🎓 Discover PhD and Master's programmes at leading universities worldwide — Sign up free to save searches and get email alerts
UNI

Foundation-model-guided world models and predictive control for autonomous remote handling in extreme environments

✓ Fully Funded 🎓 Engineering 🎓 Mechatronics 🎓 Robotics machine learning predictive control foundation models world models autonomous robotics robotic manipulation remote handling extreme environments

Explore autonomous robotic manipulation using foundation models to improve decision-making under uncertainty. Engage with cutting-edge predictive control and world model methods for hazardous, unstructured environments.

AI-generated overview

🌍
Why This Research Matters

This research advances autonomous robotic capabilities for safe and robust operation in extreme environments like fusion and nuclear plants, reducing human risk and enabling critical industrial tasks. Enhancing decision-making under uncertainty promises practical and academic innovation in embodied AI.

Robotics Robotic Manipulation data-driven control foundational models

Project Description

Project Overview

This project seeks to develop intelligent robotic systems for autonomous remote handling in extreme and hazardous environments such as fusion and nuclear facilities. It will explore how foundation models can guide world models and predictive control to improve decision-making, robustness, and adaptability when sensing is limited and uncertainty is high.

What You Will Do

The candidate will work with multidisciplinary research teams to combine learning-based prediction, model predictive control, and semantic priors from foundation models. The candidate will develop methods enabling robots to reason about dynamics, task constraints, and safe action selection for complex manipulation tasks.

Expected Outcomes

The research will contribute to next-generation autonomous robotic systems suited for challenging industrial applications, delivering advancements in embodied AI and autonomous robotics with both academic publications and practical implementations.

Why This Matters

Autonomous robotic handling in hazardous environments significantly reduces human risk and improves operational efficiency. By leveraging foundation models, this work aims to enhance robot capabilities in uncertain and unstructured environments, addressing critical challenges in fusion and nuclear sectors.

Entry Requirements

A strong background in robotics, control, artificial intelligence, or closely related disciplines. A master's degree or equivalent in engineering, computer science, physics, or mechatronics. Experience in Python programming and machine learning frameworks is desirable. Interest in model predictive control, world models, or learning-based robotics. Prior research or experimental experience is advantageous.

How to Apply

Apply via The University of Sheffield postgraduate application portal selecting the UKAEA Fusion Engineering CDT option: https://www.sheffield.ac.uk/postgraduate/phd/apply/applying. For more information, contact the supervisor at a.ghalamzan@sheffield.com or the CDT at hello@fusion-engineering-cdt.ac.uk.

Eligibility

UK/Home
EU
International

Supervisor Profile

PA
Prof Amir Ghalamzan
University of Sheffield
1342 Citations
22 h-index
Google Scholar

Prof Amir Ghalamzan is an Associate Professor at the University of Sheffield specializing in robotics, robotic manipulation, data-driven control, and foundational models. His research integrates machine learning and control techniques to advance autonomous robotic systems. He collaborates with leading robotics labs and has a solid record of impactful publications.

Key Publications

2023 99 citations
Tactile-sensing technologies: Trends, challenges and outlook in agri-food manipulation
2024 82 citations
Towards autonomous selective harvesting: A review of robot perception, robot design, motion planning and control
2017 75 citations
Guiding trajectory optimization by demonstrated distributions
2023 68 citations
Modular autonomous strawberry picking robotic system
2018 68 citations
Robot learning from demonstrations: Emulation learning in environments with moving obstacles

Research Contributions

Development and review of tactile-sensing technologies applicable to agri-food manipulation.
Advances understanding and capability of robotic systems to handle delicate agricultural products, improving automation in food production.
Comprehensive review and analysis of autonomous selective harvesting including robot perception, design, motion planning and control.
Supports progress toward fully autonomous robotic harvesting, potentially reducing labor costs and increasing efficiency in agriculture.
Introduction of guided trajectory optimization methods based on demonstrated distributions.
Facilitates more efficient robot motion planning by leveraging demonstration data, improving learning and execution of complex tasks.
Design and implementation of a modular autonomous robotic system for strawberry picking.
Demonstrates practical applications of robotics in precision agriculture, enabling scalable automation solutions for fruit harvesting.

Related Opportunities

Multi-arm and Constrained Manipulation in Robotics
The University of Manchester Dr Murilo Marinho 🎓 Robotics

Explore how to safely control multiple robotic arms performing dexterous manipulation in constrained and changing environments. Develop and integrate model-based and data-driven methods to enhance robot adaptability and…

This research addresses critical safety challenges in robotic manipulation within constrained and dynamic environments such as surgical or …

877+ citations · h17
Robotics Human-Robot Interaction Surgical Robots
Sports Acoustics: Impact Sound Analysis in Cricket, Golf, Baseball and Tennis
University of Southampton Dr. Giacomo Squicciarini 🎓 Acoustics 🎓 Engineering

Explore how the sounds of ball impacts reveal shot quality in four major sports. Analyze acoustic signals combined with physics models and machine learning to create new performance metrics. Gain experience with Hawk-Ey…

This research unravels the acoustic signatures behind elite athletes' intuitive judgements, providing a scientific basis to a traditionally…

1613+ citations · h23
Noise and vibration railway noise acoustics
Multi-Scale Computational Framework for Charge Transport and Thermoelectric Properties in Self-Assembled Monolayer Molecular Junctions
Maynooth University Prof. Pierre Cazade 🎓 Biochemistry 🎓 Chemistry Deadline: 01 May 2026

Develop models to predict charge transport and thermoelectric behavior in molecular junctions. Explore nanoscale thermoelectrics for waste heat recovery. Collaborate internationally to bridge molecular design and device…

This research aims to enable rational design of molecular electronic devices, improving nanoscale energy harvesting technologies such as mo…

Charge Transport Thermoelectric Properties Molecular Junctions Self-Assembled Monolayers
Synergistic acoustic-electrostatic-inertial separation of microplastics from blood: concept and development
Monash University Malaysia Dr Ajay Achath Mohanan 🎓 Biomedical Engineering 🎓 Engineering

Investigate novel separation techniques combining acoustic, electrostatic, and inertial forces to remove microplastics from blood. Develop innovative biomedical devices with potential clinical applications to reduce hea…

This research aims to develop clinically applicable devices to separate microplastics from blood, potentially mitigating associated health …

154+ citations · h7
Microplastics Acoustic Separation Electrostatic Separation Microfluidics