VAST: Visual and Spectral Terrain Classification in Unstructured Multi-Class Environments
VAST: Visual and Spectral Terrain Classification in Unstructured Multi-Class Environments
复制标题
VAST：非结构化多类环境中的视觉和光谱地形分类
DOI：
10.1109/iros47612.2022.9982078
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
T. Padır
中科院分区：
文献类型：
--
作者：
Nathaniel Hanson;Michael Shaham;D. Erdoğmuş;T. Padır
对于在非结构化环境中运行的机器人来说，地形分类是一项具有挑战性的任务。现有的分类方法做出了简化的假设，例如类别数量减少、可清晰分割的道路或良好的照明条件，并主要关注一种传感器类型。这些假设不能很好地转化为越野车辆，因为越野车辆在不同的地形条件下运行。为了提供移动的机器人的能力，以识别正在穿越的地形，避免不理想的表面类型，我们提出了一个多模态传感器套件能够分类不同的地形。我们捕捉高分辨率的宏观图像的表面纹理，光谱反射率曲线，并从9自由度（DOF）的惯性测量单元（IMU）在11个不同的地形在一天中的不同时间的本地化数据。使用这个数据集，我们在每种模式上训练单独的神经网络，然后将它们的输出联合收割机组合在一个融合网络中。融合网络在测试集上的准确率达到99.98%，超过最佳单个网络组件的结果0.98%。我们的结论是，视觉，光谱和IMU数据的组合提供了有意义的改进，在最先进的地形分类方法。为这项研究创建的数据可在https://github.com/RIVeR-Lab/vast_data上获得。
Terrain classification is a challenging task for robots operating in unstructured environments. Existing classification methods make simplifying assumptions, such as a reduced number of classes, clearly segmentable roads, or good lighting conditions, and focus primarily on one sensor type. These assumptions do not translate well to off-road vehicles, which operate in varying terrain conditions. To provide mobile robots with the capability to identify the terrain being traversed and avoid undesirable surface types, we propose a multimodal sensor suite capable of classifying different terrains. We capture high resolution macro images of surface texture, spectral reflectance curves, and localization data from a 9 degrees of freedom (DOF) inertial measurement unit (IMU) on 11 different terrains at different times of day. Using this dataset, we train individual neural networks on each of the modalities, and then combine their outputs in a fusion network. The fused network achieved an accuracy of 99.98% percent on the test set, exceeding the results of the best individual network component by 0.98%. We conclude that a combination of visual, spectral, and IMU data provides meaningful improvement over state of the art in terrain classification approaches. The data created for this research is available at https://github.com/RIVeR-Lab/vast_data.
影响因子：
5.2
作者：
Chen, Yu;Rastogi, Chirag;Norris, William R.
通讯作者：
Norris, William R.
使用受控光纤光谱技术进行软抓手的手持物体识别
DOI：
10.1109/robosoft54090.2022.9762166
发表时间：
2021
期刊：
2022 IEEE 5th International Conference on Soft Robotics (RoboSoft
影响因子：
--
作者：
Hanson, Nathaniel;Hochsztein, Hillel;Vaidya, Akshay;Willick, Joel;Dorsey, Kristen;Padir, Taskin
通讯作者：
Padir, Taskin