Learning to self-navigate
Making that happen won't be easy. Automakers will need to rely on developments outside the prescribed boundaries of the auto industry -- in universities and at supplier facilities.
The biggest (and possibly most important) participants are the sensor suppliers. Makers of accelerometers and gyroscopes are already working with automotive teams on the development of systems such as dead reckoning, which enables vehicles to know where they are. For dead reckoning, engineers blend information from global positioning satellites (GPS) with inertial data coming from the car's onboard sensors. This gives the vehicle a sense of where it is on a map at any given time. Engineers say that it's necessary to use both sources because GPS systems don't update themselves fast enough to provide exact locations. GPS receives about five signals per second, while inertial sensors may update at rates of 1kHz or 2kHz.
"There's a function called map matching," Muddiman said. "You know all the physical entities -- streets, driveways, intersections -- and you use the inertial data to confirm that you've traversed from one digitized point on the map to another digitized point."
Radar technology, which is already making inroads in adaptive cruise control and collision avoidance, could be employed for forward object detection in autonomous vehicles. (Source: Freescale Semiconductor)
To get the inertial part of that equation, engineers need to draw data from accelerometers and gyroscopes. They typically use so-called low-G accelerometers, which can sense subtle changes in acceleration and direction down to tenths of a G-load. The sensors make it possible for the vehicle to interpret distance and position at high-resolution levels. Even the smallest movement, such as the changing of lanes, can be picked up by the low-G accelerometers. Gyroscopes add to that knowledge by measuring the vehicle's attitude (pitch, roll, and yaw) and thus filling in the data the accelerometers miss.
For engineers, the real trick lies in taking that mountain of data and blending it to form a coherent picture. To do that, they employ processors. Sensors, for example, may contain onboard processors that filter the digital data and send it to a "base band" applications processor, which also examines GPS data. Typically, such computing chores can be handled by dual- or quad-core processors. "The application processor takes all the data and compares it to determine if the information it's getting from the GPS system is accurate," Muddiman said.
Avoiding obstacles
Figuring out a car's location is only one of the chores that makes autonomy possible. A larger, more complex task is determining what's in front of the vehicle and whether it's time to stop or go. To do that, researchers are employing stereo vision cameras, radar systems, and lasers.
Vision, which is not yet playing a big role in autonomous vehicles, uses cameras similar to those employed in smartphones. Engineers say those cameras could provide important information, but researchers haven't figured out how to make sense of it all.
I have to admit--this is one technology I have a hard time wrapping my brain around, although I know it's only a matter of time before this doesn't seem weird or scary. I think the slow and steady approach to tackling the problem in discrete phases is a necessity. Not only does it ensure everything is working up to snuff, but it gives us, as a society, time to digest and feel comfortable with the whole concept of autonomous driving cars.
Beth, I think it will take time to get used to this. I have trouble riding in the front when my teenage boys drive. At least I can yell at them. I guess I would yell at the car in the future.
On the serious side, I think it is interesting that the current research uses all these complex sensors. Humans use mostly just vision. Multi-sensor fusion, as it is called, is very complex. It might be better to work on vision driven algorithms. If you could merge what humans do with vision with the "concentration" that computer are good at, you would have safe roads.
It certainly has admirable goals - I am all for a zero fatality rate in any mode of transportation! But the complexity of successful sensor integration coupled with the challenges of interpreting unpredictable situations overwhelms me. I think doing it in stages is very smart indeed. If the technology is viable - it will certainly solve a lot of problems. I can sympathize with you Naperlou - I have two teenage sons that will soon become new drivers and I find the prospect very worrisome. Completely autonomous driving would not only eliminate the human element - it would also allow those who are uncomfortable driving themselves or who are physically impaired to utilize autonomous driving and be back on the road again...but like Beth, I do have a hard time wrapping my brain around it. I know hubby won't want to give up his 87 Cutlass so I guess they'll have to come up with a refit kit too ;)
Chuck, Excellent article. It makes sense to me that software algorithms are really the key to making this happen. It's not that hard to foresee the hardware being refined and relatively inexpensive but fast, accurate, decision-making is really the key. Especially given the number of lawsuits that could be spawned as a result of product liability issues.
I can see this as an addition instead of a replacement to how we drive today. This could help sight impaired people become more independent and mobile. It can also solve the drowsy driving issue amoung many truck drivers or long commuters.
No matter how cool, if it doesn't look sexy, it will never catch on...like the segway. Many drivers (aka mistake-prone humans) around the world love speed and versatility. And, they love showing off the skills needed to drive a car well.
Thanks, Al. You've hit the nail on the head with your comment about lawsuits. There are a few big problems on the horizon. One is that many drivers won't want to give up control. Another is the legal issues that will arise when machines make mistakes. And the third is that everyone won'y buy their autonomous cars on the same day, or same year, or same decade. There's going to be a mix of human drivers and autonomous cars for awhile, and the machines will need to be able to deal with that.
Fastest, easiest implementation will likely be an extension of the diamond lanes used for carpooling. This would somewhat ease the chaotic environment described in the article.
I am quite ready for this technology; reducing accidents while giving more free time is a double win.
However, I do want the human to have final say over the controls. I do not want an AirBus fiasco where the flight computers can override the pilot's instructions.
Like any parent with a new teenage driver, you're going to be apprehensive at first with this technology, but humans are quick to accept it if it "just works."
I entirely expect that insurance costs will actually push this tech forward. When people are offered significant discounts for hands-off driving, they'll weigh the costs and be motivated towards whatever saves them money.
I personally would love to have a chauffeur. A non-human one is always immediately available. Besides, with people wanting to be "connected" all the time as is evident by the increasingly common texting-while-driving stories, I won't be surprised if the car becomes a mobile hot spot, where we just get in an go. I feel sorry for the taxi drivers though (not really).
I agree, btwolfe. I would love to have an autonomous driver cart me around so I could work in the back seat on the way to the office. Of course, it all hinges on the autonomous driver's ability to get me to my destination safely.
I love to hear people's reactions when I tell them about the inevitable arrival of autonomous cars. It is amazing how resistant people are to the idea of giving up that control. But here is the thing that I think will ultimately force the issue: car insurance. Once the near perfect record of autonoumous cars becomes established, insuring them will be dirt cheap. But this is America afterall, so you choose: Pay $30/year for your auto-car, or take the wheel yourself for $3000/year.
I, too, like to hear people's reactions to the idea of the autonomous car, sbauman. The initial reaction is always disbelief. But after that, the reaction is overwhelmingly negative -- most people don't like the loss of control. I agree with you that insurance will have to drive it. If autonomous cars can eliminate 30,000 deaths a year on American roads, it makes sense that the insurance companies would step in.
The question, though, is which insurance? No matter how good the safety systems are, there will still be accidents. A tire will blow, a sensor will fail, a kid will run into the road and the trial lawyers will be set free to go after everybody in the supply chain. I'm not sure I would want to be the company that supplies software for any of these.
I can see it working most of the time, but what about construction zones, roadway debris, the truck that just blew a tire next to you, deer, snow, rain? I'm not saying it can't work, I'm saying that it can only be a high-end cruise control. Most of the time it would be great, but you can't be asleep at the wheel.
@tekochip - I think your argument applies to humans as well... our ability to react is directly affected by our attentiveness. A driver going down the freeway in mental "cruise mode" probably wouldn't notice that debris that's about to fall off the truck in front of them any better than an autonomous driver. I'm sure these systems will eventually evolve to watch for situations like this. However, debris on the road I believe is already a part of the system.
What makes an autonomous driver even more compelling is that it can gather info from other autonomous vehicles further up the road about debris, giving you vehicle more time to react.
Again, to get a picture of this development we should be looking into it over a longer time period. When electronics start to penetrate the cars the development was evidently preparing the path for autonomous vehicles. I did work long ago in the semicondurctor industry and the automotive side of biz grew at tremendous speed. All was was said about the acceptance, of the liability issue and the fail-safe-operation undeniable is true.
Evidently the road into the future had to take a path that prepared the ground, allowed for going through the learning curve, for autonomous vehicles. Driver assisstant systems are the buzz word of the, let´s call it first generation. Small step further came with the automatic parking electronics. All the issues mentioned here applied to that. Than I remember came the question of using autonomous driving in logistic centers were trucks are unloaded and loaded. Here you had a controlled environment with a determined liability frame work.
Next generation we can see in the market today. Those are further improved driver assisstant systems that watch to what the driver is doing and to advise him to react if he is not doing as he should and act by its own when the driver fails. Collision prevention, there is an ad about a french car maker advertizing this function. If the car is about to leave the lane or paveed surface. The roadCruiser keeping the distance from the car in front. The system watching the eyes of the driver to notice when he falls asleep. And finally the developments in the area of traffic assistance, where the dialog between the car to exchange information about traffic. The system watching the streeet ahead to see obstacle or traffic under conditions were the human eye cannot see anything. All this is closely linked to the sensors and the related software development. And the development and the passing of the learning curve takes place in this systems.
Living in Germany with our Atutobahns, here would be an ideal place to start autonomous driving. You have a more controlled environment and a system that is close to its limits in capacity. Just forcing trucks when they enter the autobahn to stay on a reserved lane, drive so close to each other to limit the air resistance would reduce consumption of fuel, protect the environment, reduce an important source for accidents and allow for longer driving times for the drivers, as this could rest while the truck drives and finally the capacity increase of the Autobahn would be tremendous. Next step would be for the normal vehicles. You can see this to analogy with the reserved lane for conmuters with more than one person inside!
As energy efficiency becomes more and more a concern for makers of electronics devices, researchers are coming up with new ways to harvest energy from sound vibration, footsteps, and even electromagnetic fields in the air.
The government wants to study your brain, and DARPA wants to use similar information to give robots true autonomy beyond any artificial intelligence developed to date. Sound like science fiction? It's not.
By refining topologies and using new fluid technology, Moog's new peak sine drive controller increases available power without increasing controller volume.
From Dell / Intel® New Paradigms in Design Work Scott Hamilton, vertical market strategist for Dell Precision workstations, 5/2/2013 3
Early in my career, I worked as a draftsman and remember the days of drawing on vellum with numbered pencils and Mylar with plastic lead. This was a fun experience in the sense that I ...
I've been using workstations for more than 10 years and love finding ways to get more performance from my system. With demanding professional applications that require more power each ...
A lasting memory from my first job as an engineer in an auto assembly plant is standing on hard concrete at six in the morning, vending-machine coffee clutched in hand, listening to ...
A quick look into the merger of two powerhouse 3D printing OEMs and the new leader in rapid prototyping solutions, Stratasys. The industrial revolution is now led by 3D printing and engineers are given the opportunity to fully maximize their design capabilities, reduce their time-to-market and functionally test prototypes cheaper, faster and easier. Bruce Bradshaw, Director of Marketing in North America, will explore the large product offering and variety of materials that will help CAD designers articulate their product design with actual, physical prototypes. This broadcast will dive deep into technical information including application specific stories from real world customers and their experiences with 3D printing. 3D Printing is
To save this item to your list of favorite Design News content so you can find it later in your Profile page, click the "Save It" button next to the item.
If you found this interesting or useful, please use the links to the services below to share it with other readers. You will need a free account with each service to share an item via that service.
Tweet This
0 
