Safe Human-Robot Interaction for Offshore Inspection

The goal of this project is to enable robots to safely and effectively collaborate with humans in teams through grounded human-robot interaction for offshore inspection.
Description of the Project: 

**Note: Project availability subject to collaboration agreement being signed**

This exciting PhD project is sponsored by Total where you will work on human-robot interaction with their latest robot for inspection of offshore oil and gas platforms.

For humans to collaborate effectively and safely on shared tasks in human-machine teams, they need to be able to develop a trusting, working relationship through interaction, dialogue and speech. To do this, partners need to have a mutual understanding of the world and the task at hand.  As robotic systems become more human-like and autonomous, this relationship with humans becomes more important; because once established, human-machine teams will need to be more efficient and more robust to be able to safely handle problematic situations, for example, when failure occurs, be it on the system or human side.

 You will investigate interaction techniques to address some of the following research questions, firstly in simulation then with the real robot. Example topics include:

  1. Techniques for vision-and-language navigation, following natural language instructions situated in a dynamic, shared view of the world.
  2. Techniques to enable a human operator to teach the robot by incrementally building common ground through situated human-robot dialogue.
  3. Techniques to explain the robot’s actions to increase transparency and thus adoption.
  4. Voice-enabled search over logs of information gathered from the robot (images/sensor output) to inform inspection and manage operator information overload.
Resources required: 
Data and access to robot
Project number: 
600004
First Supervisor: 
University: 
Heriot-Watt University
Essential skills and knowledge: 
Machine learning
Desirable skills and knowledge: 
ROS, interest in dialogue and NLP
References: 

Misra, D. K., Langford, J., & Artzi, Y. (2017). Mapping Instructions and Visual Observations to Actions with Reinforcement Learning. https://arxiv.org/pdf/1704.08795.pdf

 

https://visualqa.org/

Industry placement details: 
Industrial placement will be located within TEPUK GRC R&D centre in Aberdeen with opportunity to work on TEPUK production sites (onshore and offshore). Total E&P UK Limited (TEPUK) (https://www.total.co.uk/) is one of the largest exploration and production subsidiaries of the Total Group, a global energy business with operations in more than 130 countries with over 100,000 employees. The Total Group is a global integrated energy producer and provider, a leading international oil and gas company, a major player In solar energy with SunPower and Total Solar. Headquartered in Aberdeen, Europe's oil & gas capital, TEPUK Is currently one of the UK Continental Shelf (UKCS) In terms of production and reserves. Being part of the Total Group means the workforce includes both local and expatriate staff, drawn from more than 35 countries. Industry Supervisor would be Kris Kydd, a chartered Electrical Engineer with over 13 years’ experience in the Oil & Gas Industry. Previously working in Operations. Now Head of Robotics R&D for all robotic locomotion systems & associated applications (regardless of TRL) for use in the energy industry both for human engineered environments and unmanned automated plants.