Robotic Mapping Approach under Illumination-Variant Environments at Planetary Construction Sites
In planetary construction, the semiautonomous teleoperation of robots is expected to perform complex tasks for site preparation and infrastructure emplacement. A highly detailed 3D map is essential for construction planning and management. However, the planetary surface imposes mapping restrictions...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/4/1027 |
| _version_ | 1797476738588999680 |
|---|---|
| author | Sungchul Hong Pranjay Shyam Antyanta Bangunharcana Hyuseoung Shin |
| author_facet | Sungchul Hong Pranjay Shyam Antyanta Bangunharcana Hyuseoung Shin |
| author_sort | Sungchul Hong |
| collection | DOAJ |
| description | In planetary construction, the semiautonomous teleoperation of robots is expected to perform complex tasks for site preparation and infrastructure emplacement. A highly detailed 3D map is essential for construction planning and management. However, the planetary surface imposes mapping restrictions due to rugged and homogeneous terrains. Additionally, changes in illumination conditions cause the mapping result (or 3D point-cloud map) to have inconsistent color properties that hamper the understanding of the topographic properties of a worksite. Therefore, this paper proposes a robotic construction mapping approach robust to illumination-variant environments. The proposed approach leverages a deep learning-based low-light image enhancement (LLIE) method to improve the mapping capabilities of the visual simultaneous localization and mapping (SLAM)-based robotic mapping method. In the experiment, the robotic mapping system in the emulated planetary worksite collected terrain images during the daytime from noon to late afternoon. Two sets of point-cloud maps, which were created from original and enhanced terrain images, were examined for comparison purposes. The experiment results showed that the LLIE method in the robotic mapping method significantly enhanced the brightness, preserving the inherent colors of the original terrain images. The visibility and the overall accuracy of the point-cloud map were consequently increased. |
| first_indexed | 2024-03-09T21:07:57Z |
| format | Article |
| id | doaj.art-343b3ceea5f44e27aefb2e58098c5e3c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T21:07:57Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-343b3ceea5f44e27aefb2e58098c5e3c2023-11-23T21:55:49ZengMDPI AGRemote Sensing2072-42922022-02-01144102710.3390/rs14041027Robotic Mapping Approach under Illumination-Variant Environments at Planetary Construction SitesSungchul Hong0Pranjay Shyam1Antyanta Bangunharcana2Hyuseoung Shin3Department of Geoinformatic Engineering, Inha University, Incheon 22212, KoreaDepartment of Mechanical Engineering, Korea Advanced Institute of Science and Technology, College of Engineering, Daejeon 34141, KoreaDepartment of Mechanical Engineering, Korea Advanced Institute of Science and Technology, College of Engineering, Daejeon 34141, KoreaDepartment of Future Technology and Convergence Research, Korea Institute of Civil Engineering and Building Technology, Goyang-si 10223, KoreaIn planetary construction, the semiautonomous teleoperation of robots is expected to perform complex tasks for site preparation and infrastructure emplacement. A highly detailed 3D map is essential for construction planning and management. However, the planetary surface imposes mapping restrictions due to rugged and homogeneous terrains. Additionally, changes in illumination conditions cause the mapping result (or 3D point-cloud map) to have inconsistent color properties that hamper the understanding of the topographic properties of a worksite. Therefore, this paper proposes a robotic construction mapping approach robust to illumination-variant environments. The proposed approach leverages a deep learning-based low-light image enhancement (LLIE) method to improve the mapping capabilities of the visual simultaneous localization and mapping (SLAM)-based robotic mapping method. In the experiment, the robotic mapping system in the emulated planetary worksite collected terrain images during the daytime from noon to late afternoon. Two sets of point-cloud maps, which were created from original and enhanced terrain images, were examined for comparison purposes. The experiment results showed that the LLIE method in the robotic mapping method significantly enhanced the brightness, preserving the inherent colors of the original terrain images. The visibility and the overall accuracy of the point-cloud map were consequently increased.https://www.mdpi.com/2072-4292/14/4/1027planetary constructionrobotic mappingSLAMlow-light enhancement3D point-cloud mapdeep learning |
| spellingShingle | Sungchul Hong Pranjay Shyam Antyanta Bangunharcana Hyuseoung Shin Robotic Mapping Approach under Illumination-Variant Environments at Planetary Construction Sites Remote Sensing planetary construction robotic mapping SLAM low-light enhancement 3D point-cloud map deep learning |
| title | Robotic Mapping Approach under Illumination-Variant Environments at Planetary Construction Sites |
| title_full | Robotic Mapping Approach under Illumination-Variant Environments at Planetary Construction Sites |
| title_fullStr | Robotic Mapping Approach under Illumination-Variant Environments at Planetary Construction Sites |
| title_full_unstemmed | Robotic Mapping Approach under Illumination-Variant Environments at Planetary Construction Sites |
| title_short | Robotic Mapping Approach under Illumination-Variant Environments at Planetary Construction Sites |
| title_sort | robotic mapping approach under illumination variant environments at planetary construction sites |
| topic | planetary construction robotic mapping SLAM low-light enhancement 3D point-cloud map deep learning |
| url | https://www.mdpi.com/2072-4292/14/4/1027 |
| work_keys_str_mv | AT sungchulhong roboticmappingapproachunderilluminationvariantenvironmentsatplanetaryconstructionsites AT pranjayshyam roboticmappingapproachunderilluminationvariantenvironmentsatplanetaryconstructionsites AT antyantabangunharcana roboticmappingapproachunderilluminationvariantenvironmentsatplanetaryconstructionsites AT hyuseoungshin roboticmappingapproachunderilluminationvariantenvironmentsatplanetaryconstructionsites |