With the increase in number of satellites, for a multitude of tasks, a communication threshold is limiting the usefulness of the data gathering performed in-orbit. To alleviate this boundary, an option is to make use of an Artificial Intelligence (AI) software implementation which will be able to focus on the date(change) of interest and discard the repeating or unnecessary aspects. This is currently performed at ground stations, but will need to be applied on-board satellites to make the data collection smarter and limit the load on the downlink communication. It would be convenient to have a modular approach, with the ability to be applied to a variety of instrument types.
- The objective of the assignment is to develop a solution to the downlink data limitations by having AI on board of a satellite, reducing the data to be send down. This software should be modular in design, i.e. possibly applied to a variety of instruments and situations. This focus on software is to be in conjunction with research done at Hyperion, which focusses on the hardware requirements. Together, the goal is to have a working demonstrator/prototype at the end of 2020.
Tasks to be foreseen in the project (to be based on the student’s interest and distribution of tasks in agreement with the Hyperion topic):- Analysis of strategy and trends on AI based on Space Agency programmes
– Analysis of current state-of-the-art data processing in satellites
– Compilation of requirements for AI hardware and software for on-board processing
– Analysis of currently available AI hardware and software that may be suitable for on-board processing
– Design of suitable interfaces to “universal” payloads
– Development of an AI-hardware
– Development of software prototype
– Identification of training sources and execution of test trainings
– Compilation of strategy on how, when and where to train the AI
– Participation and/or execution of environmental testing campaign, such as radiation testing
– Support to identify suitable In-Orbit-demonstration
The following outcome of the graduation project is expected:
- A master thesis, including:
– Literature study
– Master thesis
- A demonstrator/prototype
- 4th year master student in the following fields:
– Information technology
– Geo-information sciences & Earth observation
– Engineering & technology
- Interest in software development and AI
- Space affinity optional
What we offer
•A challenging graduation project in a high-tech result orientated work environment
•Weekly supervision and availability of the technical staff for support
•An internship allowance
•Close cooperation with (a) student(s) of Hyperion working on a supplementary assignment
The Royal Netherlands Aerospace Centre NLR is the research organization in the Netherlands in the field of aerospace engineering. Around 650 employees highly educated from aircraft engineers to psychologists and from mathematicians to application experts. Visit our NLR media channel on YouTube for a good impression of the organization.
This assignment will be mainly managed by the AI group within the Aerospace Systems and Information Supremacy (ASIS) department.
Apply by sending your cv and cover letter to Alexander.Haagsma@@nlr.nl.
Datum : 24/01/2020
Locatie : Amsterdam of Marknesse
Uren : 40
Opleidingsniveau : WO
Werkniveau : MSc
Achtergrond : Electrical Engineering, Computer Science, Informatics