arXiv：cs.AI· Ke Gui, Chenghao Shi, Ziyue Wang, Longwen Chen, Xieyuanli Chen, Huimin Lu·· 16 小时前
G²WAM：面向高效几何锚定图像目标导航的世界动作模型
G$^2$WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation
AI 导读
研究者提出几何锚定世界动作模型 G²WAM，用于图像目标导航。它通过场景坐标定位模块将当前、目标与历史帧锚定在统一参考系，无需显式 3D 重建，并在潜空间中联合预测未来状态与动作，省去 CEM 式规划。在四个轨迹预测基准上平均 ATE 和 RPE 分别降低 40.1% 和 35.2%，闭环导航成功率从 54.0% 提升至 63.0%，SPL 从 36.4% 提升至 59.2%。
正文
Abstract:World models capture environment dynamics and support counterfactual reasoning for planning. In image-goal navigation, where the target often lies beyond the current field of view, the agent must not only model environmental dynamics but also maintain a persistent spatial memory of the scene. Existing approaches either introduce spatial context by fine-tuning pretrained models on the target task, which underexploits their spatial priors, or rely on external 3D reconstruction, which is computationally expensive for real-world deployment. In this paper, we propose the Geometry Grounded World Action Model (G$^2$WAM) for image-goal navigation. G$^2$WAM encodes spatial cues through a learned scene-coordinate localization module that anchors the current, goal, and history frames in a common reference frame, yielding a stable and consistent spatial context that enables efficient navigation without explicit 3D reconstruction. Following the world-action-model paradigm, G$^2$WAM jointly predicts future states and actions, eliminating the need for costly cross-entropy method (CEM) style planning. In addition, G$^2$WAM operates entirely in latent space, avoiding the computational burden of pixel-level reconstruction and substantially reducing inference cost. Across four trajectory prediction benchmarks, G$^2$WAM reduces average ATE and RPE by 40.1% and 35.2%, respectively. In closed-loop navigation experiments, it improves the success rate from 54.0% to 63.0% and the success weighted by path length (SPL) from 36.4% to 59.2%, while maintaining high efficiency.
| Comments: | 20 pages, including references and appendix |
| Subjects: | Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2610.16558 [cs.AI] |
| (or arXiv:2610.16558v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16558 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ke Gui [view email]
[v1]
Mon, 12 Oct 2026 10:36:40 UTC (953 KB)
来源：arXiv：cs.AI · arxiv.org