arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.09798cs.ROcs.CV
收藏

基于3D特征场的视觉与语言导航Sim-to-Real迁移

Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation

Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Institute of Intelligent Computing Technology, CAS(中国科学院智能计算技术研究所);Peng Cheng Laboratory(鹏城实验室)

Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, Shuqiang Jiang

AI总结:

提出基于3D特征场的sim-to-real迁移方法,通过语义可通行地图和新视角预测赋予单目机器人全景感知能力,将高性能全景VLN模型迁移至单目机器人,显著提升真实世界导航性能。

摘要:

视觉与语言导航(VLN)使智能体能够遵循自然语言指令在3D环境中导航至远程位置。在该领域,智能体通常在导航模拟器中进行训练和评估,缺乏有效的sim-to-real迁移方法。仅配备单目相机的VLN智能体表现出极其有限的性能,而使用全景观测训练的主流VLN模型性能更好,但难以部署在大多数单目机器人上。针对此情况,我们提出一种sim-to-real迁移方法,赋予单目机器人全景可通行性感知和全景语义理解能力,从而将高性能全景VLN模型平滑迁移至普通单目机器人。本工作提出语义可通行地图以预测以智能体为中心的可导航路径点,并通过3D特征场预测这些可导航路径点的新视角表示。这些方法拓宽了单目机器人有限的视野,并显著提升了真实世界中的导航性能。我们的VLN系统在模拟环境的R2R-CE和RxR-CE基准上超越了以往的SOTA单目VLN方法,并在真实世界环境中得到验证,为真实世界VLN提供了实用且高性能的解决方案。

英文摘要:

Vision-and-language navigation (VLN) enables the agent to navigate to a remote location in 3D environments following the natural language instruction. In this field, the agent is usually trained and evaluated in the navigation simulators, lacking effective approaches for sim-to-real transfer. The VLN agents with only a monocular camera exhibit extremely limited performance, while the mainstream VLN models trained with panoramic observation, perform better but are difficult to deploy on most monocular robots. For this case, we propose a sim-to-real transfer approach to endow the monocular robots with panoramic traversability perception and panoramic semantic understanding, thus smoothly transferring the high-performance panoramic VLN models to the common monocular robots. In this work, the semantic traversable map is proposed to predict agent-centric navigable waypoints, and the novel view representations of these navigable waypoints are predicted through the 3D feature fields. These methods broaden the limited field of view of the monocular robots and significantly improve navigation performance in the real world. Our VLN system outperforms previous SOTA monocular VLN methods in R2R-CE and RxR-CE benchmarks within the simulation environments and is also validated in real-world environments, providing a practical and high-performance solution for real-world VLN.

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。

↑