Publications

• Foster, J., Gudelis, M., Ghalamzan Esfahani, A. (2022) Robotic Perception in Agri-food Manipulation: A Review. Task-Informed Grasping: Agri-Food manipulation (TIG-III) workshop (Aug 2022).
• Foster, J., & Brintrup, A. (2023) Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization, Preprint.
• Foster, J., & Brintrup, A. (2023) Aiding Food Security and Sustainability Efforts Through Graph Neural Network-Based Consumer Food Ingredient Detection and Substitution, Scientific reports, 13(18809).
• Schoepf, S., Foster, J., & Brintrup, A. (2023) Identifying contributors to supply chain outcomes in a multi-echelon setting: a decentralised approach, arXiv pre-print.
• Foster, J., Schoepf, S., & Brintrup, A. (2023) Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening, arXiv pre-print.
• Foster, J., Schoepf, S., & Brintrup, A. (2024) Loss-Free Machine Unlearning, arXiv pre-print.
• Schoepf, S., Foster, J., & Brintrup, A. (2024) Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening, arXiv pre-print.
• Foster, J., Fogarty, K., Schoepf, S., Oztireli, A.C., & Brintrup, A. (2024) Zero-Shot Machine Unlearning at Scale via Lipschitz Regularization, arXiv pre-print.
• Schoepf, S., Foster, J., & Brintrup, A. (2024) Potion: Towards Poison Unlearning, arXiv pre-print.

Presentations

• “Perception in Agri-food Manipulation: A Review” (oral) – International Conference on Robotics and Automation (ICRA) Task-Informed Grasping Workshop – III [May 2021] – Online.
• “Visual Serving for Human Tracking and Counting” (oral) – AgriFoRwArdS CDT Summer School 2021 [June 2021] – Online.
• “Visual Serving for Human Tracking and Counting” (oral) – AgriFoRwArdS CDT Annual Conference 2021 [July 2021] – Online.
• “Uncertainty-Guided Collaboration for Multi-Agent Precision Agriculture” (oral) – University of Cambridge Corpus Christie College Dyson Farming Industry visit [May 2022] – Cambridge, UK.
• “Uncertainty-Guided Collaboration in Multi-Agent Deep Reinforcement Learning” (oral) – AgriFoRwArdS CDT Annual Conference 2022 [June 2022] – Lincoln, UK.
• “Uncertainty-Guided Collaboration for Multi-Agent Precision Agriculture” (oral) – Dyson Farming industry visit [July 2022] – Lincoln, UK.
• “Poisson Distributions: Fisheries for the Future” (oral) – AgriFoRwArdS CDT Summer School 2022 [July 2022] – Norwich, UK.
• “Does Baxter Dream of Electric Beans?” (oral) – AgriFoRwArdS CDT Summer School 2023 [March 2023] – Lincoln, UK.
• “Can AI’s Learn From Each Other?” (oral) – University of Cambridge Corpus Christi College Engineering Masterclass [May 2023] – Cambridge, UK.
• “Towards Robust Continual Learning with Bayesian Adaptive Moment Estimation” (oral) – Dyson Farming industry visit [May 2023] – Lincoln, UK.
• “Variational collaboration: How, when, and from whom to learn in a complex supply chain network” (oral) – Alan Turing Workshop on Firm-level Supply Network Reconstruction [July 2023] – Cambridge, UK.
• “Uncertainty-Guided Multi-Agent Continual Learning for Food Supply-Chain Knowledge Graph Completion” (poster) – Towards Autonomous Robotic Systems (TAROS) 2023 / AgriFoRwArdS CDT Annual Conference 2023 / Joint Robotics CDT Annual Conference 2023 [September 2023] – Cambridge, UK.
• “Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening” (poster) – The 38th Annual AAAI Conference on Artificial Intelligence (AAAI-24) [February 2024] – Vancouver, Canada.
• “Loss-Free Machine Unlearning” (poster) – International Conference on Learning Representations (ICLR) 2024 [May 2024] – Vienna, Austria.
• “Exploration of LLM-Enhanced State-Machine function-calls for Planning Robot Actions” (oral) – AgriFoRwArdS CDT Summer School: Robotic Phenotyping [July 2024] – Wageningen, The Netherlands.
• “Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening” (poster) – AgriFoRwArdS CDT Summer School: Robotic Phenotyping [July 2024] – Wageningen, The Netherlands.

Other Activities

• Member of the AgriFoRwArdS CDT Advisory Board (March 2021 to present).
• Member of the AgriFoRwArdS CDT Student Panel (March 2022 to present).
• Co-supervised 6 Mathematics PhD students across UK universities for a research project with the Heilbronn Institute for Mathematical Research.
• NCNR project – robotic sort and segmentation of nuclear material.
• Entered the PUB.R Competition at the International Conference on Robotics and Automation (ICRA) 2023.
• Discussion Panel member at the AgriFoRwArdS CDT Open Day for potential students – Discussion topic: What is it like to be an AgriFoRwArdS student [March 2022].
• Alan Turing Institute Enrichment Scheme (Oct 2023).

About me

Hi I’m Jack, I started out studying Computer Science at Keele before moving to the University of Birmingham to complete my master’s in Robotics. After that, I joined the CDT in 2020. So far, I have really enjoyed working with the cohort, its far more engaging and fun to attend talks or training days with a big group of people you know and are friends with. I’m mainly interested in the autonomy and decision making behind robotics, particularly long-term autonomy, and anything to do with neural nets, genetic algorithms, or multi-agent systems. In my spare time, I enjoy playing the guitar, photography, or nipping into town on the electric scooters dotted around Cambridge!

MSc Project

Lifelong Learning for Sensor-based Precipitation Regression

This project seeks to improve the crop yield of a small farm by optimising the soil-moisture content via precipitation regression. A CNN or RNN, will use wind speed/direction, humidity, temperature, and air pressure to predict future precipitation. Once the network is trained, lifelong learning will be applied to improve the network’s performance when localised within the small farm, using data collected in real-time from a range of sensors and an Arduino. The future precipitation will be combined with the current moisture levels to create predictions on whether the crop requires watering today.

PhD Project

Collaborative Lifelong Learning for Robust Site-Specific Crop Management

Farms are not, in general, homogeneous. As such, the farm-wide treatment and maintenance of crops leads to sub-optimal crop yield or quality. By taking a finer grained approach, crop would receive the necessary care for their needs, rather than the average need of the farm. However, it is impractical for human experts to manually analyse the needs of crop on such a granular scale.

To address this need, we first propose novel machine learning approaches for crop care, such as soil-moisture optimisation via LSTM neural networks. To collect real-time data of the farm a custom sensor system will be developed and several of them deployed to collect relevant environmental data from a small region of the farm.

Finally, to improve the long-term autonomy and overall performance of an agent, a collaborative multi-agent system will be constructed to facilitate the lifelong learning from both an agent’s environment, but also from other agents. This will improve the robustness and performance of agents over long periods of time.

Jack’s PhD project is being carried out in collaboration with Dyson Farming, under the primary supervision of Dr Alexandra Brintrup