Formula One trials AI in Abu Dhabi to tackle track limits breaches

The Paris-based FIA said it would be using 'Computer Vision' technology that uses shape analysis to work out the number of pixels going past the track edge.

The AI will sort out the genuine breaches, where drivers cross the white line at the edge of the track with all four wheels, reducing the workload for the FIA's remote operations centre (ROC) and speeding up the response.

The July 2nd Austrian Grand Prix was a high water mark for the sport with just four people having to process an avalanche of some 1,200 potential violations.

By the title-deciding Qatar weekend in October there were eight people assigned to assess track limits and monitor 820 corner passes, with 141 reports sent to race control who then deleted 51 laps.

Some breaches still went unpunished at October's US Grand Prix in Austin, however.

Stewards said this month that their inability to properly enforce track limits violations at turn six was "completely unsatisfactory" and a solution needed to be found before the start of next season.

Tim Malyon, the FIA's head of remote operations and deputy race director, said the Computer Vision technology had been used effectively in medicine in areas such as scanning data from cancer screening.

"They don’t want to use the Computer Vision to diagnose cancer, what they want to do is to use it to throw out the 80% of cases where there clearly is no cancer in order to give the well trained people more time to look at the 20%," he said.

"And that’s what we are targeting."

Malyon said the extra Computer Vision layer would reduce the number of potential infringements being considered by the ROC, with still fewer then going on to race control for further action.

"The biggest imperative is to expand the facility and continue to invest in software, because that’s how we’ll make big strides," he said. "The final takeaway for me is be open to new technologies and continue to evolve.

"I’ve said repeatedly that the human is winning at the moment in certain areas. That might be the case now but we do feel that ultimately, real time automated policing systems are the way forward."