GeoWorldAD: Geometry World Action Model for Autonomous Driving
2026-07-20 • Robotics
Robotics
AI summaryⓘ
The authors propose GeoWorldAD, a new model for self-driving cars that uses 3D space information to plan safe and efficient driving paths. Unlike earlier models that relied mainly on visual data, GeoWorldAD uses current and predicted future 3D geometry to better understand the environment and anticipate how it will change shortly. This helps the car avoid collisions without being overly cautious. Their tests show that grounding decisions in 3D geometry and considering future changes improves autonomous driving performance.
autonomous drivingtrajectory planning3D geometryego-aligned spacefuture geometry tokenscollision avoidancevision transformersscene evolutiontrajectory refinementNAVSIM
Authors
Songyan Zhang, Jinyuan Tian, Hanbing Li, Daqi Liu, Hao Chen, Wenhui Huang, Fang Li, Guang Chen, Hangjun Ye, Long Chen, Kuiyuan Yang, Chen Lv
Abstract
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.