期刊
SENSORS
卷 21, 期 4, 页码 -出版社
MDPI
DOI: 10.3390/s21041243
关键词
simultaneous localization and mapping; loop closure detection; deep learning; neural networks; autonomous mobile robots
资金
- Ministry of Trade, Industry and Energy (MOTIE)
- Korea Institute for Advancement of Technology (KIAT) through the International Cooperative RD program [P0004631]
- MSIT (Ministry of Science and ICT), Korea, under the Grand Information Technology Research Center support program [IITP-2020-001462]
- Institute of Information & communications Technology Planning & Evaluation (IITP) - Korea government (MSIT) [IITP-2020-0-00211]
- Institute for Information & Communication Technology Planning & Evaluation (IITP), Republic of Korea [2020-0-01462-002, 2020-0-00211-002] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
- Korea Evaluation Institute of Industrial Technology (KEIT) [P0004631] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Loop closure detection is crucial in SLAM, reducing error and creating a consistent global map. This survey examines existing literature on loop closure detection algorithms, particularly focusing on deep learning-based methods, identifying challenges, and discussing future directions.
Loop closure detection is of vital importance in the process of simultaneous localization and mapping (SLAM), as it helps to reduce the cumulative error of the robot's estimated pose and generate a consistent global map. Many variations of this problem have been considered in the past and the existing methods differ in the acquisition approach of query and reference views, the choice of scene representation, and associated matching strategy. Contributions of this survey are many-fold. It provides a thorough study of existing literature on loop closure detection algorithms for visual and Lidar SLAM and discusses their insight along with their limitations. It presents a taxonomy of state-of-the-art deep learning-based loop detection algorithms with detailed comparison metrics. Also, the major challenges of conventional approaches are identified. Based on those challenges, deep learning-based methods were reviewed where the identified challenges are tackled focusing on the methods providing long-term autonomy in various conditions such as changing weather, light, seasons, viewpoint, and occlusion due to the presence of mobile objects. Furthermore, open challenges and future directions were also discussed.
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