期刊
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
卷 30, 期 9, 页码 1100-1123出版社
SAGE PUBLICATIONS LTD
DOI: 10.1177/0278364910385483
关键词
Robotics; SLAM; appearance-based navigation; FAB-MAP
类别
资金
- Systems Engineering for Autonomous Systems (SEAS) Defence Technology Centre
- EPSRC
- EPSRC [EP/I005021/1] Funding Source: UKRI
- Engineering and Physical Sciences Research Council [EP/I005021/1] Funding Source: researchfish
We describe a new formulation of appearance-only SLAM suitable for very large scale place recognition. The system navigates in the space of appearance, assigning each new observation to either a new or a previously visited location, without reference to metric position. The system is demonstrated performing reliable online appearance mapping and loop-closure detection over a 1000 km trajectory, with mean filter update times of 14 ms. The scalability of the system is achieved by defining a sparse approximation to the FAB-MAP model suitable for implementation using an inverted index. Our formulation of the problem is fully probabilistic and naturally incorporates robustness against perceptual aliasing. We also demonstrate that the approach substantially outperforms the standard term-frequency inverse-document-frequency (tf-idf) ranking measure. The 1000 km data set comprising almost a terabyte of omni-directional and stereo imagery is available for use, and we hope that it will serve as a benchmark for future systems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据