Postgraduate research project

Autonomous Unmanned Aerial Vehicle data analysis: is it the key to the many:1 ratio, or are we missing a step?

Funding
Fully funded (UK only)
Type of degree
Doctor of Philosophy
Entry requirements
2:1 honours degree View full entry requirements
Faculty graduate school
Faculty of Engineering and Physical Sciences
Closing date

About the project

Within the context of ground military operations, Unmanned Aerial Vehicles (UAVs) are commonly deployed for Intelligence, Surveillance, and Reconnaissance (ISR) missions. The decision-making that ensues based on UAV data can range from collecting further intelligence, to more extreme courses of action such as air strikes and weapon deployment.

The information gathered by UAV(s) has the potential to dynamically inform the development the goals and tasks of the military command team. There is a continuous drive within the military to reduce the human-UAV team to one human operator role, whilst increasing the number of UAVs deployed within the human-robot team. This goal is known as the many:1 ratio. 

The continuous developments of automated capabilities, such as automatic object detection and image classification, are thought to provide the functionality that will pave the way to this many:1 ratio.

Based on the identified gaps in the literature, and imminent technological advancements, you will investigate:

  • the short and long term capabilities of automation and implications on the role of the payload operator
  • the impact of different levels of automation on the payload operator’s performance, and whether automation errors can be identified and recovered from
  • the efficiency of implementing a user-centred payload operator interface on individual and team performance

You'll study the impact of automated capabilities on the role of the payload operator, and identify support mechanisms that keep the operator in the loop through the medium of a role-specific user interface.

This PhD will employ an approach with mixed methods, utilising relevant human factors methods depending on phase of the project, including but not limited to:

  • hierarchical task analysis
  • operator event sequence diagrams
  • interviews and observational data collection
  • user trials, and system-based methods 

You'll be expected to spend time at the University of Southampton and Thales sites in Reading and others depending on data collection opportunities.