Deepening the Sense of Touch in Planetary Exploration with Geometric and Topological Deep Learning
Deepening the Sense of Touch in Planetary Exploration with Geometric and Topological Deep Learning
复制标题
DOI：
10.1609/aaai.v35i17.17793
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Yuzhou Chen;Y. Marchetti;Y. Gel
中科院分区：
文献类型：
--
作者：
Yuzhou Chen;Y. Marchetti;Y. Gel
触觉和嵌入式传感是一个新概念，最近出现在火星车和行星探测任务的背景下。各种传感器，如测量压力和直接集成在车轮上的传感器，有可能为探索车辆增加“触觉”。我们研究了深度学习（DL）的实用性，从传统的卷积神经网络（CNN）到新兴的几何和拓扑DL，再到基于实验触觉轮概念的新数据集的行星探索地形分类。该数据集包括来自压力传感器阵列的2D电导率图像，该压力传感器阵列缠绕在漫游车车轮周围，能够读取车轮下方地面的压力特征。无论是新的还是传统的DL工具以前都没有应用于触觉传感数据。我们讨论了这些方法的优点和局限性的分析，非传统的压力图像及其在行星表面科学的潜在用途的见解。
Tactile and embedded sensing is a new concept that has recently appeared in the context of rovers and planetary exploration missions. Various sensors such as those measuring pressure and integrated directly on wheels have the potential to add a "sense of touch" to exploratory vehicles. We investigate the utility of deep learning (DL), from conventional Convolutional Neural Networks (CNN) to emerging geometric and topological DL, to terrain classification for planetary exploration based on a novel dataset from an experimental tactile wheel concept. The dataset includes 2D conductivity images from a pressure sensor array, which is wrapped around a rover wheel and is able to read pressure signatures of the ground beneath the wheel. Neither newer nor traditional DL tools have been previously applied to tactile sensing data. We discuss insights into advantages and limitations of these methods for the analysis of non-traditional pressure images and their potential use in planetary surface science.