AI is a stream of high-performing computer systems that can perform tasks that would usually require human intelligence often relating to problem solving, and decision-making processes. These systems learn from vast amounts of data, recognising patterns, and then utilising these patterns to process information with human thought.
In the context of motorsport, it can be regarded as ‘machine learning’. This taps into the area of AI that uses algorithms to analyse large quantities of data. Machine learning needs an aspect of training to improve, therefore to begin with it can make mistakes, but improvement will be seen overtime.
As a result, there needs to be a good amount of caution in place if it is to be used in motorsport, however once developed it could have the potential to transform motor racing – making it faster than ever.
A clear commitment to the fact that AI will not be replacing their engineers... rather acting as a tool they can use to inform their decisions
AI is currently being used in certain areas of motorsport. The first motorsports team to publicly admit use of AI was one based in Wakefield – United Autosports. They used a model to speed up the decision-making process when determining which parts should be used and replaced on their cars. They have also used it to analyse timing and scoring patterns from endurance races to predict when safety cars and yellow flags were likely to occur.
As of now most teams are using AI, in one way or another – confirmed by Mercedes technical director James Allison. He explains how AI is gaining traction in aerodynamics, race strategy, and is being used to create surrogate models, for testing.
McLaren have also openly acknowledged their involvement with AI. However, they make a clear commitment to the fact that AI will not be replacing their engineers, or data scientists but rather acting as a tool they can use to inform their decisions.
A powerful application of AI is surrogate modelling, because instead of running thousands of expensive computational fluid dynamics programmes, engineers can train a machine-learning model on a limited dataset. Essentially, they can build accurate predictions from complex simulations, in much quicker time.
Ultimately, motorsport will be revolutionised.
Performance can also be optimized by improving aerodynamics. By recognising the best shapes of car, and precise angles of the wings so that there is minimal drag, and maximum downforce. This would essentially reduce lap time significantly.
It can also improve race strategy by analysing large datasets in real-time to make quick decisions. This could be used in pit stop timing, tire management, and analysing/predicting how opponents may move, so that the driver knows where to position themselves strategically - all of which would make racing faster.
The Future...
The next generation of racing will be undeniably faster. AI will not only making racing faster in terms of the speed (of the cars), but it will also transform every decision, allowing teams to work to their best, consistently. Ultimately, motorsport will be revolutionised – the faster engineers process data, predict outcomes, and refine designs, the faster the cars will go.