The driverless car is taking big leaps forward under the stewardship of Google, which has made its robot cars even better at handling everyday city driving situations.
The tech giant's driverless cars have now clocked up an impressive 700,000 – travelling around Google's headquarters in Mountain View, California.
Among the improvements to the car's software are:
- More detailed maps that include curbs and various traffic signals.
- The ability to distinguish between pedestrians and cyclists – each of whom behave differently on or around the road.
- Sign reading ability has evolved to allow for the sudden appearance of signs – such as the fold-out stop signs found on school buses.
- The ability to determine the likelihood of certain situations taking place, based on thousands of possibilities.
A Google blog post on the new developments stated:
“What looks chaotic and random on a city street to the human eye is actually fairly predictable to a computer. As we’ve encountered thousands of different situations, we’ve built software models of what to expect, from the likely (a car stopping at a red light) to the unlikely (blowing through it). We still have lots of problems to solve, including teaching the car to drive more streets in Mountain View [Google’s home town] before we tackle another town, but thousands of situations on city streets that would have stumped us two years ago can now be navigated autonomously.”
The Californian search giant has fitted a number of Lexus RX450H SUVs with the driverless technology, which features the ability to build up a real-time three dimensional image of the vehicle's surroundings.
In the event of something going wrong, a driver sits in the driver's seat, ready to take control, while an engineer sits in the passenger seat.
In the future, the question of who owns a vehicle may be less important in terms of insurance, since all cars may be driven in the same way. Equally, personal cover for vehicle breakdown – based on the person rather than the vehicle – may also become the norm.