HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving

• URL: http://arxiv.org/abs/2604.03581v1
• Date: Sat, 04 Apr 2026 04:12:47 GMT
• Title: HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving
• Abstract summary: We propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy.<n>We show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM.
• Score: 51.268878540511054
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end planning has emerged as a dominant paradigm for autonomous driving, where recent models often adopt a scoring-selection framework to choose trajectories from a large set of candidates, with diffusion-based decoding showing strong promise. However, directly selecting from the entire candidate space remains difficult to optimize, and Gaussian perturbations used in diffusion often introduce unrealistic trajectories that complicate the denoising process. In addition, for training these models, reinforcement learning (RL) has shown promise, but existing end-to-end RL approaches typically rely on a single coupled reward without structured signals, limiting optimization effectiveness. To address these challenges, we propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy that decomposes planning into a coarse-to-fine process. To improve trajectory generation, we introduce Structure-Preserved Trajectory Expansion, which produces realistic candidates while maintaining kinematic structure. For policy learning, we develop Metric-Decoupled Policy Optimization (MDPO) to enable structured RL optimization across multiple driving objectives. Extensive experiments show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM, outperforming prior arts by a huge margin: +2.3 EPDMS on NAVSIM and +4.9 Route Completion on HUGSIM.

Related papers

• Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions [1.3299507495084417]
  This paper presents a learning-augmented trajectory planning framework for cooperative unmanned aerial vehicle (UAV) and unmanned ground vehicle (UGV) handover missions.<n>We propose a neural surrogate planner utilizing decoupled encoder-decoder long short-term memory (LSTM) networks to generate coordinated handover trajectory predictions.<n> Benchmark evaluations demonstrate that the learning-augmented planning framework achieves more than a threefold speedup and 100% optimization success rate.
  arXiv  Detail & Related papers  (2026-05-19T09:07:59Z)
• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models [55.01951088768769]
  DiffusionOPD is a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD)<n>We show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance.
  arXiv  Detail & Related papers  (2026-05-14T16:49:09Z)
• TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment [52.570581883709345]
  We propose Trajectory Matching Policy Balance Optimization (TMPO), which replaces reward with human-level reward distribution matching.<n>TMPO improves generative diversity over state-of-the-art methods by 9.1%, and achieves competitive performance in all downstream and efficiency metrics.<n>To further reduce multi-trajectory training time on large-scale flow- prefixes, TMPO incorporates Dynamic Tree Sampling models, where trajectories share denoising and branch at dynamically scheduled steps.
  arXiv  Detail & Related papers  (2026-05-09T04:41:02Z)
• Joint Optimization of Trajectory Control, Resource Allocation, and Task Offloading for Multi-UAV-Assisted IoV [42.14161392443562]
  This paper investigates a multi-Unmanned Aerial Vehicle (UAV) joint base station-assisted Internet of Vehicles (IoV) task offloading system.<n>To minimize system delay, a novel multi-agent reinforcement learning paradigm is proposed.
  arXiv  Detail & Related papers  (2026-05-06T02:59:18Z)
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving [7.691237575352413]
  PaIR-Drive is a general framework for collaborative and Reinforcement learning in end-to-end autonomous driving.<n>During training, PaIR-Drive separates IL and RL into two parallel branches with conflict-free training objectives.<n>PaIR-Drive consistently outperforms existing RL fine-tuning methods, and could even correct human experts' suboptimal behaviors.
  arXiv  Detail & Related papers  (2026-03-14T08:53:47Z)
• Drive As You Like: Strategy-Level Motion Planning Based on A Multi-Head Diffusion Model [7.3078271605135114]
  We propose a diffusion-based multi-head trajectory planner(M-diffusion planner)<n>During the early training stage, all output heads share weights to learn to generate high-quality trajectories.<n>We incorporate a large language model (LLM) to guide strategy selection, enabling dynamic, instruction-aware planning.
  arXiv  Detail & Related papers  (2025-08-23T08:33:11Z)
• Generalized Trajectory Scoring for End-to-end Multimodal Planning [42.38746285135693]
  Generalized Trajectory Scoring (GTRS) is a unified framework for end-to-end multi-modal planning.<n>GTRS consists of three complementary innovations: (1) a diffusion-based trajectory generator that produces diverse fine-grained proposals; (2) a vocabulary generalization technique that trains a scorer on super-dense trajectory sets with dropout regularization; and (3) a sensor augmentation strategy that enhances out-of-domain generalization.<n>As the winning solution of the Navsim v2 Challenge, GTRS demonstrates superior performance even with sub-optimal sensor inputs.
  arXiv  Detail & Related papers  (2025-06-07T05:06:05Z)
• Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models [79.2162092822111]
  We systematically evaluate reinforcement learning (RL) and control-based methods on a suite of navigation tasks.<n>We employ a latent dynamics model using the Joint Embedding Predictive Architecture (JEPA) and employ it for planning.<n>Our results show that model-free RL benefits most from large amounts of high-quality data, whereas model-based planning generalizes better to unseen layouts.
  arXiv  Detail & Related papers  (2025-02-20T18:39:41Z)
• Predictive Planner for Autonomous Driving with Consistency Models [5.966385886363771]
  Trajectory prediction and planning are essential for autonomous vehicles to navigate safely and efficiently in dynamic environments.<n>Recent diffusion-based generative models have shown promise in multi-agent trajectory generation, but their slow sampling is less suitable for high-frequency planning tasks.<n>We leverage the consistency model to build a predictive planner that samples from a joint distribution of ego and surrounding agents, conditioned on the ego vehicle's navigational goal.
  arXiv  Detail & Related papers  (2025-02-12T00:26:01Z)
• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving.<n>Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.<n>Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment [58.049113055986375]
  We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy.<n>The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms.<n>We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
  arXiv  Detail & Related papers  (2024-06-11T01:20:53Z)
• Reinforcement Learning to Optimize the Logistics Distribution Routes of Unmanned Aerial Vehicle [0.0]
  This paper proposes an improved method to achieve path planning for UAVs in complex surroundings: multiple no-fly zones. The results show the feasibility and efficiency of the model applying in this kind of complicated situation.
  arXiv  Detail & Related papers  (2020-04-21T09:42:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.