Outdoor SLAM using visual appearance and laser ranging
This paper describes a 3D SLAM system using information from an actuated laser scanner and camera installed on a mobile robot. The laser samples the local geometry of the environment and is used to incrementally build a 3D point-cloud map of the workspace. Sequences of images from the camera are use...
| المؤلفون الرئيسيون: | , , , |
|---|---|
| التنسيق: | Conference item |
| منشور في: |
2006
|
| _version_ | 1826276160692027392 |
|---|---|
| author | Newman, P Cole, D Ho, K IEEE |
| author_facet | Newman, P Cole, D Ho, K IEEE |
| author_sort | Newman, P |
| collection | OXFORD |
| description | This paper describes a 3D SLAM system using information from an actuated laser scanner and camera installed on a mobile robot. The laser samples the local geometry of the environment and is used to incrementally build a 3D point-cloud map of the workspace. Sequences of images from the camera are used to detect loop closure events (without reference to the internal estimates of vehicle location) using a novel appearance-based retrieval system. The loop closure detection is robust to repetitive visual structure and provides a probabilistic measure of confidence. The images suggesting loop closure are then further processed with their corresponding local laser scans to yield putative Euclidean image-image transformations. We show how naive application of this transformation to effect the loop closure can lead to catastrophic linearization errors and go on to describe a way in which gross, pre-loop closing errors can he successfully annulled. We demonstrate our system working in a challenging, outdoor setting containing substantial loops and beguiling, gently curving traversais. The results are overlaid on an aerial image to provide a ground truth comparison with the estimated map. The paper concludes with an extension into the multi-robot domain in which 3D maps resulting from distinct SLAM sessions (no common reference frame) are combined without recourse to mutual observation. © 2006 IEEE. |
| first_indexed | 2024-03-06T23:09:50Z |
| format | Conference item |
| id | oxford-uuid:6510f58b-a8ab-4cd2-be8f-e3de738ad41a |
| institution | University of Oxford |
| last_indexed | 2024-03-06T23:09:50Z |
| publishDate | 2006 |
| record_format | dspace |
| spelling | oxford-uuid:6510f58b-a8ab-4cd2-be8f-e3de738ad41a2022-03-26T18:23:08ZOutdoor SLAM using visual appearance and laser rangingConference itemhttp://purl.org/coar/resource_type/c_5794uuid:6510f58b-a8ab-4cd2-be8f-e3de738ad41aSymplectic Elements at Oxford2006Newman, PCole, DHo, KIEEEThis paper describes a 3D SLAM system using information from an actuated laser scanner and camera installed on a mobile robot. The laser samples the local geometry of the environment and is used to incrementally build a 3D point-cloud map of the workspace. Sequences of images from the camera are used to detect loop closure events (without reference to the internal estimates of vehicle location) using a novel appearance-based retrieval system. The loop closure detection is robust to repetitive visual structure and provides a probabilistic measure of confidence. The images suggesting loop closure are then further processed with their corresponding local laser scans to yield putative Euclidean image-image transformations. We show how naive application of this transformation to effect the loop closure can lead to catastrophic linearization errors and go on to describe a way in which gross, pre-loop closing errors can he successfully annulled. We demonstrate our system working in a challenging, outdoor setting containing substantial loops and beguiling, gently curving traversais. The results are overlaid on an aerial image to provide a ground truth comparison with the estimated map. The paper concludes with an extension into the multi-robot domain in which 3D maps resulting from distinct SLAM sessions (no common reference frame) are combined without recourse to mutual observation. © 2006 IEEE. |
| spellingShingle | Newman, P Cole, D Ho, K IEEE Outdoor SLAM using visual appearance and laser ranging |
| title | Outdoor SLAM using visual appearance and laser ranging |
| title_full | Outdoor SLAM using visual appearance and laser ranging |
| title_fullStr | Outdoor SLAM using visual appearance and laser ranging |
| title_full_unstemmed | Outdoor SLAM using visual appearance and laser ranging |
| title_short | Outdoor SLAM using visual appearance and laser ranging |
| title_sort | outdoor slam using visual appearance and laser ranging |
| work_keys_str_mv | AT newmanp outdoorslamusingvisualappearanceandlaserranging AT coled outdoorslamusingvisualappearanceandlaserranging AT hok outdoorslamusingvisualappearanceandlaserranging AT ieee outdoorslamusingvisualappearanceandlaserranging |