AI-Search, an artificial intelligence (Ai) project run by Defence personnel in search-and-rescue (SAR) trials has demonstrated the potential to save lives.
The project aims to apply modern AI to help detect small and difficult-to-spot targets, such as life rafts and individual survivors.
Plan Jericho’s AI lead, Wing Commander Michael Gan said, “The idea was to train a machine-learning algorithm and AI sensors to complement existing visual search techniques,”
“Our vision was to give any aircraft and other Defence platforms, including unmanned aerial systems, a low-cost, improvised SAR capability.” adding that search and rescue missions, which are traditionally done by human eyes scanning the wide expanse of oceans, “is a very very demanding task for Air Force personnel”.
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.
Lieutenant Hubbert was given a month to develop the new algorithms and completed the work in a fortnight, coming up with an AI system comprising of a sensor and processor, which in this case was something available commercially off-the-shelf in the form of a GoPro camera and a laptop.
A series of machine-learning algorithms alongside other deterministic processes being run through the processor is then trained to analyse the imagery collected by camera sensors and run through a processor to aid human observers.
AI-Search was first trialled successfully in the waters off Tasmania 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.
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,” Lieutenant 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, and was borne of a challenge from the Director General Air Combat Capability, Air Commodore Darren Goldie, to find a way of enhancing SAR using improved sensors.
See a short and very video with more details about AI-Search:
WATCH our AI-Search prototype for airborne search & rescue.
We recently flew our 2nd sortie in a C-27J Spartan to train the #AI to recognise life rafts, life boats and safety equipment.
This is a Plan Jericho collab with 35SQN & @Australian_Navy #AusAirForce #JerichoEdge pic.twitter.com/M1uRzTmWyL
— Royal Australian Air Force (@AusAirForce) March 16, 2020
