Google's self-driving fleet of Prius and Lexus vehicles have a stellar safety record, and, at least according to Google, are now safer than human drivers. That's partially because machines aren't distracted by things like spilled coffee or an obnoxious song on the radio. They also don't get tired after a 10-hour day at the office.
But another part of that equation is that self-driving vehicles are really, really good at identifying hundreds of distinct objects swirling around them simultaneously—everyday obstacles like pedestrians, cyclists, orange cones, or even cuddly animals darting out into traffic.
In a new blog post, Google shows us how its smart cars assess and navigate some of the trickier traffic scenarios, like, say, a road construction bottleneck near its Mountain View campus. The company writes that its vehicles have now logged "nearly 700,000 autonomous miles, and with every passing mile we've grown more optimistic that we're heading toward an achievable goal—a vehicle that operates fully without human intervention."
As Fast Company detailed earlier this year, the technology still has a long way to go, and a lot of regulatory hurdles to clear. But a fully autonomous future with accident-avoiding smart cars sounds pretty great—at least if we're ever able to afford them.