Here’s the latest data from the DIY Robocar monthly race series, thanks to our Track Master, Adam Conway.
A few things to note about these results:
- The gap between traditional computer vision techniques (“CV”) and convolutional neural network machine learning (“ML”, also known as AI/deep learning/CNN) is shrinking.
- The best of both will probably beat the best human drivers by the end of the year
- This is in some sense a proxy war for the philosophical debate between the two approaches that is playing out in the full-sized self-driving car industry. Google/Waymo represents the ML-centric approach, while Tesla represents the CV-centric approach.
- In both CV and ML, the top teams are using custom code. The two standard platforms — Donkey for ML and OpenMV for CV — are not yet beating the custom rigs. But over time, with more adoptions and collective development, there’s no reason why they can’t.
- Everyone is getting better fast!
No offense to the machines, but those lines do not look linear. It appears unclear whether they will beat the humans soon, or just approach the human mark asymptotically. Still, there has been a lot of progress, congrats!
Do the human racers use FPV gear?
in the interest of objectivity, the human racers should be required to race w FPV gear. The things we could do with the CV/ML equivalent of ‘human eyes observing from a fixed point above the track’ would likely propel CV/ML ahead.