具身开发者社区

外观

论文arXiv 2610.1655816 天前

G$^2$WAM：用于高效且几何扎根图像目标导航的 World Action Models ​

针对图像目标导航中的视野外目标与空间记忆需求，G$^2$WAM用场景坐标定位和潜空间动作世界模型，在轨迹预测基准与闭环导航中验证。

AI 整理
  • 本体 SDK 与控制
  • 感知与导航
  • 具身模型

原文链接：G$^2$WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation（arXiv 2610.16558 · 发布日期：2026-10-12）

G$^2$WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation

针对图像目标导航中的视野外目标与空间记忆需求，G$^2$WAM用场景坐标定位和潜空间动作世界模型，在轨迹预测基准与闭环导航中验证。

核心要点 ​

  • 图像目标导航中目标常超出当前视野，智能体需建模动态并保持持久空间记忆。
  • G$^2$WAM学习场景坐标定位，将当前、目标和历史帧锚定到共同参考系。
  • 模型联合预测未来状态和动作，并在潜空间运行，避免显式3D重建和CEM式规划。
  • 在四个轨迹预测基准上降低平均ATE和RPE，并在闭环导航中提升成功率与SPL。

验证范围与局限：验证范围为四个轨迹预测基准和闭环导航实验，摘要未说明是否为真机或仿真。

英文摘要 (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.

作者：Ke Gui, Chenghao Shi, Ziyue Wang, Longwen Chen, Xieyuanli Chen, Huimin Lu

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2610.16558：G$^2$WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation访问 2026-10-21