Long-Horizon Consistent and Interaction-Aware World Models for Multi-Style End-to-End Driving

• URL: http://arxiv.org/abs/2609.03225v1
• Date: Thu, 03 Sep 2026 00:00:39 GMT
• Title: Long-Horizon Consistent and Interaction-Aware World Models for Multi-Style End-to-End Driving
• Abstract summary: StyleDrive is a world-model-based learning framework that jointly enforces long-horizon consistency, explicitly disentangles interactive traffic states, and supports multi-style policy optimization.<n>We evaluate StyleDrive on the Bench2Drive closed-loop driving benchmark, achieving a driving score of 88.44 (+17.08) over the previous best world model-based method.
• Score: 10.506773245217945
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end autonomous driving has increasingly adopted world model-based reinforcement learning frameworks to improve learning efficiency through \textit{imagined rollouts}. However, existing world models suffer from three key limitations: temporal inconsistency in long-horizon imagined rollouts, inadequate modeling of ego-environment interactions, and limited adaptability to diverse driving styles. To address these challenges, we propose \textit{StyleDrive}, a world-model-based learning framework that jointly enforces long-horizon consistency, explicitly disentangles interactive traffic states, and supports multi-style policy optimization within a unified learning paradigm. First, we introduce a temporal consistency regularization that integrates historical latent states through gated cross-attention, stabilizing long-horizon imagined rollouts and mitigating error accumulation. Second, we design an explicit state disentanglement module that separates ego-relevant from ego-irrelevant interactive states, enabling more interpretable and efficient decision-making in complex traffic scenarios. Third, we enable multi-style driving behaviors through Group Relative Policy Optimization, which replaces per-step reward optimization with trajectory-wise relative advantages, reducing reward variance and supporting diverse driving styles without retraining. We evaluate StyleDrive on the Bench2Drive closed-loop driving benchmark, achieving a driving score of 88.44 (+17.08 over the previous best world model-based method) and a success rate of 66.82 (+16.58). Furthermore, we deploy StyleDrive on a real automated guided vehicle platform and demonstrate promising sim-to-real transfer capability in dynamic driving scenarios.

Related papers

• A Collaborative Multi-Modality Interaction for VLA-based End-to-End Autonomous Driving [96.81243316566764]
  Vision-Language-Action (VLA) models have emerged as a powerful paradigm for end-to-end autonomous driving.<n>We propose a robust VLA-based end-to-end autonomous driving system that combines multi-modality interaction with multi-trajectory planning and optimization.
  arXiv  Detail & Related papers  (2026-08-21T09:06:16Z)
• GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving [56.50032398571235]
  GraphWorld is an E2E-AD framework that explicitly enhances long-horizon planning through latent world modeling.<n>We present a World-State-Conditioned Planning that learns ego-centric latent world representations by modeling interactions between an ego vehicle and surrounding agents.<n>This latent world state captures key interaction dynamics and safety-relevant semantics, and serves as a conditioning signal to guide long-horizon, safety-aware trajectory planning.
  arXiv  Detail & Related papers  (2026-06-15T06:26:46Z)
• DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving [67.83404465171257]
  DynFlowDrive is a latent world model that models the transition of world states under different driving actions.<n>It learns a velocity field that describes how the scene state changes under different driving actions.<n>Building upon this, we introduce a stability-aware multi-mode trajectory selection strategy.
  arXiv  Detail & Related papers  (2026-03-20T06:19:31Z)
• FAR-Drive: Frame-AutoRegressive Video Generation in Closed-Loop Autonomous Driving [11.275815014211046]
  Building a learning-based closed-loop simulator for autonomous driving poses three major challenges.<n>Long-horizon temporal and cross-view consistency, mitigating autoregressive degradation under iterative self-conditioning, and satisfying low-latency inference constraints.<n>We propose FAR-Drive, a frame-level autoregressive video generation framework for autonomous driving.
  arXiv  Detail & Related papers  (2026-03-16T07:40:13Z)
• InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation [53.47253633654885]
  InstaDrive is a novel framework that enhances driving video realism through two key advancements.<n>By incorporating these instance-aware mechanisms, InstaDrive achieves state-of-the-art video generation quality.<n>Our project page is https://shanpoyang654.io/InstaDrive/page.html.
  arXiv  Detail & Related papers  (2026-02-03T08:22:13Z)
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving [49.07731497951963]
  ReCogDrive is a novel Reinforced Cognitive framework for end-to-end autonomous driving.<n>We introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers.<n>We then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner.
  arXiv  Detail & Related papers  (2025-06-09T03:14:04Z)
• From Imitation to Exploration: End-to-end Autonomous Driving based on World Model [24.578178308010912]
  RAMBLE is an end-to-end world model-based RL method for driving decision-making.<n>It can handle complex and dynamic traffic scenarios.<n>It achieves state-of-the-art performance in route completion rate on the CARLA Leaderboard 1.0 and completes all 38 scenarios on the CARLA Leaderboard 2.0.
  arXiv  Detail & Related papers  (2024-10-03T06:45:59Z)
• 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)
• Parameterized Decision-making with Multi-modal Perception for Autonomous Driving [12.21578713219778]
  We propose a parameterized decision-making framework with multi-modal perception based on deep reinforcement learning, called AUTO. A hybrid reward function takes into account aspects of safety, traffic efficiency, passenger comfort, and impact to guide the framework to generate optimal actions.
  arXiv  Detail & Related papers  (2023-12-19T08:27:02Z)
• Isolating and Leveraging Controllable and Noncontrollable Visual Dynamics in World Models [65.97707691164558]
  We present Iso-Dream, which improves the Dream-to-Control framework in two aspects. First, by optimizing inverse dynamics, we encourage world model to learn controllable and noncontrollable sources. Second, we optimize the behavior of the agent on the decoupled latent imaginations of the world model.
  arXiv  Detail & Related papers  (2022-05-27T08:07:39Z)

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.