Postgrad LIVE! Study Fairs

Southampton | Bristol

University of Leeds Featured PhD Programmes
Anglia Ruskin University Featured PhD Programmes
University of Portsmouth Featured PhD Programmes
Birkbeck, University of London Featured PhD Programmes
University of Bristol Featured PhD Programmes

Deep Learning based Robotic Motion Generation for Manipulating Granular and Viscous Materials

Project Description

Granular and viscous media are ubiquitous in our daily life, ranging from food like dough or beans to construction materials like concrete, soils, or sands. However, research in autonomous robotic manipulations of these materials is at its infancy.
One main challenge is the material deformation, due to the viscosity, granularity, and viscoelasticity. Traditional robotic motion planning is not scalable due to explicitly designed models. To autonomously plan motions in real-time, viscous or granular characteristics need to be considered. However, physics-based numerical modelling is usually considerably computational and impractical.
This project aims to develop Deep Learning based methods for robots to learn to manipulate such materials using tools, such as scoops, shovels, or trowels, autonomously. The proposed algorithms will primarily include two methods, namely Learning from Demonstration (LfD) and Reinforcement Learning (RL), that will build a model to map robot primitive motions, such as spreading, scooping, or reaching, to the deformation of materials observed from 3D cameras.
RL requires extremely large datasets, and is time-consuming to obtain enough data through trial & error operations. The project will start with a supervised manner by using LfD for robots to learn basic skills from human demonstrators. RL will continue from the learned model and explore optimal actions in a limited search space. Ultimately, the robot will be able to perform similar tasks through autonomous motion generation.
The following tasks are proposed and which are expected to be achievable within the 3.5 year duration of the project:

1. Developing LfD algorithms to allow robots to learn basic skills in simple scenarios and acquire initial datasets. The experiments will be carried out with an industrial robot.
2. Researching on 3D deformation and mapping to robot motion segments.
3. Developing RL algorithms by designing reward functions as performance metrics of corresponding actions and policies for optimal action selection.
4. Thorough experimental performance evaluation to benchmark its generalisation capability.


You should have obtained, or be about to obtain, a First or Upper Second Class UK Honours degree, or the equivalent qualifications gained outside the UK.

Applicants with a Lower Second Class degree will be considered if they also have a master’s degree. Applicants with a minimum Upper Second Class degree and significant relevant non-academic experience are encouraged to apply.

Funding Notes

Full awards, including the Tuition fee and maintenance stipend (Approx. £14,777 in 2018/19), are open to UK Nationals and EU students who can satisfy UK residency requirements. To be eligible for the full award, EU Nationals must have been in the UK for at least 3 years prior to the start of the course for which they are seeking funding, including for the purposes of full-time education.


Applications should be made online at:

Please note the following when completing your online application:

The Programme name is Doctor of Philosophy in Engineering with an October 2019 start date.

In the "Research proposal and Funding" section of your application, please specify the project title, supervisors of the project and copy the project description in the text box provided.

Please select “No, I am not self-funding my research” when asked whether you are self-funding your research.

Please quote “project ID” when asked "Please provide the name of the funding you are applying for".

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.