|
个人信息Personal Information
教授
博士生导师
硕士生导师
主要任职：Vice Dean of School of Control Science and Engineering
性别：男
毕业院校：大连理工大学
学位：博士
所在单位：控制科学与工程学院
学科：模式识别与智能系统. 控制理论与控制工程. 导航、制导与控制. 人工智能
办公地点：大连理工大学 创新园大厦 A611室
联系方式：办公电话：0411-84707581
电子邮箱：zhuang@dlut.edu.cn
Deep-Learning-based Relocalization in Large-Scale outdoor Environment
点击次数：
论文类型：会议论文
发表时间：2021-06-29
卷号：53
期号：2
页面范围：9722-9727
关键字：3D LiDAR Scan; DCNN; Relocalization; Mobile Robot; Outdoor Environment
摘要：For the issue of relocalization, this paper proposed a deep-learning-based method for outdoor large-scale environment. In the first step, we projected a 3D Light Detection and Ranging(LiDAR) scan onto three 2D images from top to bottom. Then a densenet-based neural network structure was designed to regress a 4-DOF robot pose. These images are then stacked together, fed into the proposed DCNN architecture, and the output is the predicted robot pose. Extensive experiments have been conducted in practice with a real mobile robot, verifying the effectiveness of the proposed strategy. Our network can obtain approximately 3.5m and 4 degrees accuracy outdoors. Copyright (C) 2020 The Authors.