Research Studentship in Mission Planning for Long-Term Multi-Objective Remote Inspection (1)
Research Studentship in Mission Planning for Long-Term Multi-Objective Remote Inspection
Project: Mission Planning for Long-Term Multi-Objective Remote Inspection of Nuclear facilities
3.5-year DPhil studentship
Prof Nick Hawes and Prof Maurice Fallon
Nuclear facilities need repeated remote inspections over long durations (months to years). This will be especially true in future nuclear facilities such as those focussing on Nuclear Fusion, since such facilities will be completely dependent on robotic maintenance due to the challenging environments inside. In order to enable the delivery of such inspection missions by autonomous robots they must be able to plan missions that manage multiple objectives. For example, on a single day a mission may need to trade off the number of locations in the environment that are inspected against the battery life of the robot. And even within such a mission, autonomously balancing the amount of time spent gathering detailed readings of one location versus high level inspections of many areas (e.g. for physical change detection) may need to be balanced efficiently. Additional trade-offs may be present within a single mission, such as providing enough slack to allow operators to request additional tasks, or managing the risk from exposure to environmental hazards. Over a longer timescale (e.g. across a week or month), an inspection system may need to also deliver quality of service guarantees (e.g. every location is inspected for at least an hour) whilst also allowing time for repairs or managing facility access constraints. In this project we will develop a generic multi-objective mission planning system which can deliver policies to control an autonomous inspection robot over long-term missions in nuclear facilities. It will explicitly represent objectives and constraints at different temporal scales, and support dynamic behaviour changes according to changing environment conditions and user requirements. We will evaluate the planner by integrating it with state-of-the-art mapping and change detection systems, and deploying it on an autonomous mobile robot (likely a Spot or Jackal) over an extended period in a representative facility.
Course fees are covered. The stipend (tax-free maintenance grant) is c. £16062 p.a. for the first year, and at least this amount for a further two and a half years.
Prospective candidates will be judged according to how well they meet the following criteria:
- A first-class honours degree in Computer Science, Engineering, or a cognate discipline
- Excellent English written and spoken communication skills
- Previous experience in algorithms for decision making, planning, or control in autonomous systems, particularly under uncertainty
- An ability to translate algorithms from theory to a practical implementation, especially on robots
- Ability to program in Python or C++
The following skills are desirable but not essential:
- Experience with the Robotic Operating System (ROS)
- Experience with robotic mapping and perception
- Experience with probabilistic machine learning methods
We keen to recruit students who increase the diversity of our group.
Details about funding body:
RACE (Remote Applications in Challenging Environments, http://www.race.ukaea.uk/) was founded in 2014 as part of the UK Atomic Energy Authority (UKAEA) fusion research and development programme - to create robots for operating in some of the most challenging environments imaginable. UKAEA’s wider mission is to lead the commercial development of fusion power and related technology, and position the UK as a leader in sustainable nuclear energy.
Based at Culham Science Centre near Oxford and at a new technology facility in South Yorkshire, UKAEA runs the UK’s fusion research programme and operates the Joint European Torus (JET) fusion experiment on behalf of scientists from 28 European countries. UKAEA is keeping the UK at the forefront of fusion as the world comes together to build the first powerplant-scale experiment, ITER – one step away from the realisation of nuclear fusion as a carbon-neutral energy source. JET serves as a test base for ITER, as well as future fusion demonstration powerplants putting electricity on the grid such as DEMO and UK’s own future STEP powerplant.
Informal enquiries are encouraged and should be addressed to Prof Nick Hawes (firstname.lastname@example.org).
Candidates must submit a graduate application form and are expected to meet the graduate admissions criteria. Details are available on the course page of the University website.
Please quote 22ENGSIN_NH in all correspondence and in your graduate application.
Application deadline: noon on 17 June 2022
Start date: October 2022