However, Taub says tomorrow's vehicles won't need to add much computing capability to make it all happen. Given the prevalence of today's complex safety systems, much of the computing power is already in place, he said.
"Each sensor will have its own smarts," he said. "And then all the information from the sensors will be sent to a central processor that will do the integration and fuse it into a single level of situational awareness. But you won't need supercomputers. It's a distributed network, and we think it's doable."
In the beginning, autonomous cars will be "sensor-intensive." They'll employ radar, LIDAR (light detection and ranging), ultrasound, and camera-based sensors. Such subsystems, working with central processors and highly developed software algorithms, will endow the vehicles with the full, 360° situational awareness that vehicle developers seek.
Eventually, some of the sensors will be augmented or even replaced by on-board vehicle-to-vehicle and vehicle-to-infrastructure communication systems. Those systems will enable the vehicles to communicate silently with one another, as well as with stop lights, road signs, and virtually everything else that matters. As a result, the vehicles will get the situational awareness they need without the high cost of lasers.
To a small degree, vehicle autonomy may already be happening around us. The now-famous Google automated cars have logged more than 140,000 miles, including drives on such well-known venues as Hollywood Boulevard, Lombard Street in San Francisco, the Golden Gate Bridge, and the Pacific Coast Highway.
Taub says that much of the technology is already in place, and that production vehicle manufacturers are already using some of it. Adaptive cruise control and lane-keeping technologies are popping up on vehicles. And accident avoidance -- the ability to commandeer the brakes and steering wheel -- is coming very soon. Those features, he said, lay the groundwork for complete autonomy.
To keep up with our Chevy Volt coverage, go to Drive for Innovation and follow the cross-country journey of EE Life editorial director Brian Fuller. On his trip, sponsored by Avnet Express, Fuller is driving a Volt across America to interview engineers.
I suppose stranger things have happened and there's no doubt the technology will get there. This is clearly one of those situations where the technology is likely ahead of consumer's comfort zone for entrusting their safety to some computerized, autonomous vehicle system. Even the idea of cars chugging along with people in the backseats doing other stuff is creepy to me, however inevitable.
I'm wondering how the Allstates of the world are viewing the increase in automotive computing capability and if they will factor it into their rates at some point. (I mean in terms of REDUCING insurance rates.) I was shocked recently to find out that my six-year old Sentra cost more to insure than a newer car, and the agent told me that one reason is that newer cars have all those airbags. By analogy, I wonder if a car with some demonstrated autonomy via computer control will be similar safer and thus qualify for reduced rates, at least at some point when this all shakes out and becomes more mainstream.
That's an interesting point, Alex, and really turns the notion of autonomous driving on its head when you really start to think about it. Of course, the goal is to eliminate driver distraction and increase vehicle safety, which is sort of hard to get your arms when envisioning cars driving themselves down the road. But I suppose as the technology matures and the vision systems, sensors, and embedded software systems become more powerful and refined, driving will likely be a much safer business and perhaps will garner the early adopters some whopping discounts on their insurance premiums.
Self-driving cars could boost the use of infotainment aboard vehicles. While many of us may see this as a way to work on the way to work, I would imagine the freedom of attention inside the bar would increase the consumption of videos and TV. In a self-driving car, a robust infotainment center would be a must.
They’ve already commercialized the hardest part – parallel parking, now available from the very high-end cars all the way down to the Ford Focus. And as the article eludes, most (if not all) of the remaining sensing technology is already developed and ready.It was about 2005 I toured the M.I.T. Media center and saw a presentation on the autonomous vehicle in a highway environment.The constant distance and constant speed sensing completely eliminated the “rush-n-brake” situation that causes stop-n-go in the passing lanes.I dream of the day when it’s a reality.2020 seems realistic.
Eliminating the "rush-n-brake" situation that leads to "stop-n-go" passing--now that has to be THE salient sales pitch that can get skeptics like me rethinking their openness to embrace an autonomous vehicle system. Any one who's crawled in traffic for hours and hours on end will likely feel the same.
That's a good point, Rob. The infotainment in cars could increase and will not undergo the discussion of "it is is a distraction" because there are no drivers to distract. I am curious to see how the self driving cars will play a part in car accidents and wonder if it would increase/decrease driver safety.
That's a good one, mrmikel. That brings up a huge question -- what happens when the car breaks the law -- turning too soon or too late in a left-turn situation with oncoming traffic? Those are tough calls under any circumstances. Even if the oncoming driver is at fault, what happens when that driver lies? The driver-less car can tell its side of the story. Or would video cameras be necessary?
I would think if the car is driving itself, video cameras and sensors will be standard features throughout the vehicle and will be able to deliver the video play back of the real story behind the accident. But you raise a really good issue.
For industrial control applications, or even a simple assembly line, that machine can go almost 24/7 without a break. But what happens when the task is a little more complex? That’s where the “smart” machine would come in. The smart machine is one that has some simple (or complex in some cases) processing capability to be able to adapt to changing conditions. Such machines are suited for a host of applications, including automotive, aerospace, defense, medical, computers and electronics, telecommunications, consumer goods, and so on. This radio show will show what’s possible with smart machines, and what tradeoffs need to be made to implement such a solution.