Slightly off topic - but does this imply that the mapping services are upping accuracy enough to permit this to happen - or are you saying that the software will have to be improved more to make this a safe approach?
Software and hardware will need to be improved before this can happen, according to the experts:
"The car’s sensors can’t tell if a road obstacle is a rock or a crumpled piece of paper, so the car will try to drive around either. Urmson also says the car can’t detect potholes or spot an uncovered manhole if it isn’t coned off. Urmson says these sorts of questions might be unresolved simply because engineers haven’t yet gotten to them. But researchers say the unsolved problems will become increasingly difficult. For example, John Leonard, an MIT expert on autonomous driving, says he wonders about scenarios that may be beyond the capabilities of current sensors, such as making a left turn into a high-speed stream of oncoming traffic."
Google’s Self-Driving Cars Still Face Many Obstacles | MIT Technology Review
Here's the maps issue:
"But the maps have problems, starting with the fact that the car can’t travel a single inch without one. Since maps are one of the engineering foundations of the Google car, before the company's vision for ubiquitous self-driving cars can be realized, all 4 million miles of U.S. public roads will be need to be mapped, plus driveways, off-road trails, and everywhere else you'd ever want to take the car. So far, only a few thousand miles of road have gotten the treatment, most of them around the company's headquarters in Mountain View, California. The company frequently says that its car has driven more than 700,000 miles safely, but those are the same few thousand mapped miles, driven over and over again."
Google self-driving car: It may never actually happen.
- - - Updated - - -
The autopilot demonstrated at the P85D unveil did slow you to a smooth and complete stop to avoid hitting the completely stopped car that was in the lane. It also did lane keeping, not just departure warning (not much of an autopilot otherwise!). I don't know if the complete stop ability will be part of the ACC feature separate from autopilot, but would expect so. On the other hand, I doubt the lane keeping would be separate than autopilot, but again, just my supposition.
Good to hear but if those features are coming with auto-pilot, and are not currently in use, it could be many years down the road before we actually see them. For instance, what if you need to swerve around an open manhole but the car takes you back to it? New types of sensors may be required and not just updated software for this to actually work. It's fine to demonstrate it at an airport but real world driving has many other factors to account for and while I love Tesla, I also know they are prone to hype.