EAGER: Toward Descriptive Mapping for Underwater Exploration

EAGER：走向水下探索的描述性绘图

• 批准号: 1551391
• 负责人: Brendan Englot
• 金额: $ 9.5万
• 依托单位: Stevens Institute of Technology
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-09-01 至 2017-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1551391&HistoricalAwards=false
• 关键词: EAGER; Toward; Descriptive; Mapping; Underwater

This project will provide a new solution for 3D mapping and exploration of underwater environments characterized by sparse and noisy data. It will enhance the capability of underwater robots to autonomously map, navigate, and inspect a previously unknown shallow-water environment. The development of this project will benefit from its long association with United States Coast Guard.This project will advance the state of the art in three-dimensional occupancy mapping using Gaussian process regression, a supervised learning method with great promise for its application to robot mapping. This project will apply these methods to online 3D mapping with a field robot, mapping underwater structures with a scanning sonar.

该项目将为以稀疏和噪声数据为特征的水下环境的3D映射和探索提供新的解决方案。它将增强水下机器人自主绘制地图、导航和检查以前未知的浅水环境的能力。该项目的发展将受益于其与美国海岸警卫队的长期合作，该项目将利用高斯过程回归推进三维占用映射的最新技术，这是一种有监督的学习方法，在机器人映射中具有很大的应用前景。该项目将应用这些方法与现场机器人进行在线3D映射，用扫描声纳映射水下结构。