One can imagine a self-driving car going steadily on a motorway or a highway. But, driving takes a whole new direction when it comes to driving in the streets. One sees many cyclists, motorcyclists and pedestrians moving in the streets at different speeds. Google says that its self driving cars are now capable enough of handling tricky streets.
Google is optimistic about them hitting the roads in the near future. Google’s self-driving cars faced a stiff challenge when busy streets came under consideration. This is because these self-driving cars lack the instincts that we possess. These help us understand and predict what the other person is going to do. Programmed self-driving cars lack these sorts of human characteristics.
In order to rectify this shortcoming, the Google team has come up with the system that classifies different types of people and moving objects it comes across. For example, cars are categorized as red boxes, cyclists as purple boxes, and this system notifies the traffic hazards. The responses of Google’s self-driving car is triggered by these different colors. Google admits that its self-driving car isn’t ready for the road yet, but it is getting closer with the passage of time.
This project was launched in 2009. The car is estimated to have driven 700,000 test miles. Google issued a statement about these cars in 2012. Google said that it had not caused any accidents yet. Google, then shifted the focus from motorway to its street driving about a year ago. “It’s really important to be able to drive on city streets if we’re going to make meaningful progress toward making self-driving cars a reality,” the company said recently. Hundreds and thousands of new driving scenarios were added. The self-driving cars also programmed to pause for 1.5 seconds after a light turns green to prevent other drivers running a red light. Google will definitely face any obstacles before it can launch these cars commercially and make them hit the roads. It may have to win numerous legal battles.
“We still have lots of problems to solve,” Chris Urmson, director of Google’s Self-Driving Car Project, wrote in the blog. “But thousands of situations on city streets that would have stumped us two years ago can now be navigated autonomously. As it turns out, what looks chaotic and random on a city street to the human eye is actually fairly predictable to a computer,” he further added. “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).”