A consistent and long-term mapping approach for navigation
The construction and maintenance of a robocentric map is key to high-level mobile robotic tasks like path planning and smart navigation. But the challenge of dynamic environment and huge amount of dense sensor data makes it hard to be implemented in a real-world application for long-term use. In thi...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://www.zealpress.com/ijratv5a4/ https://hdl.handle.net/10356/141288 |
| _version_ | 1826128402283757568 |
|---|---|
| author | Zhang, Handuo Karunasekera, Hasith Wang, Han |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Zhang, Handuo Karunasekera, Hasith Wang, Han |
| author_sort | Zhang, Handuo |
| collection | NTU |
| description | The construction and maintenance of a robocentric map is key to high-level mobile robotic tasks like path planning and smart navigation. But the challenge of dynamic environment and huge amount of dense sensor data makes it hard to be implemented in a real-world application for long-term use. In this paper we present a novel mapping approach by incorporating semantic cuboid object detection and multi-view geometry information. The proposed system can precisely describe the incremental 3D environment in real-time and maintain a long-term map by extracting out moving objects. The representation of the map is a collection of sub-volumes which can be utilized to perform pose graph optimization to address the challenge of building a consistent and scalable map. These sub-volumes are first aligned by localization module and refined by fusing the active volumes using co-visible graph. With the proposed framework we can obtain the object-level constraints and propose a consistent obstacle mapping system combining multi-view geometry with obstacle detection to obtain robust static map in a complex environment. Public dataset and self-collected data demonstrate the efficiency and consistency of our proposed approach. |
| first_indexed | 2024-10-01T07:24:23Z |
| format | Journal Article |
| id | ntu-10356/141288 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:24:23Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1412882020-06-05T08:33:49Z A consistent and long-term mapping approach for navigation Zhang, Handuo Karunasekera, Hasith Wang, Han School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics Robocentric Mapping Navigation The construction and maintenance of a robocentric map is key to high-level mobile robotic tasks like path planning and smart navigation. But the challenge of dynamic environment and huge amount of dense sensor data makes it hard to be implemented in a real-world application for long-term use. In this paper we present a novel mapping approach by incorporating semantic cuboid object detection and multi-view geometry information. The proposed system can precisely describe the incremental 3D environment in real-time and maintain a long-term map by extracting out moving objects. The representation of the map is a collection of sub-volumes which can be utilized to perform pose graph optimization to address the challenge of building a consistent and scalable map. These sub-volumes are first aligned by localization module and refined by fusing the active volumes using co-visible graph. With the proposed framework we can obtain the object-level constraints and propose a consistent obstacle mapping system combining multi-view geometry with obstacle detection to obtain robust static map in a complex environment. Public dataset and self-collected data demonstrate the efficiency and consistency of our proposed approach. NRF (Natl Research Foundation, S’pore) Published version 2020-06-05T08:33:49Z 2020-06-05T08:33:49Z 2018 Journal Article Zhang, H., Karunasekera, H., & Wang, H. (2018). A consistent and long-term mapping approach for navigation. International Journal of Robotics and Automation Technology, 5, 23-31. 2409-9694 https://www.zealpress.com/ijratv5a4/ https://hdl.handle.net/10356/141288 5 23 31 en MRP1A International Journal of Robotics and Automation Technology © 2018 Zhang et al.; Licensee Zeal Press. This is an open access article licensed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/), which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited. application/pdf |
| spellingShingle | Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics Robocentric Mapping Navigation Zhang, Handuo Karunasekera, Hasith Wang, Han A consistent and long-term mapping approach for navigation |
| title | A consistent and long-term mapping approach for navigation |
| title_full | A consistent and long-term mapping approach for navigation |
| title_fullStr | A consistent and long-term mapping approach for navigation |
| title_full_unstemmed | A consistent and long-term mapping approach for navigation |
| title_short | A consistent and long-term mapping approach for navigation |
| title_sort | consistent and long term mapping approach for navigation |
| topic | Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics Robocentric Mapping Navigation |
| url | https://www.zealpress.com/ijratv5a4/ https://hdl.handle.net/10356/141288 |
| work_keys_str_mv | AT zhanghanduo aconsistentandlongtermmappingapproachfornavigation AT karunasekerahasith aconsistentandlongtermmappingapproachfornavigation AT wanghan aconsistentandlongtermmappingapproachfornavigation AT zhanghanduo consistentandlongtermmappingapproachfornavigation AT karunasekerahasith consistentandlongtermmappingapproachfornavigation AT wanghan consistentandlongtermmappingapproachfornavigation |