arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.18477cs.RO
收藏

迈向野外的长期机器人技术

Towards Long-term Robotics in the Wild

School of Electrical Engineering and Robotics, Queensland University of Technology (QUT)(昆士兰科技大学电气工程与机器人学院);CSIRO(联邦科学与工业研究组织)

Stephen Hausler, Ethan Griffiths, Milad Ramezani, Peyman Moghadam

AI总结:

本文指出自然环境机器人数据集稀缺,提出 WildPlaces 和 WildScenes 基准提供多模态数据,并验证其在地点识别和语义分割等任务中的实用性。

摘要:

本文强调了大规模数据集对提升野外机器人(尤其是自然环境)能力的重要性。尽管城市和郊区数据集众多,但针对自然环境的很少。我们最近的基准 WildPlaces 和 WildScenes 通过在森林环境中提供同步的图像、激光雷达、语义及精确的 6-DoF 位姿信息来填补此空白。我们突出了该数据集的多模态特性,并展示其在地点识别及 2D 和 3D 语义分割等下游任务中的实用性。

英文摘要:

In this paper, we emphasise the critical importance of large-scale datasets for advancing field robotics capabilities, particularly in natural environments. While numerous datasets exist for urban and suburban settings, those tailored to natural environments are scarce. Our recent benchmarks WildPlaces and WildScenes address this gap by providing synchronised image, lidar, semantic and accurate 6-DoF pose information in forest-type environments. We highlight the multi-modal nature of this dataset and discuss and demonstrate its utility in various downstream tasks, such as place recognition and 2D and 3D semantic segmentation tasks.

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。

↑