Localization in Unstructured Environments: Towards Autonomous Robots in Forests with Delaunay Triangulation
Autonomous harvesting and transportation is a long-term goal of the forest industry. One of the main challenges is the accurate localization of both vehicles and trees in a forest. Forests are unstructured environments where it is difficult to find a group of significant landmarks for current fast f...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/11/1870 |
| _version_ | 1797565712393306112 |
|---|---|
| author | Qingqing Li Paavo Nevalainen Jorge Peña Queralta Jukka Heikkonen Tomi Westerlund |
| author_facet | Qingqing Li Paavo Nevalainen Jorge Peña Queralta Jukka Heikkonen Tomi Westerlund |
| author_sort | Qingqing Li |
| collection | DOAJ |
| description | Autonomous harvesting and transportation is a long-term goal of the forest industry. One of the main challenges is the accurate localization of both vehicles and trees in a forest. Forests are unstructured environments where it is difficult to find a group of significant landmarks for current fast feature-based place recognition algorithms. This paper proposes a novel approach where local point clouds are matched to a global tree map using the Delaunay triangularization as the representation format. Instead of point cloud based matching methods, we utilize a topology-based method. First, tree trunk positions are registered at a prior run done by a forest harvester. Second, the resulting map is Delaunay triangularized. Third, a local submap of the autonomous robot is registered, triangularized and matched using triangular similarity maximization to estimate the position of the robot. We test our method on a dataset accumulated from a forestry site at Lieksa, Finland. A total length of 200 m of harvester path was recorded by an industrial harvester with a 3D laser scanner and a geolocation unit fixed to the frame. Our experiments show a 12 cm s.t.d. in the location accuracy and with real-time data processing for speeds not exceeding 0.5 m/s. The accuracy and speed limit are realistic during forest operations. |
| first_indexed | 2024-03-10T19:16:53Z |
| format | Article |
| id | doaj.art-531f427c8833459e99121fb266960ead |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T19:16:53Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-531f427c8833459e99121fb266960ead2023-11-20T03:17:28ZengMDPI AGRemote Sensing2072-42922020-06-011211187010.3390/rs12111870Localization in Unstructured Environments: Towards Autonomous Robots in Forests with Delaunay TriangulationQingqing Li0Paavo Nevalainen1Jorge Peña Queralta2Jukka Heikkonen3Tomi Westerlund4Turku Intelligent Embedded and Robotic Systems, University of Turku, 20500 Turku, FinlandTurku Intelligent Embedded and Robotic Systems, University of Turku, 20500 Turku, FinlandTurku Intelligent Embedded and Robotic Systems, University of Turku, 20500 Turku, FinlandTurku Intelligent Embedded and Robotic Systems, University of Turku, 20500 Turku, FinlandTurku Intelligent Embedded and Robotic Systems, University of Turku, 20500 Turku, FinlandAutonomous harvesting and transportation is a long-term goal of the forest industry. One of the main challenges is the accurate localization of both vehicles and trees in a forest. Forests are unstructured environments where it is difficult to find a group of significant landmarks for current fast feature-based place recognition algorithms. This paper proposes a novel approach where local point clouds are matched to a global tree map using the Delaunay triangularization as the representation format. Instead of point cloud based matching methods, we utilize a topology-based method. First, tree trunk positions are registered at a prior run done by a forest harvester. Second, the resulting map is Delaunay triangularized. Third, a local submap of the autonomous robot is registered, triangularized and matched using triangular similarity maximization to estimate the position of the robot. We test our method on a dataset accumulated from a forestry site at Lieksa, Finland. A total length of 200 m of harvester path was recorded by an industrial harvester with a 3D laser scanner and a geolocation unit fixed to the frame. Our experiments show a 12 cm s.t.d. in the location accuracy and with real-time data processing for speeds not exceeding 0.5 m/s. The accuracy and speed limit are realistic during forest operations.https://www.mdpi.com/2072-4292/12/11/1870roboticslocalizationdelaunay triangulationSLAMforest localization |
| spellingShingle | Qingqing Li Paavo Nevalainen Jorge Peña Queralta Jukka Heikkonen Tomi Westerlund Localization in Unstructured Environments: Towards Autonomous Robots in Forests with Delaunay Triangulation Remote Sensing robotics localization delaunay triangulation SLAM forest localization |
| title | Localization in Unstructured Environments: Towards Autonomous Robots in Forests with Delaunay Triangulation |
| title_full | Localization in Unstructured Environments: Towards Autonomous Robots in Forests with Delaunay Triangulation |
| title_fullStr | Localization in Unstructured Environments: Towards Autonomous Robots in Forests with Delaunay Triangulation |
| title_full_unstemmed | Localization in Unstructured Environments: Towards Autonomous Robots in Forests with Delaunay Triangulation |
| title_short | Localization in Unstructured Environments: Towards Autonomous Robots in Forests with Delaunay Triangulation |
| title_sort | localization in unstructured environments towards autonomous robots in forests with delaunay triangulation |
| topic | robotics localization delaunay triangulation SLAM forest localization |
| url | https://www.mdpi.com/2072-4292/12/11/1870 |
| work_keys_str_mv | AT qingqingli localizationinunstructuredenvironmentstowardsautonomousrobotsinforestswithdelaunaytriangulation AT paavonevalainen localizationinunstructuredenvironmentstowardsautonomousrobotsinforestswithdelaunaytriangulation AT jorgepenaqueralta localizationinunstructuredenvironmentstowardsautonomousrobotsinforestswithdelaunaytriangulation AT jukkaheikkonen localizationinunstructuredenvironmentstowardsautonomousrobotsinforestswithdelaunaytriangulation AT tomiwesterlund localizationinunstructuredenvironmentstowardsautonomousrobotsinforestswithdelaunaytriangulation |