It appears that Google’s self driving cars seem to be getting better and better with vehicles now capable of interpreting hand signals from cyclists, something that is surely welcome news.
Using machine learning, Google produced a program that was capable of observing cyclists both on a private test track and out on the open road and the software was able to recognise common riding behaviours. This, when put into practice, will help autonomous vehicles to predict a cyclist’s next move.
Google’s June report said “Our sensors can detect a cyclist’s hand signals as an indication of an intention to make a turn or shift over. Cyclists often make hand signals far in advance of a turn, and our software is designed to remember previous signals from a rider so it can better anticipate a rider’s turn down the road.”
One of the impressive features about the new cars is that they are even capable of recognizing unicyclists as well as other variations of cycles.
The report continued: “We also aim to give cyclists ample buffer room when we pass, and our cars won’t squeeze by when cyclists take the centre of the lane, even if there’s technically enough space,” the report said. “Whether the road is too narrow or they’re making a turn, we respect this indication that cyclists want to claim their lane.”
However, Google did report that there had been two minor accidents during testing in Austin, Texas.
In the first incident, the Google car suffered minor damage to the front wing when another car entered its lane.
Another Google car suffered minor damage to the rear when a car rolled into the back of it at 3mph – the Google car had stopped at a red traffic light.