The progression of seaweed farming and cultivation to an industrial scale relies on automating its processes. Utilization of Autonomous Underwater Vehicle (AUV) can enable this process through their capacity to automate crop and structural inspections. However, the current bottleneck for their deployment is guaranteeing their safe navigation within the farms, necessitating an accurate online pose estimate and a map of the infrastructure for obstacle avoidance. To this end, in this paper, we propose a Simultaneous Localization and Mapping (SLAM) framework for AUV navigation through a kelp farm that provides structural and visual information of the state of the farm from Sidescan Sonar (SSS) and visual imagery. SSS is utilized for localizing the AUV with respect to the algae farm while also allowing for the mapping of the farm structure to account for possible disturbances. Key to our method is the modeling of the algae ropes as sequences of individual SSS detections. Relevant pose and position estimates are fused with captured imagery to produce a 3D mosaic of the farm for assessing algae health. We present the results of our approach on the tasks of SSS-based SLAM and 3D visual mosaicing from surveys both in simulation and on a real farm. Our evaluation confirms the effectiveness of the proposed approach, emphasizing its relevance for marine agriculture. ; För att nå storskalig algodling krävs automatisering av odlingsprocesserna. Användande av AUVer (Autonomous Underwater Vehicles) kan hjälpa automatiseringen genom inspektion av grödor eller infrastruktur. I nuläget är användbarheten av AUVer begränsad på grund av svårigheter i att garantera säker navigering inom odlingen, vilket bygger på en exakt uppkopplad riktnings-beräkning och en karta av infrastrukturen för att möjliggöra undvikande av hinder. För att lösa detta föreslår den här avhandlingen ett SLAM (Simultaneous Localization and Mapping) ramverk för AUV navigering av en sockertångsodling som ger strukturell och visuell ...
AUV SLAM for Algae Farm Inspection : 3D Mosaicing using Sonar-Based SLAM
2023-01-01
Hochschulschrift
Elektronische Ressource
Englisch
DDC: | 629 |
Reliability Of Inspection By SLAM
NTRS | 1988
|Underwater SLAM for Structured Environments Using an Imaging Sonar - Conclusion
Tema Archiv | 2010
|Underwater SLAM for Structured Environments Using an Imaging Sonar - Introduction
Tema Archiv | 2010
|