Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey
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 existi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/4/1243 |
| _version_ | 1797411938328641536 |
|---|---|
| author | Saba Arshad Gon-Woo Kim |
| author_facet | Saba Arshad Gon-Woo Kim |
| author_sort | Saba Arshad |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T04:53:37Z |
| format | Article |
| id | doaj.art-04f24c9d5f9a45b6ad26133e21904270 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T04:53:37Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-04f24c9d5f9a45b6ad26133e219042702023-12-03T13:08:01ZengMDPI AGSensors1424-82202021-02-01214124310.3390/s21041243Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A SurveySaba Arshad0Gon-Woo Kim1Intelligent Robots Laboratory, Department of Control and Robot Engineering, Chungbuk National University, Cheongju-si 28644, KoreaIntelligent Robots Laboratory, Department of Control and Robot Engineering, Chungbuk National University, Cheongju-si 28644, KoreaLoop 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.https://www.mdpi.com/1424-8220/21/4/1243simultaneous localization and mappingloop closure detectiondeep learningneural networksautonomous mobile robots |
| spellingShingle | Saba Arshad Gon-Woo Kim Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey Sensors simultaneous localization and mapping loop closure detection deep learning neural networks autonomous mobile robots |
| title | Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey |
| title_full | Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey |
| title_fullStr | Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey |
| title_full_unstemmed | Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey |
| title_short | Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey |
| title_sort | role of deep learning in loop closure detection for visual and lidar slam a survey |
| topic | simultaneous localization and mapping loop closure detection deep learning neural networks autonomous mobile robots |
| url | https://www.mdpi.com/1424-8220/21/4/1243 |
| work_keys_str_mv | AT sabaarshad roleofdeeplearninginloopclosuredetectionforvisualandlidarslamasurvey AT gonwookim roleofdeeplearninginloopclosuredetectionforvisualandlidarslamasurvey |