Postgraduate Research Opportunity

Robot Skill Acquisition and Shared Autonomy


Title: Enabling robot skill acquisition and shared autonomy for undertaking complex tasks in industrial environments

Funding: Full time Home/EU fees and a stipend of £15,285 p.a.

Application deadline: 20th January 2021.

Start date: April 2021

Duration: 3 years (full time)

Location: Colchester Campus

Based in: School of Computer Science and Electronic Engineering


Removing personnel from hazardous environments encountered in industrial asset and maintenance settings require Robotic Autonomous Systems (RAS) equipped with advanced cognitive abilities to cope with highly unstructured environments and complex tasks.

Although Machine Learning has shown great promise in a broad range of commercial fields, achieving similar breakthroughs within inspection and maintenance applications has proven difficult.  This is mainly because RAS operating in such settings must rely on their on-board computational capacity; access to cloud infrastructure can be prohibitive either due to connectivity limitations or due to strict real-time processing requirements.

Thus, autonomy needs to be embodied within limited computing power.

The project

The focal points of this research will be to develop compute- and data-efficient imitation learning techniques. New imitation learning techniques will need to be explored for the robot to learn both what and how to imitate. To achieve this, few-shot and zero-shot learning techniques will be considered.

There will be two core research outputs:

  1. A holistic framework for skill transfer from human operators to RAS enabling shared autonomy facilitating further adoption of skill transfer algorithms based on imitation learning in service and industrial robotics.
  2. Algorithmic modules for data-efficient learning of navigation and/or manipulation behaviours. These modules will offer significant benefits in streamlining the robotic control algorithm design for robots operating in unstructured environments and undertaking complex tasks, significantly lowering the barriers for industrial RAS adoption.


This project is funded by Essex University, Lloyds Register Foundation and TWI.

The studentship includes:

  • The funding covers the cost of Home/EU tuition fees (further fee details). Non-EU students are welcome to apply, but the funding will only cover the cost of overseas tuition fees and the applicant need to self-fund their living cost for three years.
  • A standard tax-free stipend for three years equivalent to the Research Councils UK National Minimum Doctoral Stipend (£15,285 in 2020-21).
  • £2,500 training bursary via Proficio funding, which may be used to cover the cost of advanced skills training including conference attendance and travel.


The successful candidate would be expected to speak fluent English and meet our English Language requirements.


  • BSc or BEng degree (1st, 2:1, or equivalent) in computer science, or a related subject.
  • Strong analytical and mathematical skills.
  • Advanced knowledge of Python.
  • Experience in skill acquisition or modelling.
  • Experience in design and deployment of machine learning models.
  • Deep understanding of computer vision concepts.


  • Peer reviewed publication(s) in robotics control.
  • Experience in Tensorflow and/or Pytorch Machine Learning libraries.
  • Experience in inspection/maintenance robotic applications.
  • MSc degree (or equivalent) in computer science, or a related subject.

Note: Overseas applicants should also submit IELTS results (minimum 6.5) if applicable

How to apply

You can apply for this postgraduate research opportunity online.

Please upload your CV, personal statement, and transcripts of any undergraduate or masters programmes.

Instruction to applicants

When you apply online you will be prompted to fill out several boxes in the form:

  • For "Course title" please put "PhD Computer Science".
  • For "Proposed research topic or area of research" please put the title of this studentship (Enabling robot skill acquisition and shared autonomy for undertaking complex tasks in industrial environments) and the REF: (CSEE-Apr2021-01).

If you have any informal queries about this opportunity please email the lead supervisor, Dr Vishwanathan Mohan (lead supervisor) (, Dr Panos Chatzakos (, and Dr Anirban Chowdhury (