基于三维激光测距的移动机器人室外环境语义地图构建

项目名称： 基于三维激光测距的移动机器人室外环境语义地图构建

项目编号： No.61503056

项目类型： 青年科学基金项目

立项/批准年度： 2016

项目学科： 自动化技术、计算机技术

项目作者： 闫飞

作者单位： 大连理工大学

项目金额： 20万元

中文摘要： 以工作在室外三维环境中的移动机器人语义地图构建为研究对象，针对三维激光数据图像化表述、室外物体识别以及环境语义信息提取等问题，研究移动机器人在室外环境中的自主行为问题的系统理论与实用方法。从三维激光数据的动态补偿入手，建立面向复杂室外三维场景的语义地图构建方法框架，重点研究具有在线自学习能力的室外场景理解中的样本更新，以及大范围语义地图构建中的全局一致性维护问题，强调研究由基础的三维激光数据图像化表述、到自主室外场景理解、再到基于复合特征的语义地图构建研究所具有的相关性和连续性，给出针对这些共性问题的完整理论框架与使用方法，并利用实际平台进行实验验证。作为智能机器人自主行为理论的一项重要内容，本项目意义在于解决移动机器人自主工作在室外三维场景中所出现的新问题，从而为该方法的实用化提供可靠的技术支持和原型验证。

中文关键词： 语义地图；室外场景理解；三维环境建模；激光测距；移动机器人

英文摘要： In this project we will investigate the problem of semantic map building for mobile robots in 3D outdoor environments. Considering the complexity of 2D image representation for 3D laser scanning data, outdoor object detection and semantic information extraction, we try to present the systematic theory and practical method in the field of robot autonomous behavior. At the threshold of this project, we adopt a technique of dynamic compensation for 3D laser scanning data, so that a semantic mapping approach for complex outdoor environments can be proposed. Furthermore, we will focus on the sample updating technique in the scene understanding approach with online self-learning ability and the global consistency maintaining for large-scale semantic mapping. Also, we will lay emphasis on the research continuity and relationship between the basic image representation for 3D laser scanning data, outdoor scene understanding and semantic mapping, so that the complete theoretical framework and its application will be developed. Experimental results implemented on mobile robot platforms will be given to show the validity of the proposed methods. As the main tasks in the field of intelligent robot autonomous behavior, we will investigate the new problems when mobile robot works in 3D outdoor scenes, as well as provide technical support for future practical application by autonomous robot system in real environments.

英文关键词： semantic map;outdoor scene understanding;3D environment modeling;laser scanning;mobile robot