arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.14281cs.CV
收藏

地标感知的视觉导航数据集

A Landmark-Aware Visual Navigation Dataset

Rutgers University(罗格斯大学);Stony Brook University(石溪大学);Georgia State University(佐治亚州立大学)

Faith Johnson, Bryan Bo Cao, Kristin Dana, Shubham Jain, Ashwin Ashok

AI总结:

提出LAVN数据集,包含RGBD观测和人类点-点击对,用于有监督学习以人为中心的探索策略和地图构建,覆盖室内外场景。

摘要:

由专家示范学习到的地图表示已显示出有前景的研究价值。然而,视觉导航领域仍面临挑战,因为缺乏能够支持高效、有监督的环境表示学习的真实世界人类导航数据集。我们提出了一个地标感知的视觉导航(LAVN)数据集,以支持以人为中心的探索策略和地图构建的有监督学习。我们收集RGBD观测和人类点-点击对,由人类标注者在虚拟和真实世界环境中进行探索,目标是实现空间的全覆盖探索。人类标注者还沿着每条轨迹提供不同的地标示例,我们直觉认为这将简化地图或图构建以及定位的任务。这些人类点-点击在环境探索学习过程中作为航路点预测的直接监督。我们的数据集涵盖了广泛的场景,包括室内环境中的房间以及室外的步行道。我们在https://huggingface.co/datasets/visnavdataset/lavn(DOI: 10.57967/hf/2386)发布了我们的数据集,并附有详细文档,以及长期保存的计划。

英文摘要:

Map representations learned by expert demonstrations have shown promising research value. However, the field of visual navigation still faces challenges due to the lack of real-world human-navigation datasets that can support efficient, supervised, representation learning of environments. We present a Landmark-Aware Visual Navigation (LAVN) dataset to allow for supervised learning of human-centric exploration policies and map building. We collect RGBD observation and human point-click pairs as a human annotator explores virtual and real-world environments with the goal of full coverage exploration of the space. The human annotators also provide distinct landmark examples along each trajectory, which we intuit will simplify the task of map or graph building and localization. These human point-clicks serve as direct supervision for waypoint prediction when learning to explore in environments. Our dataset covers a wide spectrum of scenes, including rooms in indoor environments, as well as walkways outdoors. We release our dataset with detailed documentation at https://huggingface.co/datasets/visnavdataset/lavn (DOI: 10.57967/hf/2386) and a plan for long-term preservation.

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。

↑