Plan Jericho’s AI lead, Wing Commander Michael Gan, said his team recognised the potential for the technology to augment and enhance SAR.

“The idea was to train a machine-learning algorithm and AI sensors to complement existing visual search techniques,” he said.

“Our vision was to give any aircraft and other Defence platforms, including unmanned aerial systems, a low-cost, improvised SAR capability.” 

His team approached Lieutenant Harry Hubbert of Warfare Innovation Navy Branch, who was prominent in developing AI-enabled autonomous maritime vehicles for the Five Eyes Exercise Autonomous Warrior in Jervis Bay in late 2018.

LEUT Hubbert was given a month to develop the new algorithms and completed the work in a fortnight.

The AI comprises a series of machine-learning algorithms alongside other deterministic processes to analyse the imagery collected by camera sensors and aid human observers.

VIEW ALL

AI-Search was first trialled successfully aboard a RAAF C-27J Spartan last year. The second trial took place in March this year near Stradbroke Island, Queensland. During these trials, AI-Search detected a range of small targets in a wide sea area while ‘training’ the algorithm.  

Using commercial off-the-shelf components with custom software and programming by LEUT Hubbert, the trials highlighted the feasibility of the technology, which can be applied easily to other ADF airborne platforms.

“There is a lot of discussion about AI in Defence but the sheer processing power of machine-learning applied to SAR has the potential to save lives and transform it,” LEUT Hubbert said.

The project is a collaboration between Warfare Innovation Navy Branch, Plan Jericho, RAAF Air Mobility Group’s No. 35 Squadron and the University of Tasmania’s Australian Maritime College.

The project stemmed from a challenge from the Director-General Air Combat Capability, AIRCDRE Darren Goldie, to find a way of enhancing SAR using improved sensors.