Effects of Neural Network Architecture on Topography Estimation From Satellite Imagery for Multi-Terrain Autonomous Vehicle Path Planning and Control
Effects of Neural Network Architecture on Topography Estimation From Satellite Imagery for Multi-Terrain Autonomous Vehicle Path Planning and Control
复制标题
DOI：
10.1109/most57249.2023.00021
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Ryan Lynch;Sumedh Beknalkar;Jack Lynch;A. Mazzoleni;M. Bryant
中科院分区：
文献类型：
--
作者：
Ryan Lynch;Sumedh Beknalkar;Jack Lynch;A. Mazzoleni;M. Bryant
全球变暖是世界上最紧迫的问题之一。然而，研究它对极地冰盖和其他北极环境的影响可能会受到那里经常存在的危险和难以航行的地形的阻碍。多地形自动驾驶汽车可以通过提供一个移动的平台来帮助研究人员在这些恶劣的环境中收集数据，同时避免对人类生命的任何风险并加快研究过程。这些自主机器人车辆的机械设计和最终功效在很大程度上取决于它们所部署的特定任务，但地形条件在地理上和季节性上可能变化很大，使得这些无人驾驶车辆的使命规划更加困难。本文提出了使用各种基于UNet的神经网络架构，从卫星图像生成数字高程图，并探讨和比较其功效的一组训练和验证数据集生成的卫星图像。这些由模型生成的数字高程图不仅可以被研究人员用来跟踪北极地形随时间的变化，而且可以快速为自主探索研究漫游车提供必要的地形信息，以确定使命期间的最佳路径。本文分析了不同的模型架构和训练方案：传统的UNet，传统的UNet与数据增强，一个UNet与一个单一的主动跳层视觉Transformer（ViT），和一个UNet与多个主动跳层ViT。每个模型都是在加拿大埃尔斯米尔岛的卫星图像数据集和相应的数字高程图上训练的。利用ViTs并没有显示出UNet性能的显着改善，但这可能会随着培训时间的延长而改变。本文提出了提高这些神经网络性能的机会，以及进一步研究的后续步骤，包括提高数据集中图像的多样性，从完全不同的地理位置生成测试数据集，并允许模型有更多的时间进行训练。
Global warming is one of the world’s most pressing issues. The study of its effects on the polar ice caps and other arctic environments, however, can be hindered by the often dangerous and difficult to navigate terrain found there. Multi-terrain autonomous vehicles can assist researchers by providing a mobile platform on which to collect data in these harsh environments while avoiding any risk to human life and speeding up the research process. The mechanical design and ultimate efficacy of these autonomous robotic vehicles depends largely on the specific missions they are deployed for, but terrain conditions can vary wildly geographically as well as seasonally, making mission planning for these unmanned vehicles more difficult. This paper proposes the use of various UNet-based neural network architectures to generate digital elevation maps from satellite images, and explores and compares their efficacy on a single set of training and validation datasets generated from satellite imagery. These digital elevation maps generated by the model could be used by researchers not only to track the change in arctic topography over time, but to quickly provide autonomous exploratory research rovers with the topographical information necessary to decide on optimal paths during the mission. This paper analyzes different model architectures and training schemes: a traditional UNet, a traditional UNet with data augmentation, a UNet with a single active skip-layer vision transformer (ViT), and a UNet with multiple active skip-layer ViT. Each model was trained on a dataset of satellite images and corresponding digital elevation maps of Ellesmere Island, Canada. Utilizing ViTs did not demonstrate a significant improvement in UNet performance, though this could change with longer training. This paper proposes opportunities to improve performance for these neural networks, as well as next steps for further research, including improving the diversity of images in the dataset, generating a testing dataset from a completely different geographic location, and allowing the models more time to train.