F1 AI to police track limits in the future

The technology, known as 'Computer Vision,’ employs shape analysis to scrutinise pixels in a video feed, aiding in the determination of track limit breaches. The FIA anticipates this will significantly refine the process, reducing the number of cases requiring human verification.

The implementation of AI is expected to decrease the workload on the FIA's Remote Operations Centre (ROC), streamlining the response time from breach reporting to decision-making. Tim Malyon, head of the ROC, emphasised the role of AI in filtering out incidents that do not necessitate human judgement. He said: "At the moment we've 'brute forced' the situation by saying 'we need to make thousands of checks, how do we do that? Well, we throw people at it, because that's the most accurate solution. What we're looking to do now is introduce a level above ROC, and that's AI software."

Malyon outlined the goal to lower the typical 800 reports from a grand prix to a more manageable 50, easing the strain on FIA staff. In addition to Computer Vision, the FIA trialled Catapult in Abu Dhabi, a system designed to improve car location accuracy. Chris Bentley, Single-Seater Head of Information Systems Strategy, mentioned how similar technology is used in NFL for player identification and how it could enhance the FIA's live feeds. He said: "There are examples in NFL where they can identify every player on the pitch, even if they're in a big huddle. We can also use that technology on our live feeds. That will be the same as the new tool, and then we will be able to draw the 'lines of interest'. And then the AI would learn as it goes along."

Malyon also highlighted ongoing efforts to advance these technologies and deploy new ones. Plans include expanding the ROC team and doubling the connection bandwidth between the track and Geneva to support increased remote working. He reflected on lessons from track limit issues earlier in the year, revealing that human analysis of video footage proved more effective than automated systems. He said: "We basically concluded that the loops were insufficiently accurate, and that by far, our most accurate solution was having a data analyst looking at the video itself. In fact, that's an interesting element of the story as currently, through loop positioning, through GPS positioning etc, the human still wins."

Bentley further explained the decision to disable loops for circuit tracking, except in cases of chicanes, to better align with their objectives. He concluded: "We've turned off loops now for every circuit unless there's a chicane, because it just gets in the way of what we're trying to achieve. And ultimately the rule of thumb is that if it's too close to call, then the benefit of the doubt goes with the driver."