Core Project 4 aims at converting the collected data into robotic actions in the fields, exploiting digital avatars. Precise robotic weeding, for example, seeks to intervene in a minimally invasive way, reducing the amount of inputs such as herbicides. This project develops autonomous field aerial and ground robots that detect and identify individual plants, weed mapping the field to treat individual plants with the most appropriate intervention. The robots precisely apply nitrogen fertilizer enabled by digital avatars that predict the plant nutrient demand and probable losses in the field.
Research Videos
Image-based Plant Phenotyping
PhenoRob PhD Student Jan Weyler talks about his research within Core Project 4: Autonomous In-Field Intervention.
Precision Weed Management Enabled by Robotics and Robotics Vision
PhenoRob PhD Student Alireza Ahmadi talks about his research within Core Project 4: Autonomous In-Field Intervention.
Topic Introduction: UAV Remote Sensing for Improving Crop Models
PhenoRob PhD Student Jordan Bates talks about his research within Core Project 4: Autonomous In-Field Intervention.
AgroC Model Development and Parameterization to Characterize Plant-soil System
PhenoRob PhD Student Rajina Bajracharya talks about her research within Core Project 4: Autonomous In-Field Intervention.
Developing New Algorithms for Autonomous Decision Making to Optimize Robotic Farming
PhenoRob Junior Research Group Leader Marija Popovic talks about her research within Core Project 4: Autonomous In-Field Intervention.
Developing Weed Management Strategies for Autonomous Field Robots
PhenoRob PhD Student Marie Zingsheim talks about her research within Core Project 4: Autonomous In-Field Intervention.
Virtual Temporal Samples for RNNs: applied to semantic segmentation in agriculture
Normally, to train a recurrent neural network (RNN), labeled samples from a video (temporal) sequence are required which is laborious and has stymied work in this direction. By generating virtual temporal samples, we demonstrate that it is possible to train a lightweight RNN to perform semantic segmentation on two challenging agricultural datasets. full text in arxiv: https://arxiv.org/abs/2106.10118 check My GitHub for interesting ROS-based projects: https://github.com/alirezaahmadi
Talk by R. Sheikh on Gradient and Log-based Active Learning for Semantic Segmentation… (ICRA’20)
ICRA 2020 talk about the paper: R. Sheikh, A. Milioto, P. Lottes, C. Stachniss, M. Bennewitz, and T. Schultz, “Gradient and Log-based Active Learning for Semantic Segmentation of Crop and Weed for Agricultural Robots,” in Proceedings of the IEEE Int. Conf. on Robotics & Automation (ICRA), 2020. PDF: https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/sheikh2020icra.pdf
IROS’20: Domain Transfer for Semantic Segmentation of LiDAR Data using DNNs presented by J. Behley
F. Langer, A. Milioto, A. Haag, J. Behley, and C. Stachniss, “Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks,” in Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2020. Paper: https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/langer2020iros.pdf
ICRA’2020: Visual Servoing-based Navigation for Monitoring Row-Crop Fields
Visual Servoing-based Navigation for Monitoring Row-Crop Fields by A. Ahmadi et al. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2020.
ICRA’19: Robot Localization Based on Aerial Images for Precision Agriculture by Chebrolu et al.
Robot Localization Based on Aerial Images for Precision Agriculture Tasks in Crop Fields by N. Chebrolu, P. Lottes, T. Laebe, and C. Stachniss In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2019. Paper: http://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/chebrolu2019icra.pdf
Towards Autonomous Visual Navigation in Arable Fields
Rou pare can be found in Arxiv at: [Towards Autonomous Crop-Agnostic Visual Navigation in Arable Fields](https://arxiv.org/abs/2109.11936) You can find the implementation in : [visual-multi-crop-row-navigation](https://github.com/Agricultural-Robotics-Bonn/visual-multi-crop-row-navigation) more detail about our project BonnBot-I and Phenorob at: https://www.phenorob.de/ http://agrobotics.uni-bonn.de/
Adaptive-Resolution Field Mapping Using Gaussian Process Fusion With Integral Kernels by L.Jin et al
This short paper trailer is based on the following publication: L. Jin, J. Rückin, S. H. Kiss, T. Vidal-Calleja, and M. Popović, “Adaptive-Resolution Field Mapping Using Gaussian Process Fusion With Integral Kernels,” IEEE Robotics and Automation Letters, vol. 7, pp. 7471-7478, 2022. doi:10.1109/LRA.2022.3183797
Modeling Interactions of Agricultural Systems with the Terrestrial Water and Energy Cycle
Stefan Kollet, Professor of Integrated Modeling of Terrestrial Systems at the Institute of Bio- and Geosciences (IBG-3), Forschungszentrum Jülich and at the Institute of Geosciences, University of Bonn gives a PhenoRob Interdisciplinary Lecture [PILS] on modeling interactions of agricultural systems with the terrestrial water and energy cycle.
Large-eddy Simulation of Soil Moisture Heterogeneity Induced Secondary Circulation with Ambient Wind
This video is based on the following publication: L. Zhang, S. Poll, and S. Kollet, “Large-eddy Simulation of Soil Moisture Heterogeneity Induced Secondary Circulation with Ambient Winds,” Quarterly Journal of the Royal Meteorological Society, 2022. doi:10.5194/egusphere-egu22-5533
ICRA22: Adaptive Informative Path Planning Using Deep RL for UAV-based Active Sensing, Rückin et al.
Rückin J., Jin, L., and Popović, M., “Adaptive Informative Path Planning Using Deep RL for UAV-based Active Sensing,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2022. doi: ICRA46639.2022.9812025 PDF: https://arxiv.org/abs/2109.13570 Code: https://github.com/dmar-bonn/ipp-rl
Crop Agnostic Monitoring Using Deep Learning
Prof. Dr. Chris McCool is Professor of Applied Computer Vision and Robotic Vision, head of the Agricultural Robotics and Engineering department at the University of Bonn M. Halstead, A. Ahmadi, C. Smitt, O. Schmittmann, C. McCool, “Crop Agnostic Monitoring Driven by Deep Learning”, in Front. Plant Sci. 12:786702. doi: 10.3389/fpls.2021.786702
Graph-based View Motion Planning for Fruit Detection
This video demonstrates the work presented in our paper “Graph-based View Motion Planning for Fruit Detection” by T. Zaenker, J. Rückin, R. Menon, M. Popović, and M. Bennewitz, submitted to the International Conference on Intelligent Robots and Systems (IROS), 2023. Paper link: https://arxiv.org/abs/2303.03048 The view motion planner generates view pose candidates from targets to find new and cover partially detected fruits and connects them to create a graph of efficiently reachable and information-rich poses. That graph is searched to obtain the path with the highest estimated information gain and updated with the collected observations to adaptively target new fruit clusters. Therefore, it can explore segments in a structured way to optimize fruit coverage with a limited time budget. The video shows the planner applied in a commercial glasshouse environment and in a simulation designed to mimic our real-world setup, which we used to evaluate the performance. Code: https://github.com/Eruvae/view_motion_planner