Karoline’s research interests include, 3D perception, sensor fusion, mobile autonomy, and long-term autonomy.
- Heiwolt, K., Mandil, W., Cielniak, G. and Hanheide, M. (2020) ‘Automated Topological Mapping for Agricultural Robots‘, UKRAS20 Conference: Robots into the real world Proceedings.
- Oppermann, L., Hirzel, S., Güldner, A., Heiwolt, K., Krassowski, J., Schade, U., Lange, C. and Prinz, W. (2021) ‘Finding and analysing energy research funding data: The EnArgus system‘, Energy and AI.
- Heiwolt, K., Duckett, T., and Cielniak, G. (2021) ‘Deep semantic segmentation of 3D plant point clouds‘, Annual Conference Towards Autonomous Robotic Systems 2021.
- Heiwolt, K., Öztireli, C., & Cielniak, G. (2023) Statistical shape representations for temporal registration of plant components in 3D. IEEE International Conference on Robotics and Automation (ICRA), London, United Kingdom, 2023, pp. 9587-9593.
- Lincoln Conference on Intelligent Robots and Systems 2020 (October 2020): Semantic Segmentation of Plant Leaves from 3D Point Clouds using Deep Learning.
- Lincoln Agri-Robotics Mini Conference 2020 (December 2020): Semantic-assisted 4D crop mapping.
- University of Lincoln Postgraduate Research Showcase 2021 (February 2021): 4D Crop Modelling.
- AgriFoRwArdS CDT Annual Conference 2021 (July 2021): Using deep learning for semantic segmentation of 3D plant point clouds.
- AgriFoRwArdS CDT Annual Conference 2021 (July 2021): RAS Counter: Non-invasive yield prediction for vineyards
- Towards Autonomous Robotic Systems Conference 2021 (September 2021): Deep Semantic Segmentation of 3D plant point clouds.
- Joint Robotics and Autonomous Systems CDT Conference 2021 (October 2021): Deep Semantic Segmentation of 3D plant point clouds.
- 7th International Plant Phenotyping Symposium (IPPS) (September 2022): Temporal Registration of Plant Parts in 3Dc
- International Conference on Robotics and Automation (ICRA) 2023 (June 2023): Statistical shape representations for temporal registration of plant components in 3D.
- The Towards Autonomous Robots and Systems (TAROS) Conference 2023 / CDT Annual Conference / Joint Robotics CDT Conference (September 2023): Statistical shape representations for temporal registration of plant components in 3D.
- Member of the AgriFoRwArdS CDT Drink Outside the Box Organisation Committee.
- Member of the AgriFoRwArdS CDT Advisory Board.
- Member of the AgriFoRwArdS CDT Equality, Diversity and Inclusion Panel.
- Cohort 1 representative on the CDT Student Panel.
- Took part in the AgriFoRwArdS Summer School 2021 resulting in co-authored presentation at the AgriFoRwArdS CDT Annual Conference 2021: RAS Counter: Non-invasive yield prediction for vineyards (in collaboration with Harry Rogers, Ni Wang, Obinamuni De Silva, Huijiang Wang).
- Awarded Best Student Presentation at the AgriFoRwArdS CDT Annual Conference 2021 for ‘Using deep learning for semantic segmentation of 3D plant point clouds‘.
- Member of the discussion panel for Tony Pridmore’s Keynote presentation at the AgriFoRwArdS CDT Annual Conference 2021, ‘Plant Phenotyping: Getting to the root of the problem’.
- Represented the CDT at the school outreach University of Lincoln British Science Week event 2022.
- Member of AgriFoRwArdS CDT Annual Conference 2022 discussion panel.
- Took part in the L-CAS Summer Undergraduate Student Project Scheme 2022
My name is Karoline, I am from Germany, and I joined the CDT in September 2019. I have a background in neuroscience and robotics and I am especially interested in the research areas of 3D perception, sensor fusion, and mobile autonomy. I chose to join this CDT because the development of robots for agricultural applications offers many interesting real-world challenges that could have a great positive impact on a sustainable global food chain. I am currently working on my PhD with Grzegorz Cielniak at the University of Lincoln alongside a brilliant cohort of fellow PhD students with different backgrounds.
Semantic Segmentation of Plant Leaves from 3D Point Clouds using Deep Learning
In this project we aim to address the problem of semantically segmenting plant leaves from the background and other plant organs in three-dimensional point clouds of individual plants captured by RGBD sensors. Previous work utilises explicit prior knowledge about the expected plant morphology and sensor set-up, as well as manually tuned parameters to achieve this segmentation. Here we propose to train a supervised machine learning algorithm to predict the segmentation output directly from point cloud data and minimise the necessary user input.
4D Scene Analysis for Autonomous Operation of Mobile Robots on Farms
This research addresses challenges in 4D scene analysis for autonomous operation of mobile robots on farms. The deployment of agricultural robots will increase sustainability and support precision farming operations tuned to needs of individual plants. This research will enable robots to maintain precise 3D representations of uncertain and highly variable farm environments together with their semantics in order to safely traverse the farm autonomously, as well as to reconstruct structural representations of the crop. Additionally, registering these representations over time would allow for sustained crop monitoring and provide insight into spatio-temporal dynamics and interactions between the plants and environmental factors.