EPSRC Centre for Doctoral Training in Agri-Food Robotics: AgriFoRwArdS - Elijah Almanzor

Elijah Almanzor

  • University of Cambridge in collaboration with Jersey Farmers' Union

Research Interests

Intelligent soft robots for soft/delicate harvest picking.

Presentations

  • AgriFoRwArdS CDT Annual Conference (2021): Visual perception for harvesting grapes.

Other Activities and Outputs

  • Took part in the AgriFoRwArdS Summer School 2021 resulting in a co-authored presentation at the AgriFoRwArdS CDT Annual Conference 2021: Visual perception for harvesting grapes (in collaboration with Joshua Davy, Madeleine Darbyshire, Willow Mandil, Jerry Shi).

About me

I have always been interested in robotics and completed a Mechanical Engineering degree. I am currently very interested in designing more intelligent soft robots for soft/delicate harvest picking.

MSc Project

Deep Reinforcement Learning for Control of Robotic Manipulators for Grasping Strawberries in Simulation

The agricultural sector is under pressure from the exponential growth of human population, climate change and aging labour work-forces. Robotics and Autonomous Systems are therefore being researched as a possible solution to ensuring a sustainable global-food chain for the future. Intelligent robotic manipulators could be used to assist workers in operations such as harvesting, precision weeding and food handling in warehouses. This project will therefore look at the use of the Twin-Delayed Deep Deterministic Policy Gradient (TD3) Deep Reinforcement Learning (DRL) algorithm as an end-to-end control mechanism for the self-robotic learning of a policy capable of manipulating and handling randomised strawberry clusters, as harvesting strawberries require dexterous movements subject to unstructured configurations and chaotic dynamics.

Various research have already implemented DRL with robotic manipulators, however there are sparse works on the applications of DRL in the domain of agriculture. TD3 requires no predefined labelled training dataset as the low-level joint space control policy is learnt via agent interactions with the environment through hand-crafted reward functions. The project aims to learn the policy in simulation followed by transference to a real environment with additional research on reducing the reality-simulation gap.

PhD Project

Automation and Robotization of the Planting of the ‘Jersey Royal’ Potatoes

The agricultural industry in Jersey faces a considerable technological challenge in the planting of their main product, Jersey Royal new potatoes, due to the lack of available manual labour from Brexit, increase in wages as well as the Covid19 pandemic.

Research into robotic technologies for low-cost rapid handling of the seed potatoes from storage to soil is explored in the project. Low-cost robotic arms with suitable grasping end-effectors and machine intelligence will be developed and tested with reasonable speed, accuracy, and reliability. Exploration of minimalistic solutions for locomotion such that the planting robot can be mobilised will also be undertaken.