AI at the Edge
Artificial Intelligence at the Edge, or Edge-AI, is a recent area of AI technology development that becomes attractive and necessary when users are confronted with connectivity limitations and data privacy issues. The space domain is arguably the ultimate edge and the application of Edge-AI to miniaturised space systems is a growing research strength for the ¹ú²ú¾«Æ· Canberra Space team. Edge-AI is also applied to aspects of space operations such as Space Situational Awareness and Space Traffic Management.ÌýÌý
Edge-AI research at ¹ú²ú¾«Æ· Canberra Space focuses on the development of miniaturised satellites as edge devices, capable of performing complex tasks and analysis of data on orbit. This allows actionable information to be communicated directly and rapidly to the end user without the need to downlink large volumes of potentially sensitive data.ÌýÌý
However, we take this further. Our research on distributed learning is designed to link the Edge-AI-enabled satellites into semi-autonomous intelligent satellite constellations. Such constellations could collectively perform complex missions with outcomes that significantly exceed that of the sum of the individual units.ÌýÌý
At the same time, we apply machine learning to the science of Space Situational Awareness and Space Traffic Management, including collision avoidance, space surveillance and formation flying and control.Ìý
Associated schools, institutes & centres
Impact
The enhanced capabilities of intelligent satellite constellations will improve traditional applications and uncover novel uses of space systems and space-derived information. Most sectors and aspects of society depend on space – this will have a significant impact on each of them.ÌýIn particular, intelligentÌýspace systems offer the opportunity for the development and rapid (near real-time) delivery of information ready for decision-making, directly to the end user.Ìý
Competitive advantage
Our AI-for-space capability includesÌýtheÌýdevelopment of advanced machine learning algorithms and approachesÌýand their applicationÌýto advanced edge-AI accelerator devices. ThisÌýincludesÌýgraphics processing units (GPUs)ÌýandÌývision processing unitsÌý(VPUs).ÌýAlgorithms and approachesÌýthat offerÌýtheÌýopportunity for deployment toÌýminiaturisedÌýsatellite constellations with multi-modal sensorsÌýare a key focus.ÌýÌý
Our capabilities were demonstrated by exceptional performance in recent global AI-for-space competitions. We placed seventh in Airbus'Ìý2019 SatelliteÌýPoseÌýEstimationÌýChallengeÌýand thirdÌýin ESA'sÌý2020 CollisionÌýAvoidanceÌýChallenge. We achieved these resultsÌýdespite employing AI approaches deliberately designed to beÌýgeneralisableÌýand scalable,Ìýrather than tuned for the constraints of specific competitions.ÌýÌý
We developed and are demonstratingÌýedge-AI hardwareÌýonÌýourÌýM2 Pathfinder and M2Ìýsatellites, includingÌýpowerful in-house onboard computing and processing capabilities combiningÌýcentral processing unitÌý(CPU)ÌýandÌýfield-programmable gate array (FPGA)Ìýtechnologies. We also developed aÌýhigh-resolution imager/CPU/FPGA/GPU capability for on-board image processing that will be demonstrated on M2.Ìý
Most importantly we areÌýone team under one roof.ÌýWe combine space engineering and science, including space mission development, with research in the application of AI to space. This is enormously beneficialÌýto our effortsÌýinÌýdevelopingÌýintelligent space system technologies.
±Ê²¹°ù³Ù²Ô±ð°ù²õÌý
Our current partners in this effort include Frontier Development Lab (in particular, FDL AUSNZ) and theÌýSmartSatÌýCooperativeÌýResearchÌýCentre’s Artificial Intelligence in Space Research Network.Ìý
Ìý