Novelty Detection in Lunar Analogue Terrains

Lunar and planetary rovers are faced with a high volume of data from their sensors and cameras, and yet decisions must be made rapidly to prioritize to which crater it should drive up to and of which rock it should take a closer look. In Canada’s intended upcoming exploration of the Lunar surface aboard short-timescale commercial missions, these considerations are of utmost importance. By leveraging recent advances in artificial intelligence (AI), this research will equip rovers with the ability to survey its surroundings and discover which elements of the terrain ahead are novel and potentially interesting to scientists. The rover will then be able to prioritize which data to pass on to the science team or even select its next point of investigation autonomously.

Braden Stefanuk
Faculty Supervisor: 
Krzysztof Skonieczny
Partner University: