用三维几何与未来场景预测提升自动驾驶决策安全与效率
GeoWorldAD: Geometry World Action Model for Autonomous Driving
- 基于自车对齐的3D空间建模，显式融入几何约束
- 通过隐式未来几何令牌预测短时场景演化，减少过度保守决策
- 适用于需要高安全性与高效能的自动驾驶系统设计
自动驾驶需在动态三维环境中做出安全且高效的规划决策。尽管近期视觉/视频-动作模型可直接从视觉观测学习策略，并随视觉变压器和大规模训练数据的进步而扩展，但往往缺乏明确的几何定位和未来感知的空间引导，限制了其在避障与行驶进展之间的平衡能力。本文提出GeoWorldAD，一种将轨迹规划锚定于自车对齐3D空间并以潜在未来几何标记预测短时场景演化的几何世界动作模型。当前几何提供安全规划的关键空间约束，而未来几何揭示周围代理与自车中心自由空间的演化趋势，从而在不牺牲安全的前提下减少过度保守决策。为高效利用这些几何线索，GeoWorldAD通过迭代轨迹优化逐步聚合多尺度当前几何与潜在未来几何。在NAVSIM v1和v2上的实验表明，该模型达到业界领先性能，验证了显式三维几何定位与未来几何世界建模在安全高效自动驾驶中的有效性。
原文摘要 · Abstract (English)
Autonomous driving requires both safe and efficient planning decisions in dynamic 3D environments. Although recent Vision/Video-Action models learn policies directly from visual observations and scale well with advances in vision transformers and large-scale training data, they often lack explicit geometric grounding and future-aware spatial guidance, limiting their ability to balance collision avoidance and driving progress. In this work, we propose GeoWorldAD, a geometry world action model that grounds trajectory planning in ego-aligned 3D space and anticipates short-horizon scene evolution with latent future geometry tokens. Present geometry provides essential spatial constraints for safe planning, while future geometry reveals how surrounding agents and ego-centric free space may evolve, reducing overly conservative decisions without sacrificing safety. To efficiently exploit these geometric cues, GeoWorldAD progressively aggregates multi-scale present geometry and latent future geometry through iterative trajectory refinement. Experiments on NAVSIM v1 and v2 demonstrate state-of-the-art performance, highlighting the effectiveness of explicit 3D geometry grounding and future geometry world modeling for safe and efficient autonomous driving.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。