretraining on large trajectory data, outperforming prior methods like FAST on robotic tasks.
Unleashing the potential of diffusion models for end-to-end autonomous driving
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
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 and robustness 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.
citation-role summary
background 2
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
Derail adversarial perturbations hijack the scoring head in generative E2E driving planners, flipping safe to unsafe trajectory selection with 39-80% score drops and up to 50% collision rates.
D³-MoE disentangles style and physical axes with diffusion and self-supervised MoE experts to produce style-controllable trajectories, reporting SOTA 88.2 PDMS on NAVSIM.
ReflectDrive-2 combines masked discrete diffusion with RL-aligned self-editing to generate and refine driving trajectories, reaching 91.0 PDMS on NAVSIM camera-only and 94.8 in best-of-6.
R²LPL converts recoverable policy mistakes identified in closed-loop rollouts into corrective supervised targets for lifelong policy improvement, reaching SOTA on nuPlan benchmarks with few cycles.
CRAFT is an on-policy RL fine-tuning framework that decomposes closed-loop policy gradients into a group-normalized counterfactual proxy plus residual correction from interaction events, achieving top closed-loop performance on Bench2Drive across multiple driving architectures.
RAD-2 uses a diffusion generator and RL discriminator to cut collision rates by 56% in closed-loop autonomous driving planning.
citing papers explorer
-
X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining
X-Tokenizer creates semantic action tokens via asymmetric residual quantization and contrastive pretraining on large trajectory data, outperforming prior methods like FAST on robotic tasks.
-
Off the Rails: Hijacking the Scoring Head in Generative End-to-End Driving Planners with Safety-Violating Adversarial Perturbations
Derail adversarial perturbations hijack the scoring head in generative E2E driving planners, flipping safe to unsafe trajectory selection with 39-80% score drops and up to 50% collision rates.
-
D$^3$-MoE:Dual Disentangled Diffusion Mixture-of-Experts for Style-Controllable End-to-End Autonomous Driving
D³-MoE disentangles style and physical axes with diffusion and self-supervised MoE experts to produce style-controllable trajectories, reporting SOTA 88.2 PDMS on NAVSIM.
-
ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
ReflectDrive-2 combines masked discrete diffusion with RL-aligned self-editing to generate and refine driving trajectories, reaching 91.0 PDMS on NAVSIM camera-only and 94.8 in best-of-6.
-
Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving
R²LPL converts recoverable policy mistakes identified in closed-loop rollouts into corrective supervised targets for lifelong policy improvement, reaching SOTA on nuPlan benchmarks with few cycles.
-
CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
CRAFT is an on-policy RL fine-tuning framework that decomposes closed-loop policy gradients into a group-normalized counterfactual proxy plus residual correction from interaction events, achieving top closed-loop performance on Bench2Drive across multiple driving architectures.
-
RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
RAD-2 uses a diffusion generator and RL discriminator to cut collision rates by 56% in closed-loop autonomous driving planning.