Stabilize an Unsupervised Feature Learning for LiDAR-based Place Recognition
文献类型：会议论文
| 作者 | Wang HS(王贺升)3; Choset, Howie5; Yin P(殷鹏)1,2; Xu LY(许凌云)1,2 ; Liu Z(刘哲)6; Li, Lu5; Salman, Hadi5; He YQ(何玉庆)1,2; Xu WL(徐卫良)4
|
| 出版日期 | 2018 |
| 会议日期 | October 1-5, 2018 |
| 会议地点 | Madrid, Spain |
| 页码 | 1162-1167 |
| 英文摘要 | Place recognition is one of the major challenges for the LiDAR-based effective localization and mapping task. Traditional methods are usually relying on geometry matching to achieve place recognition, where a global geometry map need to be restored. In this paper, we accomplish the place recognition task based on an end-to-end feature learning framework with the LiDAR inputs. This method consists of two core modules, a dynamic octree mapping module that generates local 2D maps with the consideration of the robot's motion; and an unsupervised place feature learning module which is an improved adversarial feature learning network with additional assistance for the long-term place recognition requirement. More specially, in place feature learning, we present an additional Generative Adversarial Network with a designed Conditional Entropy Reduction module to stabilize the feature learning process in an unsupervised manner. We evaluate the proposed method on the Kitti dataset and North Campus Long-Term LiDAR dataset. Experimental results show that the proposed method outperforms state-of-the-art in place recognition tasks under long-term applications. What's more, the feature size and inference efficiency in the proposed method are applicable in real-time performance on practical robotic platforms. |
| 产权排序 | 1 |
| 会议录 | 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | New York |
| 语种 | 英语 |
| ISSN号 | 2153-0858 |
| ISBN号 | 978-1-5386-8094-0 |
| WOS记录号 | WOS:000458872701042 |
| 源URL | [http://ir.sia.cn/handle/173321/23864]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 通讯作者 | Xu LY(许凌云) |
| 作者单位 | 1.University of Chinese Academy of Sciences, Beijing, China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China 3.Department of Automation, Shanghai Jiao Tong University, Shanghai, China 4.Department of Mechanical Engineering, University of Auckland, New Zealand 5.Robotics Institute at Carnegie Mellon University, Pittsburgh, USA 6.Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong |
| 推荐引用方式 GB/T 7714 | Wang HS,Choset, Howie,Yin P,et al. Stabilize an Unsupervised Feature Learning for LiDAR-based Place Recognition[C]. 见:. Madrid, Spain. October 1-5, 2018. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。