VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems
Indoor environments have abundant presence of high-level semantic information which can provide a better understanding of the environment for robots to improve the uncertainty in their pose estimate. Although semantic information has proved to be useful, there are several challenges faced by the res...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9045978/ |
| _version_ | 1818428170202775552 |
|---|---|
| author | Hriday Bavle Paloma De La Puente Jonathan P. How Pascual Campoy |
| author_facet | Hriday Bavle Paloma De La Puente Jonathan P. How Pascual Campoy |
| author_sort | Hriday Bavle |
| collection | DOAJ |
| description | Indoor environments have abundant presence of high-level semantic information which can provide a better understanding of the environment for robots to improve the uncertainty in their pose estimate. Although semantic information has proved to be useful, there are several challenges faced by the research community to accurately perceive, extract and utilize such semantic information from the environment. In order to address these challenges, in this paper we present a lightweight and real-time visual semantic SLAM framework running on board aerial robotic platforms. This novel method combines low-level visual/visual-inertial odometry (VO/VIO) along with geometrical information corresponding to planar surfaces extracted from detected semantic objects. Extracting the planar surfaces from selected semantic objects provides enhanced robustness and makes it possible to precisely improve the metric estimates rapidly, simultaneously generalizing to several object instances irrespective of their shape and size. Our graph-based approach can integrate several state of the art VO/VIO algorithms along with the state of the art object detectors in order to estimate the complete 6DoF pose of the robot while simultaneously creating a sparse semantic map of the environment. No prior knowledge of the objects is required, which is a significant advantage over other works. We test our approach on a standard RGB-D dataset comparing its performance with the state of the art SLAM algorithms. We also perform several challenging indoor experiments validating our approach in presence of distinct environmental conditions and furthermore test it on board an aerial robot. Video:https://vimeo.com/368217703Released Code:https://bitbucket.org/hridaybavle/semantic_slam.git. |
| first_indexed | 2024-12-14T14:57:22Z |
| format | Article |
| id | doaj.art-2c6e676e5e674f04bb670adb3b2a1698 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T14:57:22Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2c6e676e5e674f04bb670adb3b2a16982022-12-21T22:56:58ZengIEEEIEEE Access2169-35362020-01-018607046071810.1109/ACCESS.2020.29831219045978VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic SystemsHriday Bavle0https://orcid.org/0000-0002-1732-0647Paloma De La Puente1https://orcid.org/0000-0002-8652-0300Jonathan P. How2https://orcid.org/0000-0001-8576-1930Pascual Campoy3https://orcid.org/0000-0002-9894-2009Centre for Automation and Robotics, Computer Vision and Aerial Robotics Group, Universidad Politécnica de Madrid (UPM-CSIC), Madrid, SpainCentre for Automation and Robotics, Computer Vision and Aerial Robotics Group, Universidad Politécnica de Madrid (UPM-CSIC), Madrid, SpainAerospace Controls Laboratory, Massachusetts Institute of Technology (MIT), Cambridge, MA, USACentre for Automation and Robotics, Computer Vision and Aerial Robotics Group, Universidad Politécnica de Madrid (UPM-CSIC), Madrid, SpainIndoor environments have abundant presence of high-level semantic information which can provide a better understanding of the environment for robots to improve the uncertainty in their pose estimate. Although semantic information has proved to be useful, there are several challenges faced by the research community to accurately perceive, extract and utilize such semantic information from the environment. In order to address these challenges, in this paper we present a lightweight and real-time visual semantic SLAM framework running on board aerial robotic platforms. This novel method combines low-level visual/visual-inertial odometry (VO/VIO) along with geometrical information corresponding to planar surfaces extracted from detected semantic objects. Extracting the planar surfaces from selected semantic objects provides enhanced robustness and makes it possible to precisely improve the metric estimates rapidly, simultaneously generalizing to several object instances irrespective of their shape and size. Our graph-based approach can integrate several state of the art VO/VIO algorithms along with the state of the art object detectors in order to estimate the complete 6DoF pose of the robot while simultaneously creating a sparse semantic map of the environment. No prior knowledge of the objects is required, which is a significant advantage over other works. We test our approach on a standard RGB-D dataset comparing its performance with the state of the art SLAM algorithms. We also perform several challenging indoor experiments validating our approach in presence of distinct environmental conditions and furthermore test it on board an aerial robot. Video:https://vimeo.com/368217703Released Code:https://bitbucket.org/hridaybavle/semantic_slam.git.https://ieeexplore.ieee.org/document/9045978/SLAMvisual SLAMvisual semantic SLAMautonomous aerial robotsUAVs |
| spellingShingle | Hriday Bavle Paloma De La Puente Jonathan P. How Pascual Campoy VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems IEEE Access SLAM visual SLAM visual semantic SLAM autonomous aerial robots UAVs |
| title | VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems |
| title_full | VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems |
| title_fullStr | VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems |
| title_full_unstemmed | VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems |
| title_short | VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems |
| title_sort | vps slam visual planar semantic slam for aerial robotic systems |
| topic | SLAM visual SLAM visual semantic SLAM autonomous aerial robots UAVs |
| url | https://ieeexplore.ieee.org/document/9045978/ |
| work_keys_str_mv | AT hridaybavle vpsslamvisualplanarsemanticslamforaerialroboticsystems AT palomadelapuente vpsslamvisualplanarsemanticslamforaerialroboticsystems AT jonathanphow vpsslamvisualplanarsemanticslamforaerialroboticsystems AT pascualcampoy vpsslamvisualplanarsemanticslamforaerialroboticsystems |