GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving
2026-06-15 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created GraphWorld, a new system for self-driving cars that plans safer and better routes over longer distances. They designed a special graph to track nearby cars and how they might affect the self-driving car's decisions. This helps the car understand interactions with others and plan ahead more carefully. Tests showed GraphWorld reduces crashes and works well in tricky driving situations.
end-to-end autonomous drivinglong-horizon planningego-centric interaction graphlatent world modelingcross-attentiontrajectory planningmulti-agent interactioncollision reductionsafety-aware planning
Authors
Ziying Song, Caiyan Jia, Lin Liu, Lei Yang, Shengkai Zhang, Feiyang Jia, Fengda Zhao, Peiliang Wu, Shaoqing Xu, Chen Lv, Yadan Luo
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.