Ahmadi, Alireza: Precision Weed Management Enabled by Robotic and Robotics Vision. - Bonn, 2025. - Dissertation, Rheinische Friedrich-Wilhelms-Universität Bonn.
Online-Ausgabe in bonndoc: https://nbn-resolving.org/urn:nbn:de:hbz:5-82614
@phdthesis{handle:20.500.11811/13077,
urn: https://nbn-resolving.org/urn:nbn:de:hbz:5-82614,
author = {{Alireza Ahmadi}},
title = {Precision Weed Management Enabled by Robotic and Robotics Vision},
school = {Rheinische Friedrich-Wilhelms-Universität Bonn},
year = 2025,
month = may,

note = {In recent decades, traditional crop and weed management has heavily relied on herbicides and mechanical weeding. These methods have caused significant environmental and agricultural challenges. Over 2 million tons of herbicides are used annually globally, raising concerns about food safety, environmental harm, and human health risks. Weed resistance to herbicides is a growing problem, with over 500 cases reported worldwide. Meanwhile, consumer demand for organic, chemical-free food pushes farmers to reduce agrochemical use while maintaining high yields. This situation highlights the urgent need for innovative, sustainable farming solutions.
This thesis explores precision agriculture technologies, focusing on biodiversityaware robotic systems for plant-level weeding in arable farms. We tried to address the limitations of conventional weed management, by proposing advanced robotic solutions using machine vision, deep learning, and autonomous navigation for sustainable and targeted interventions in the real world. The core innovation is centered on developing a novel precision weeding and crop-monitoring robot platform called BonnBot-I. This platform is equipped with advanced sensors and computational tools to conduct autonomous operations in diverse arable farming environments.
One of the main topics in agricultural autonomy is performing reliable autonomous navigation in cluttered farming environments with poor global localization accessibility like GPS. Considering the fact that still a large portion of the arable farms are not seeded using GPS-guided systems, integration of local observations-based navigation methods could relieve environmentally posed challenges for robots to achieve reliable navigation and minimize crop damage. Hence, we introduce a vision-based navigation approach that guides the BonnBot-I through rows of crops with different canopy types and cultivars relying only on the real-time camera data.
A central aim of this thesis is to establish a robust framework for developing robots capable of conducting precise, plant-specific weed and crop management in arable farms that feature a variety of cultivars and weed densities. Hence an accurate crop and weed monitoring system is needed to shape weeding strategies based on the presence of plant instances. To fulfill this requirement, BonnBot-I incorporates cutting-edge instance-based semantic segmentation and trackingvia-segmentation methods. Our approach enables the identification and tracking of individual plants in real time, categorizing them by species, size, growth stage, and precise location under actual field conditions. These advanced systems allow us to implement eco-friendly weeding strategies tailored to specific plants in real agricultural settings. This innovation enables plant-level prioritization and the execution of targeted interventions based on each plants unique needs using BonnBot-I’s novel weeding tool. BonnBot-Iis equipped with a specialized weeding tool, including independently controllable linear axes and spray nozzles, facilitating these selective interventions. This design enables BonnBot-I to perform highly precise applications, significantly reducing the need for agrochemicals and minimizing the environmental impact associated with traditional broadcast methods.
In conclusion, this thesis demonstrates how robotics and artificial intelligence (AI) can profoundly reshape the future of crop management through innovative biodiversity-aware and plant-specific weeding practices. By integrating advanced machine vision, deep learning, and autonomous navigation, BonnBot-I provides a unique approach to sustainable agriculture that respects biodiversity and prioritizes environmental health. Unlike traditional weeding methods that rely on uniform herbicide application or mechanical removal, which often harm surrounding crops and ecosystems, BonnBot-I offers precision interventions tailored to individual plants.},

url = {https://hdl.handle.net/20.500.11811/13077}
}

Die folgenden Nutzungsbestimmungen sind mit dieser Ressource verbunden:

InCopyright