Autonomous agricultural mobile robots have seen increasingly more use for multiple tasks in recent years. The autonomous behaviour can be better accomplished if the robot is able to localize itself and build a reliable map of its surrounding environment. The large size of agricultural environments requires a more compact map representation to reduce memory and processing requirements, and using topological maps in that environments is a good option in that direction. This paper proposes a novel application of topological maps with a focus on orchards, where the trees with their distinctive features serve as the nodes, and the neighborhoods of the trees serve as the edges for the topological maps. We showcase this new topological map approach using 3D LiDAR data collected in an orchard, and we also present preliminary results showing that Iterative Closest Point (ICP) approach can be effectively used to recognize the nodes of the topological map of the orchard.
LiDAR-Based Topological Mapping of Orchard Environments
Lect. Notes in Networks, Syst.
Iberian Robotics conference ; 2022 ; Zaragoza, Spain November 23, 2022 - November 25, 2022
19.11.2022
13 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Unmanned aerial vehicle for orchard surveying and mapping
Europäisches Patentamt | 2020
|Localization and mapping performance of two LiDAR systems in unstructured environments
British Library Conference Proceedings | 2019
|