My PhD Project: Machine Learning-based Weed Detection for Agricultural Robotics

• Embedded in: GALIRUMI EU HORIZON 2020 Project (Galileo-assisted robot to tackle the weed Rumex obtusifolius and increase the profitability and sustainability of dairy farming)

  • The main objective of GALIRUMI is to deliver robot weeding for herbicide-free weed control in dairy farming. Robotic weeding will reduce the environmental impact of dairy farming by eliminating herbicide use and reducing exposure of farm workers to herbicides. It will also remove an important obstacle for dairy farmers to switch to organic production, thereby contributing to an increase in production of organically produced milk and higher incomes for farmers. European GNSS

  • Official Galirumi Project Website

• My responsibilities:
  • Hardware: Weed perception sensor System design
  • Weed Detection Algorithms: Computer Vision and Deep Learning for 2D/3D data
  • Integration and Field testing: Applying robot platform in real world, together with the other European partners of the GALIRUMI project.

Publications

Real-Time Joint-Stem Prediction for Agricultural Robots in Grasslands Using Multi-Task Learning

Jiahao Li, Ronja Güldenring, Lazaros Nalpantidis. MDPI Agronomy, 2023

RumexWeeds: A Grassland Dataset for Agricultural Robotics

Ronja Güldenring, Frits van Evert, Lazaros Nalpantidis. Journal of Field Robotics, 2023

Lightweight Monocular Depth Estimation through Guided Decoding

Michael Rudolph, Youssef Dawoud, Ronja Güldenring, Lazaros Nalpantidis, Vasileios Belagiannis. International Conference on Robotics and Automation (ICRA), 2022

Self-supervised contrastive learning on agricultural images

Ronja Güldenring, Lazaros Nalpantidis. Journal: Computers and Electronics in Agriculture, 2021

Few-leaf Learning: Weed Segmentation in Grasslands (Finalist for the Best Paper Award on Agri-Robotics)

Ronja Güldenring, Evangelos Boukas, Ole Ravn, Lazaros Nalpantidis. International Conference on Intelligent Robots and Systems, IROS 2021

Learning Local Planners for Human-aware Navigation in Indoor Environments

Ronja Güldenring, Michael Görner, Norman Hendrich, Niels Jul Jacobsen, and Jianwei Zhang. International Conference on Intelligent Robots and Systems, IROS 2020

Teaching

• Co-supervision of Master Thesis “Multi-task Learning: Weed Detection and Joint Stem Detection for Autonomous Agricultural Robots” by Jiahao Li, 2023
• Co-supervision of Special Course “Object Detection on RGB-D Images from Agricultural Environments” by Bence Bejczy, 2021
• Fall Semester 2021: TA at Software Frameworks for Autonomous Systems
• Co-supervision of Master Thesis “Real-time Object Detection using Deep Learning on Constrained Devices” by Serdar Tunckol, 2021
• Co-supervision of Bachelor Project “Software and hardware integration on Husky UGV in cooperation with Galirumi project” by Bastian Munch Kjøller, Rares-Victor Botis and Anders Skott Lind, 2021
• Co-supervision of Special Course “Specialkursus, Synthesis: Evaluation of 3D sensors in indoor and outdoor environments” by Carla Christina Salazar Navalon, 2020
• Fall Semester 2020: TA at Software Frameworks for Autonomous Systems