EPSRC Centre for Doctoral Training in Agri-Food Robotics: AgriFoRwArdS - agri for web

Bradley Hurst

  • University of Lincoln in collaboration with Jersey Farmers' Union

Research Interests

Robotic hardware design, machine vision, control, and digital twin use in agri-robotics.

Papers and Presentations

  • Aardweg, C., Hurst, B., Osmond, W., Ravikanna, R., and Roberts-Elliot, L. (2021) Automated Counting of Grapes, AgriFoRwArdS CDT Annual Conference 2021, online.
  • Davy, J., Ghalmazan, A., Hurst, B., and Owen, A. (2021) Current Advances in Hardware for Agri-Food Manipulation- A review. ICRA Task-Informed Grasping Workshop – III, online. Watch here.

Extra-Curricular Activities

  • Member of the AgriFoRwArdS Advisory Board.

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.