GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving

• URL: http://arxiv.org/abs/2606.16274v1
• Date: Mon, 15 Jun 2026 06:26:46 GMT
• Title: GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving
• Abstract summary: 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.
• Score: 56.50032398571235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end autonomous driving has made significant progress by unifying perception, prediction, and planning within a single learning framework, achieving strong performance in short-horizon decision making. However, most existing E2E-AD methods remain confined to short-horizon planning and lack the ability to model long-term temporal dependencies, which severely limits their generalization and security in complex and highly interactive driving scenarios. In this work, we propose GraphWorld, an E2E-AD framework that explicitly enhances long-horizon planning through latent world modeling. We introduce an Ego-Centric Interaction Graph, which adaptively models critical neighboring agents based on spatial proximity, and propagates relational context to planning queries via cross-node cross-attention. We present a World-State-Conditioned Planning that learns ego-centric latent world representations by modeling interactions between an ego vehicle and surrounding agents. 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. Extensive experiments on Bench2Drive, NAVSIMv1/2, and nuScenes demonstrate that GraphWorld significantly reduces collision rates and improves long-horizon planning performance, validating its effectiveness in complex driving environments.

Related papers

• Long-Horizon Consistent and Interaction-Aware World Models for Multi-Style End-to-End Driving [10.506773245217945]
  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.
  arXiv  Detail & Related papers  (2026-09-03T00:00:39Z)
• X-Foresight: A Joint Vision-Action Causal Forecasting Network via Predictive World Modeling [47.54820149491433]
  We introduce X-Foresight, a predictive world model integrated directly into the Vision-Language-Action architecture.<n>By predicting semantically distant chunks rather than adjacent frames, X-Foresight escapes trivial extrapolation.<n> Comprehensive experiments demonstrate that X-Foresight significantly outperforms VLA baselines in planning performance.
  arXiv  Detail & Related papers  (2026-05-24T06:37:04Z)
• World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks [62.389116510844445]
  We introduce emphWorld-Ego Modeling, a new conceptual paradigm that decomposes future evolution into world and ego components.<n>We instantiate this paradigm as the World-Ego Model (WEM), a unified embodied world model that couples an implicit separate world-ego planner with a cascade-parallel mixture-of-experts (CP-MoE) diffusion generator.
  arXiv  Detail & Related papers  (2026-05-19T15:10:27Z)
• The DAWN of World-Action Interactive Models [30.798493550954703]
  World prediction and action generation is treated as either isolated parallel branches or rigid predict-then-plan pipelines.<n>We instantiate this perspective with textbfDAWN (textbfDenoising textbfActions and textbfWorld itextbfNteractive model), a simple yet strong latent generative baseline.<n>DAWN achieves strong planning performance and favorable safety-related results across multiple autonomous driving benchmarks.
  arXiv  Detail & Related papers  (2026-05-12T05:30:00Z)
• DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving [13.924469176668941]
  We propose a driving world model that performs parallel prediction of latent semantic features for consecutive future frames.<n>We also introduce an efficient and adaptive text reasoning mechanism that utilizes additional social knowledge and reasoning capabilities.<n>We present a novel, efficient, and effective approach that achieves state-of-the-art (SOTA) results on the closed-loop Bench2drive benchmark.
  arXiv  Detail & Related papers  (2026-05-11T13:36:51Z)
• Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving [52.04950569530877]
  We present Uni-World VLA, a unified vision-language-action model that tightly interleaves future frame prediction and trajectory planning.<n>Our approach achieves competitive closed-loop planning performance while producing high-fidelity future frame predictions.
  arXiv  Detail & Related papers  (2026-03-28T14:39:51Z)
• World Model-Based Learning for Long-Term Age of Information Minimization in Vehicular Networks [53.98633183204453]
  In this paper, a novel world model-based learning framework is proposed to minimize packet-completeness-aware age of information (CAoI) in a vehicular network.<n>A world model framework is proposed to jointly learn a dynamic model of the mmWave V2X environment and use it to imagine trajectories for learning how to perform link scheduling.<n>In particular, the long-term policy is learned in differentiable imagined trajectories instead of environment interactions.
  arXiv  Detail & Related papers  (2025-05-03T06:23:18Z)
• 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)
• PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Driving [57.89801036693292]
  PPAD (Iterative Interaction of Prediction and Planning Autonomous Driving) considers the timestep-wise interaction to better integrate prediction and planning. We design ego-to-agent, ego-to-map, and ego-to-BEV interaction mechanisms with hierarchical dynamic key objects attention to better model the interactions.
  arXiv  Detail & Related papers  (2023-11-14T11:53:24Z)

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.