arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00759cs.RO
收藏

基于图像的机器人导航场景识别及其免人工标注训练

Image-based scene recognition for robot navigation considering traversable plants and its manual annotation-free training

Toyohashi University of Technology(丰桥技术科学大学)

Shigemichi Matsuzaki, Hiroaki Masuzawa, Jun Miura

摘要:

本文描述了一种方法,估计植物部分覆盖路径和导航通过它们的移动机器人在植物丰富的环境中操作的可通行性。传统的移动机器人依赖于场景识别方法,只考虑环境的几何信息。因此,当路径被柔性植物覆盖时,这些方法不能将路径识别为可穿越的。在本文中,我们提出了一种新的框架,基于图像的场景识别,以实现在这样的植物丰富的环境中的导航。我们的识别模型利用一般对象分类的语义分割分支和遍历性估计分支估计像素遍历性。使用无监督领域自适应方法训练语义分割分支,并且使用在数据采集阶段期间从机器人的遍历经验生成的标签图像训练遍历性估计分支,创造遍历性掩码。因此,整个模型的训练过程无需人工注释。在我们的实验中,我们表明,所提出的识别框架是能够区分可穿越的植物更准确地比传统的语义分割与可穿越的植物和非可穿越的植物类,和现有的基于图像的可穿越性估计方法。我们还进行了一个真实世界的实验,并证实了所提出的识别方法的机器人成功地在植物丰富的环境中导航。

英文摘要:

This paper describes a method of estimating the traversability of plant parts covering a path and navigating through them for mobile robots operating in plant-rich environments. Conventional mobile robots rely on scene recognition methods that consider only the geometric information of the environment. Those methods, therefore, cannot recognize paths as traversable when they are covered by flexible plants. In this paper, we present a novel framework of image-based scene recognition to realize navigation in such plant-rich environments. Our recognition model exploits a semantic segmentation branch for general object classification and a traversability estimation branch for estimating pixel-wise traversability. The semantic segmentation branch is trained using an unsupervised domain adaptation method and the traversability estimation branch is trained with label images generated from the robot's traversal experience during the data acquisition phase, coined traversability masks. The training procedure of the entire model is, therefore, free from manual annotation. In our experiment, we show that the proposed recognition framework is capable of distinguishing traversable plants more accurately than a conventional semantic segmentation with traversable plant and non-traversable plant classes, and an existing image-based traversability estimation method. We also conducted a real-world experiment and confirmed that the robot with the proposed recognition method successfully navigated in plant-rich environments.

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。

↑