Bradley Hurst
Research Interests
Bradley’s research interests include, robotic hardware design, machine vision, control, and digital twin use in agri-robotics.
Publications
- Hurst, B., Bellotto, N., & Bosilj, P. (2023) An assessment of self-supervised learning for data efficient potato instance segmentation, Towards Autonomous Robotic Systems. TAROS 2023. Lecture Notes in Computer Science, vol 14136. Springer, Cham.
Presentations
- “Automated Counting of Grapes” (oral) – AgriFoRwArdS CDT Summer School 2021 [June 2021] – Online.
- “Automated Counting of Grapes” (oral) – AgriFoRwArdS CDT Annual Conference 2021 [July 2021] – Online.
- “Fish Sorting: A whatsinyour.net solution” (oral) – AgriFoRwArdS CDT Summer School 2022 [July 2022] – Norwich, UK.
- “Team Toast” (oral) – AgriFoRwArdS CDT Summer School 2023 [March 2023] – Lincoln, UK.
- “Title Unknown” (oral) – Lincoln Centre for Autonomous Systems (L-CAS) General Meeting [September 2023] – Online.
- “An assessment of self-supervised learning for data efficient potato instance segmentation” (oral) – Towards Autonomous Robotic Systems (TAROS) 2023 / AgriFoRwArdS CDT Annual Conference 2023 / Joint Robotics CDT Annual Conference 2023 [September 2023] – Cambridge, UK.
- “Enhancing Instance Segmentation with MultitaskLearning: Integrating Mask R-CNN with Self Supervise Tasks” (poster) – Towards Autonomous Robotic Systems (TAROS) 2023 / AgriFoRwArdS CDT Annual Conference 2023 / Joint Robotics CDT Annual Conference 2023 [September 2023] – Cambridge, UK.
- “Domain Generalisation for plant/weed detection” (oral) – AgriFoRwArdS CDT Summer School: Robotic Phenotyping [July 2024] – Wageningen, The Netherlands.
- “Pseudo Labelling for Improved Segmentation of Densely Clustered Potato Tubers in Storage” (poster) – AgriFoRwArdS CDT Summer School: Robotic Phenotyping [July 2024] – Wageningen, The Netherlands.
Other Activities
- Member of the AgriFoRwArdS Advisory Board (March 2021 to present).
- Member of the AgriFoRwArdS CDT Student Panel (March 2022 to present).
- Represented the AgriFoRwArdS CDT on the University of Lincoln stand at the Fresh Produce Consortium Festivals Event 2021 – showcasing research to the public, prospective students, and industry collaborators [November 2021] – Lincoln, UK.
- Discussion Panel member at the AgriFoRwArdS CDT Annual Conference 2022 – Discussion topic: AgriFoRwArdS PhD research progress [July 2022].
About me
I previously completed a graduate scheme with Siemens (SITL), where I obtained a Meng in Mechanical Engineering and Control Systems. I am hoping to be able to apply this experience to automation and robotics to contribute towards developing a more sustainable future. I am particularly interested in agri-robotics, systems integration, and manipulation and soft robotics.
In my spare time I like to go bouldering, and occasionally enjoy attending my local hack space.
MSc Project
3D image segmentation of potato sprouts in a controlled environment
PhD Project
Active Robot Perception for Automated Potato Planting
30k-40k tonnes of Jersey Royal new potatoes are produced annually in the Island of Jersey, and up to 1000 tonnes are exported daily out of the island. The industry faces a considerable technological challenge in the planting of their main product, Jersey Royal new potatoes, because of the lack of labourers and the increase of wages, but the automation of the processes is not trivial due to the difficult physical environmental conditions on sites as well as the cost constraints.
This project therefore investigates new active robot perception solutions for the automation of potato planting at Jersey Farms. Technologies for low-cost sensing and quality control of seed potatoes from the storage will be explored, including a camera on a robot manipulator to identify and estimate the pose of potatoes that need to be handled by the grasping end-effector. Opportune software solutions will be designed and implemented in the robot sensing system to be reasonably accurate and suitable for real outdoor scenarios. The project will also explore the possibility to combine visual and tactile information (i.e. camera + touch sensor) to improve the detection and handling of potatoes in crates. Finally, the perception system will be integrated to the final mobile robot manipulator for planting the selected potatoes.
Bradley’s PhD project is being carried out in collaboration with Jersey Farmers’ Union, under the primary supervision of Dr Petra Bosilj.