Synchronous Adversarial Feature Learning for LiDAR based Loop Closure Detection

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Synchronous Adversarial Feature Learning for LiDAR based Loop Closure Detection
	Yin P(殷鹏)1,4; Xu WL(徐卫良)3; Han JD(韩建达)1 ; Peng Y(彭艳)2; Xu LY(许凌云)1,4 ; He YQ(何玉庆)1
	2018
会议日期	June 27-29, 2018
会议地点	Milwauke, WI, United states
页码	234-239
英文摘要	Loop C losure Detection (LCD) is the essential module in the simultaneous localization and mapping (SLAM) task. In the current appearance-based SLAM methods, the visual inputs are usually affected by illumination, appearance and viewpoints changes. Comparing to the visual inputs, with the active property, light detection and ranging (LiDAR) based point-cloud inputs are invariant to the illumination and appearance changes. In this paper, we extract 3D voxel maps and 2D top view maps from LiDAR inputs, and the former could capture the local geometry into a simplified 3D voxel format, the later could capture the local road structure into a 2D image format. However, the most challenge problem is to obtain efficient features from 3D and 2D maps to against the viewpoints difference. In this paper, we proposed a synchronous adversarial feature learning method for the LCD task, which could learn the higher level abstract features from different domains without any label data. To the best of our knowledge, this work is the first to extract multi-domain adversarial features for the LCD task in real time. To investigate the performance, we test the proposed method on the KITTI odometry dataset. The extensive experiments results show that, the proposed method could largely improve LCD accuracy even under huge viewpoints differences.
产权排序	1
会议录	2018 Annual American Control Conference, ACC 2018
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISSN号	0743-1619
ISBN号	978-1-5386-5428-6
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/22737]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Yin P(殷鹏)
作者单位	1.Shenyang Institute of Automation, Chinese Academy of Sciences, State Key Laboratory of Robotics, Shenyang 110016, China 2.School of Mechatronic Engineering and Automation, Robotics, Shanghai, China 3.University of Auckland, Department of Mechanical Engineering, New Zealand 4.University of Chinese Academy of Sciences, Beijing 100049
推荐引用方式 GB/T 7714	Yin P,Xu WL,Han JD,et al. Synchronous Adversarial Feature Learning for LiDAR based Loop Closure Detection[C]. 见:. Milwauke, WI, United states. June 27-29, 2018.