arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.16558cs.AIcs.RO
收藏

G²WAM:用于高效且几何基础的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

College of Intelligence Science and Technology, National University of Defense Technology(国防科技大学智能科学学院);School of Future Technology, National University of Defense Technology(国防科技大学未来技术学院)

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

AI总结:

本文提出G²WAM模型,通过场景坐标定位模块生成稳定空间上下文,联合预测未来状态与动作,在四个轨迹预测基准及闭环导航实验中均实现性能提升且推理成本降低。

摘要:

世界模型捕捉环境动态并支持规划所需的反事实推理。在图像目标导航任务中,目标常超出智能体当前视野,因此智能体不仅需建模环境动态,还需维持场景的持久空间记忆。现有方法要么通过在目标任务上微调预训练模型引入空间上下文,这会未充分利用其空间先验;要么依赖外部3D重建,这对实际部署而言计算成本高昂。本文提出用于图像目标导航的几何基础世界动作模型(G²WAM),该模型通过学习到的场景坐标定位模块编码空间线索,该模块将当前帧、目标帧和历史帧锚定到同一参考坐标系,生成稳定一致的空间上下文,无需显式3D重建即可实现高效导航。遵循世界动作模型范式,G²WAM联合预测未来状态与动作,无需采用计算成本高昂的交叉熵方法(CEM)式规划。此外,G²WAM完全在潜在空间中运行,避免了像素级重建的计算负担,大幅降低了推理成本。在四个轨迹预测基准测试中,G²WAM将平均ATE(绝对轨迹误差)和RPE(相对位姿误差)分别降低40.1%和35.2%;在闭环导航实验中,其将成功率从54.0%提升至63.0%,将按路径长度加权的成功率(SPL)从36.4%提升至59.2%,同时保持高计算效率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑