Topic: Self driving vehicles

[Thucydides]

Imagine logistics vehicles that can go down the road on their own (or maybe follow the CQ's vehicle). Imagine engineer vehicles that can be sent forward on their own to conduct breaching operations or mine clearing. That would be the next step after driving on public roads is perfected:

http://nextbigfuture.com/2010/10/google-has-robotic-self-driving-cars.html#more

Google has robotic self driving cars that have already logged 140,000 miles of robotic driving

Google has automated cars (Toyota Prius) use video cameras, radar sensors and a laser range finder to “see” other traffic, as well as detailed maps (which we collect using manually driven vehicles) to navigate the road ahead. This is all made possible by Google’s data centers, which can process the enormous amounts of information gathered by our cars when mapping their terrain.

Google gathered some of the very best engineers from the DARPA Challenges, a series of autonomous vehicle races organized by the U.S. Government. Chris Urmson was the technical team leader of the CMU team that won the 2007 Urban Challenge. Mike Montemerlo was the software lead for the Stanford team that won the 2005 Grand Challenge. Also on the team is Anthony Levandowski, who built the world’s first autonomous motorcycle that participated in a DARPA Grand Challenge, and who also built a modified Prius that delivered pizza without a person inside

Our automated cars, manned by trained operators, just drove from our Mountain View campus to our Santa Monica office and on to Hollywood Boulevard. They’ve driven down Lombard Street, crossed the Golden Gate bridge, navigated the Pacific Coast Highway, and even made it all the way around Lake Tahoe. All in all, our self-driving cars have logged over 140,000 miles. We think this is a first in robotics research.

    Christopher Urmson, a Carnegie Mellon University robotics scientist, was behind the wheel but not using it. To gain control of the car he has to do one of three things: hit a red button near his right hand, touch the brake or turn the steering wheel. He did so twice, once when a bicyclist ran a red light and again when a car in front stopped and began to back into a parking space. But the car seemed likely to have prevented an accident itself

    The Google researchers said they had carefully examined California’s motor vehicle regulations and determined that because a human driver can override any error, the experimental cars are legal.

    There is even the farther-off prospect of cars that do not need anyone behind the wheel. That would allow the cars to be summoned electronically, so that people could share them. Fewer cars would then be needed, reducing the need for parking spaces, which consume valuable land.

Google has self driving cars with LIDAR, Radar sensors, super-mapping and backup human drivers with perfect records

1. LIDAR: In addition to video cameras able to see pedestrians and bicyclists, Google’s cars are equipped with a light detection and ranging, or “LIDAR” sensor on the roof able to give the car’s computers a 3-D map of the world around the car out to 230 feet — in all directions — Markoff reports.

2. Radar Sensors: four sensors give the car’s computers a sense of what’s going on in front of the car and in back, at the same time. Not terribly exotic, considering some cars already have radar, but hooking four up to a computer at the same time gives the car an ability to see things humans driving most cars can’t.

3. SLAM: Think of this as Google Maps on steriods. Simultaneous Localization and Mapping, or SLAM, let’s the car update a map Google’s cars uses to make its way through the world even it helps each car make find its place in it, Markoff reports. The first run is made by Google’s engineers on their own, then the cars record any changes they see in their environment as they move through it. The result: they won’t do some of the stupid stuff humans do when they get lost, like turn down one-way streets.

4. Better humans: Of course, the ultimate safety feature is the human driver in every car. Google has hired a dozen people with “perfect” driving records to drive around with its cars — stepping in if anything goes awry, Markoff reports. Can’t be too many people like that in California. Maybe that’s why I hadn’t heard about this project.

[Chris Pook]

Not limited to Google - Marines (Yankee version) also mucking about with them.

Move Over Fido: Marines’ New Best Friend Could be A Robotic ‘Mule’ 
October 2010 

By Grace V. Jean 

MARINE CORPS TRAINING AREA-BELLOWS, HAWAII — Most of the services are embracing robots faster than companies can manufacture them.

The Air Force has its Predators and Reapers. The Army will soon fly the Predator family’s latest addition, the Gray Eagle, in greater numbers. Meanwhile, the Navy is preparing to operate robotic boats, underwater craft and unmanned helicopters.

As for the Marine Corps, it has been lagging behind its peers in the use of robotics because until recently it hadn’t figured out what it wanted to do with the technology. Marines are flying unmanned aircraft as surveillance tools. Now officials want to employ ground robots as a means to reduce casualties from roadside bombs and to lighten the loads on troops.

In partnership with Naval Surface Warfare Center-Dahlgren, the Marine Corps Warfighting Laboratory is working with Virginia Tech and Blacksburg, Va.-based TORC Technologies to create GUSS, the ground unmanned support surrogate vehicle.

Engineers integrated drive-by-wire technology, sensors and autonomous control mechanisms onto a Polaris all-terrain vehicle. Designed for resupply missions, casualty evacuation and carrying gear, GUSS functions in three modes: tele-operated, semi-autonomous and autonomous.

Operators can control the vehicle using a handheld device called WaySight, which resembles a boxy camcorder. By looking through the viewfinder and pressing a button, they can send GUSS to a designated location. Troops also can drive GUSS in “Wii” mode by turning the WaySight like a steering wheel as it moves along. On the passenger side of the vehicle, there is a removable operator control unit where they can pre-plan a route by using the touch screen interface. GUSS can execute a mission on its own, or it can follow a marine by honing in on his WaySight.

The lab developed four GUSS units, with the fourth vehicle carrying a tele-operated M240G machine gun system called the modular advanced armed robotic system, or MAARS. All four made their way to Hawaii where they were placed into the hands of marines from the 2nd Battalion, 3rd Marine Regiment and 1st Battalion, 12th Marine Regiment for an experiment.
Sgt. Benjamin Johns, a squad leader in 2/3’s 3rd Platoon, Golf Company, went on hours-long patrols with GUSS.

“It came in really handy as far as carrying extra water. Some of the patrols we did were five or seven hours long,” he said. Unlike his peers who were operating 30 miles north in the Kahukus Training Area without any vehicles to help them carry water, Johns’ squad was able to load 20 gallons onto GUSS and have it travel alongside the troops on patrol. When their CamelBak hydration systems were depleted, the marines could resupply from GUSS and press onward.

“We wouldn’t have been able to do that without GUSS out there to sustain us because of how hot it was. Everyone was drinking a lot of water,” said Johns. 

Sgt. Luke Maxon, a squad leader in 1st Platoon, which did not possess robotic vehicles, said that a number of patrols were sacrificed in the north because his marines quickly ran out of water.

When units came under fire and suffered casualties in the exercise, Johns said that they used GUSS to help evacuate injured marines.

“It cut down the time it would normally take by 300 percent because you didn’t have to take away the manpower,” he said. “Carrying a casualty takes four marines, which is an entire fire team out of the fight, while you’re trying to get a marine to a safe landing zone so that he can be medevaced.”

The robot also helped troops to transition quickly from mission to mission without returning to their base.

Whenever the squad conducted meetings in the mock village with Afghan role players, the marines would take off their helmets and flak jackets and store them on GUSS so that they would not have an aggressive posture when sitting down with civilian leaders. Johns recalled one such meeting when the unit received intelligence about a potentially hostile location a half-kilometer down the road. “We were able to put our gear on really quickly and then move down there to check out what we got from the leader engagement,” he said. Following raids, GUSS was readily available to carry materials and evidence that the unit turned up. In Afghanistan, marines typically have to lug the items back to the base themselves or call for a support team to bring vehicles to collect them.

Johns said the concept of GUSS is a good one, but the vehicle’s object detection sensors are still too immature for operational use.

“You’d kick up dust in front of it and for some reason the sensors would look at that cloud of dust as a wall. And it’ll stop for anywhere from one to five minutes,” Johns pointed out. “In Afghanistan and other urban terrains we’ve been operating in, there’s sand, dust, all sorts of debris that will fly up for no reason, and having it stop all the time makes it useless. You can override it with a remote, but that takes a person having to get out of the fight.”

Obstacle avoidance capability is the Holy Grail, said Brent Azzarelli, chief robotics engineer at Naval Surface Warfare Center-Dahlgren. “We know there are some areas that need some work.”

Every minute that a marine has to spend operating the robot is a minute that he is not an active member of the 13-marine squad. Andrew Culhane, director of business development at TORC, said the company is working to upgrade vehicle autonomy and navigation capabilities to allow GUSS to operate more like the 14th member of the squad.

Johns reported that the MAARS tracked vehicle was utilized for security and surveillance purposes because it had better sensors for looking at distant objects and because it was quieter than GUSS.

Vince Goulding, director of the experiments division at the warfighting lab, said that autonomous ground vehicles are coming, whether they’re carrying a machine gun or an injured marine, or whether they take the form of a 7-ton truck moving supplies. “We’re looking to do all those things,” he said. “We just want to keep minds open to develop the [tactics, techniques and procedures] we need to have down before we put these things out into the operating forces. And that’s what experimentation is all about.”

Many of the technologies have been developed as a result of the Defense Advanced Research Projects Agency’s robotic challenges earlier this decade. The lab’s team was impressed by the autonomy improvements accomplished on GUSS since its previous experiment with the technology more than a year ago.

“GUSS surprised everybody with its growth and technological capability,” said Goulding in a phone interview after returning from Hawaii. “This experiment showed me technologically it’s maturing very quickly.”                                       

[Thucydides]

Self driving vehicles have been under development for many years, with DARPA being a long time sponsor, but it seems the commercial world is leapfrogging ahead. Google has demonstrated self driving cars (using a lot of equipment added on to existing vehicles, now Mercedes is unveiling a self driving car as well. Since Mercedes is a car company, the level of integration seems much higher.

The use of self driving vehicles for logistics would be one potential near term use (imagine a line of trucks following the CQ, for example). Self driving vehicles making deliveries around the base could also make the base more productive and potentially safer. Even if we accept the need for drivers to deal with emergencies, or to take over when driving off road, the use of self driving functions will do a lot to keep drivers well rested, or vehicle crews can spend more time focusing on what is going on outside the vehicle searching for threats until it becomes time to engage the manual drive button and steering wheel.

Lots of embedded video on the link:

http://www.core77.com/blog/transportation/mercedes_driverless_research_car_looks_freaking_amazing_25652.asp

Mercedes' Driverless Research Car Looks Freaking Amazing
Posted by hipstomp / Rain Noe  |   2 Oct 2013  |  Comments (41)


Humans suck at driving. The daily rush hour traffic snarl in my Manhattan neighborhood is less about the density of vehicles and more about human incompetence. At trouble spots like Broome & Lafayette, the box is routinely blocked by drivers unable to correctly judge timing and spacing (or happy to block the box in hopes they'll get home at 6:18 rather than 6:23). Meanwhile, further up the block, other drivers leave an absurd gap between them and the car in front of them, occupied as they are with their text messaging or phone conversations.

Even worse is when humans suck at being humans. Two anger-related NYC traffic incidents recently made local headlines: In the first, a cabbie arguing with a cyclist jumped the curb and hit a British tourist in midtown, requiring the young woman to have her leg amputated below the knee. In the second incident, a man was dragged from his SUV, beaten and knifed in front of his wife and child following an accident involving a motorcycle gang. (I found the GoPro-recorded helmet cam video, which went viral, too harrowing to embed.)

So the case for driverless cars is looking pretty compelling. Imagine a parade of automated vehicles moving cleanly through Manhattan, like blood pumping through veins, at regular intervals and with perfect spacing. Imagine it being technologically impossible for a vehicle to strike a pedestrian or cyclist. I'm hoping I get to see this in my lifetime, and I just might following breakthroughs like Mercedes-Benz's, below, where they successfully navigate a 60-mile route (both urban and rural!) in their S 500 Intelligent Drive research vehicle:



They're predicting the system will be production-ready in as little as six years, which will ironically require the patience that modern-day urban motorists seem to lack. But it will be worth the wait. "Unlike us humans," Daimler AG CEO Dieter Zetsche explained at a press conference, "electronic helpers never get tired, are never absent minded, and have zero reaction time."

[Thucydides]

Google self driving cars examined. As might be expected, they are smoother and better "drivers" than most of us:

http://www.technologyreview.com/news/520746/data-shows-googles-robot-cars-are-smoother-safer-drivers-than-you-or-i/

Data Shows Google’s Robot Cars Are Smoother, Safer Drivers Than You or I
Tests of Google’s autonomous vehicles in California and Nevada suggests they already outperform human drivers.

By Tom Simonite on October 25, 2013

Road trip: This car is among those Google has modified to run without a human driver.

Data gathered from Google’s self-driving Prius and Lexus cars shows that they are safer and smoother when steering themselves than when a human takes the wheel, according to the leader of Google’s autonomous-car project.

Chris Urmson made those claims today at a robotics conference in Santa Clara, California. He presented results from two studies of data from the hundreds of thousands of miles Google’s vehicles have logged on public roads in California and Nevada.

One of those analyses showed that when a human was behind the wheel, Google’s cars accelerated and braked significantly more sharply than they did when piloting themselves. Another showed that the cars’ software was much better at maintaining a safe distance from the vehicle ahead than the human drivers were.

“We’re spending less time in near-collision states,” said Urmson. “Our car is driving more smoothly and more safely than our trained professional drivers.”

In addition to painting a rosy picture of his vehicles’ autonomous capabilities, Urmson showed a new dashboard display that his group has developed to help people understand what an autonomous car is doing and when they might want to take over. “Inside the car we’ve gone out of our way to make the human factors work,” he said.

Although that might suggest the company is thinking about how to translate its research project into something used by real motorists, Urmson dodged a question about how that might happen. “We’re thinking about different ways of bringing it to market,” he said. “I can’t tell you any more right now.”

Urmson did say that he is in regular contact with automakers. Many of those companies are independently working on self-driving cars themselves (see “Driverless Cars Are Further Away Than You Think”).

Google has been testing its cars on public roads since 2010 (see “Look, No Hands”), always with a human in the driver’s seat who can take over if necessary.

Urmson dismissed claims that legal and regulatory problems pose a major barrier to cars that are completely autonomous. He pointed out that California, Nevada, and Florida have already adjusted their laws to allow tests of self-driving cars. And existing product liability laws make it clear that a car’s manufacturer would be at fault if the car caused a crash, he said. He also said that when the inevitable accidents do occur, the data autonomous cars collect in order to navigate will provide a powerful and accurate picture of exactly who was responsible.

Urmson showed data from a Google car that was rear-ended in traffic by another driver. Examining the car’s annotated map of its surroundings clearly showed that the Google vehicle smoothly halted before being struck by the other vehicle.

“We don’t have to rely on eyewitnesses that can’t act be trusted as to what happened—we actually have the data,” he said. “The guy around us wasn’t paying enough attention. The data will set you free.”

[Humphrey Bogart]

Google self driving cars examined. As might be expected, they are smoother and better "drivers" than most of us:

http://www.technologyreview.com/news/520746/data-shows-googles-robot-cars-are-smoother-safer-drivers-than-you-or-i/

Just what we need, something else to make us even more lazy then we already are.  I am envisioning the day when humans are not allowed to drive anymore because we will pose too great a "risk" to everyone else.  I need to start saving so I can move out to the woods and live the good life!

[Thucydides]

Having been rear ended and sideswiped by idiot drivers, I would applaud ways to get them to NOT drive their vehicles.

The proposed advantages of reducing traffic jams, time in transit, motor vehicle accidents and even fuel consumption (because they will drive at the optimum speeds for conditions) will be worth billions to the economy, which will be a powerful incentive for most people. "Hobby" driving may well take place in out of the way areas the way people now go to race tracks, off road trails or rally driving venues to challenge themselves.

In fact, one of the perques of joining the military in the future might be to actually drive a vehicle (since having an unpredictable human behind the wheel to take over from the robot may be the difference between victory and defeat).

[PrairieThunder]

Having been rear ended and sideswiped by idiot drivers, I would applaud ways to get them to NOT drive their vehicles.

The proposed advantages of reducing traffic jams, time in transit, motor vehicle accidents and even fuel consumption (because they will drive at the optimum speeds for conditions) will be worth billions to the economy, which will be a powerful incentive for most people. "Hobby" driving may well take place in out of the way areas the way people now go to race tracks, off road trails or rally driving venues to challenge themselves.

In fact, one of the perques of joining the military in the future might be to actually drive a vehicle (since having an unpredictable human behind the wheel to take over from the robot may be the difference between victory and defeat).

One of the best benefits to my civilian driving is not only the various DDC and 404 courses but also combat driver courses. It has put me in an advantage both in my civvy job as well as my personal driving.

[Thucydides]

Toyota demonstrates a system which is not 100% self driving, but rather a driver assistent:

http://www2.toyota.co.jp/en/news/13/10/1011_1.html

Toyota to Launch Advanced Driving Support System Using Automated Driving Technologies in Mid-2010s
Safer Highway Driving; Reduced Environmental Effects and Driver Workload

Toyota City, Japan, October 11, 2013—Toyota Motor Corporation announces that it has developed a next-generation advanced driving support system, Automated Highway Driving Assist (AHDA), which uses automated driving technologies to support safer highway driving.

AHDA links two automated driving technologies to support safer driving and reduce driver workload: Cooperative-adaptive Cruise Control, which wirelessly communicates with preceding vehicles to maintain a safe distance; and Lane Trace Control, which aids steering to keep the vehicle on an optimal driving line within the lane.

Toyota recognizes the importance of the driver being in ultimate control of a vehicle and is therefore aiming to introduce AHDA and other advanced driving support systems where the driver maintains control and the fun-to-drive aspect of controlling a vehicle is not compromised.  Toyota plans to market the newly developed AHDA in the mid-2010s and other driving support systems as soon as possible to provide safe and secure means of transportation.

Ahead of trials on the Shuto Expressway near the Tokyo metropolitan area starting October 15, Toyota will exhibit AHDA at the 20th Intelligent Transport Systems World Congress Tokyo 2013, an international conference for intelligent transport systems (ITS), to be held from October 14 to 18.

In addition, to enable prompt market introduction of next-generation driving support systems, Toyota will make use of the cutting-edge component technologies and know-how acquired through automated driving research conducted with the advanced active safety research vehicle unveiled at the 2013 International CES in Nevada, United States in January this year.

Cooperative-adaptive Cruise Control

In contrast to standard radar cruise control (which uses millimeter-wave radar to detect other vehicles), Cooperative-adaptive Cruise Control uses 700-MHz band vehicle-to-vehicle ITS communications to transmit acceleration and deceleration data of preceding vehicles so that following vehicles can adjust their speeds accordingly to better maintain inter-vehicle distance.  By reducing unnecessary acceleration and deceleration, the system improves fuel efficiency and helps reduce traffic congestion.

Lane Trace Control

Lane Trace Control, which features completely new Toyota automated driving technologies, employs high-performance cameras, millimeter-wave radar and control software to enable an optimal and smooth driving line at all speeds.  The system adjusts the vehicle's steering angle, driving torque and braking force when necessary to maintain the optimal line within the lane.

Automated Driving Technologies Research

At the 2013 International CES, Toyota displayed the advanced active safety research vehicle, a test vehicle for automated driving technologies that Toyota is researching under its Integrated Safety Management Concept1.  The test vehicle, based on the Lexus "LS", is being used in research at the Toyota Research Institute of North America in Saline, Michigan, and is capable of autonomous driving.  It is fitted with forward-looking cameras to detect traffic signals, as well as front-mounted sensors to detect vehicles, pedestrians, and obstacles to determine traffic conditions, such as intersections and merging traffic lanes, in the vehicle's vicinity.  Such research on various elemental technologies is aimed to help drivers choose the safest routes possible.

Toyota has been researching automated driving technologies since the second half of the 1990s, and has been conducting public road tests in the U.S. for a number of years.  Within Japan, Toyota has been testing its next-generation Intelligent Driver-support System on public roads2 for approximately two years.

Based on the insights gained from automated driving research, Toyota aims to provide advanced driving support systems optimized to help enable safer driving and contribute to realizing the ultimate goal of any society that values mobility: the elimination of traffic fatalities and injuries.

In anticipation of the super-aging populations of the future, these advances will also be used to develop technologies that support senior drivers with recognition, decision-making and vehicle operation, with the aim of achieving a mobility society where they can lead fuller lives.  Furthermore, Toyota is working to provide more stable driving environments that contribute to the alleviation of traffic congestion, thereby reducing economic loss and CO2 emissions.

1The concept does not refer to the individual safety systems on the car, but the integration of those systems to offer the optimum driving support at "all driving stages" from parking, to normal operation and the moments before and after a collision, and even avoidance at the moment of an accident.

2During testing, the driver maintains awareness of safety conditions and takes control of the vehicle whenever necessary.

[eme411]

I read and see all the things going on with CF tactical vehicles and just shake my head, we have gone from a gas power fleet to diesel that gave us great reliability and have now moved to computerized engines with no end of problems ie logistics , and no longer able to repair in the field , all the special test equipment required , the modules (parts) , training for these types of vehicles, and to get all this into the field and then find out you still can't repair without shipping a new dash cluster from the factory because the dash is married to the truck and only that cluster will work, look back to the MLVW , M-35 series truck , in service now for 60 years with the US military, M-35 gasser, M-35A1 & A2 diesel , multifuel, turbo multifuel , M-35A3 Cat turbo diesel with auto trans, this truck has been the army version of the B-52 , just keep upgrading and it soldiers on, a truck that has always been easy and quick to repair in the field , a dumb truck using the KISS principal, these types of vehicles got you on the battlefield and off , alive, something to ponder when you think a computer under the hood or in the dash of your tactical vehicle is a good thing in the battlefield, think of your Leopard doing a reboot in a tank fight , make sure your boots are good,
regards Frank

[George Wallace]

........... something to ponder when you think a computer under the hood or in the dash of your tactical vehicle is a good thing in the battlefield, think of your Leopard doing a reboot in a tank fight , make sure your boots are good,

Been there.  Done that already with TCCCS.  Murphy's law and having to reboot a radio on CONTACT sucks.

[Thucydides]

There certainly are risks to new technology, and of course *we* often pay for bells and whistles without considering the cost or even how we are going to use it. Anyone remember the cards that came out when we went to SN numbers? Everyone got a plastic wallet card with a magnetic stripe across the back, yet the card had no official use to begin with (it wasn't considered an ID card, for example), and the stripe was just an extra cost with no function, since it was never activated for anything.

Perhaps a trivial example, but still represented a cost in money and effort for virtually 0 payoff.

OTOH, car companies have a very vested interest in making sure their technology works, and that it is cost effective (for them). Compare a Toyota Camery from the 1990's with today's, and the new one is more efficient, safer etc. We can get closer to"B" if we could work our procurement system much better, and we do occasionally get it right (the HLVW was a great truck and is still running strong). There are some pretty large potential benefits to harvest form this technology, even if only here in Canada, such as better fuel economy, minimizing the risks of accidents and freeing up manpower for other tasks. On that basis alone it is worth investigating.

[Thucydides]

The Dutch are developing systems to allow vehicles to cooperatively drive, in order to increase carrying capacity on the roads and reduce fuel usage (there is the obligatory bow to the Church of Global Warming in the articel as well). Once again, a system which could make logistics more efficient and reduce some of the financial burden on the CF:

http://www.tno.nl/content.cfm?context=overtno&content=nieuwsbericht&laag1=37&laag2=69&item_id=2013-11-12%2010:35:23.0&Taal=2

Automated driving; from the test track to the public road
Minister Schultz is first to ride in an automatically driven car on a Dutch highway

TNO is working on technology to enable cars and trucks to drive automatically on the highway. Cooperatively and at low cost. Tests on the public road will have to demonstrate that automatic driving boosts traffic safety, improves traffic flow, cuts down on fuel and thereby reduces CO2 emissions.

As part of the official opening of the Innovation Relay at the RAI exhibition centre in Amsterdam on 12 November, Minister Schultz took the first highway test drive in a self-steering car equipped with TNO technology.

Dutch Automated Vehicle InitiativeThe fact that Minister Schultz can now ride on the highway in this way is the result of the Dutch Automated Vehicle Initiative (DAVI) in which TU Delft, TNO, RDW and Connekt are collaborating. A unique aspect of this demonstration is that it concerns automatic, cooperatively driven cars whereby the car drives at a short distance from the car in front, determining the speed itself by communicating with other cars on the road and with the driver not having his hands on the steering wheel. This means that the cars not only have the technology for automatic driving but that they can also communicate through a wireless communication network with other cars and the surrounding infrastructure.

The TNO technology that is applied is both affordable and scalable for the future and can quickly and easily be put into practice. However, public road tests will first have to demonstrate that automatic driving can lead to more comfort, fewer traffic jams and accidents, and less fuel consumption.

Virtual TowbarDriving in ‘train carriages’ is part of automatic driving. Vehicles driving close behind each other reduces fuel consumption, from the last and the first in the train. The transport sector is tracking developments in this area very closely; it hopes that through techniques like trucks driving in columns or ‘platooning’, as the jargon calls it, the sector can stay at the head of its international rivals. This is already possible with two trucks. If two trucks drive close together, 10-20% fuel can be saved, which results in 20% lower CO2 emission. Here, too, public road tests in real traffic will have to demonstrate that the automatic driving of trucks not only makes road transport more efficient and green but also safer. TNO is striving together with the sector and the government to enable such tests to happen in 2014 and 2015.

[S.M.A.]

Won't self-driving cars only encourage people not to learn to drive? 

54 million self-driving cars will be on the road by 2035, study finds

LA Times

By David Undercoffler

January 2, 2014, 10:55 a.m.

Self-driving cars aren’t expected to begin hitting the road until 2020, but a new study predicts that once they’re here, they will quickly become a common sight.

By 2035, nearly 54 million autonomous vehicles will be in consumers’ driveways worldwide and annual sales of the vehicles will reach almost 12 million, according to the study by IHS Automotive. After 2050, the study predicts that nearly all of the vehicles in use -- both personal and commercial -- will be self-driving.

One of the biggest impacts from such widespread use of self-driving cars (SDCs) will be safety, according to the study’s co-author, Egil Juliussen.

“Accident rates will plunge to near zero for SDCs,” said Juliussen, a principal analyst for infotainment and autonomous driver-assisted systems at IHS Automotive.

Though human-driven cars will still crash into autonomous vehicles, “as the market share of SDCs on the highway grows, overall accident rates will decline steadily,” Juliussen said.

Traffic and air pollution will also decline as a result of self-driving cars because their driving patterns will be programmed to minimize their impact on the environment, Juliussen said.

[Fishbone Jones]

So as SDCs multiply and the accident rate drops, so should insurance rates, right?

[Ostrozac]

I would be interested in a self-driving car that will pick me up at the bar and take me home. Or that will drive me to Vegas while I sleep.

A cross between KITT from Knight Rider and the family truckster from Vacation would suit me fine.

[reverse_engineer]

Guess I better buy my corvette while I still can.

[Thucydides]

Audi enters the fray (well the parent company is VW, which should give you an idea of the engineering and market clout behind this). The interesting thing is how quickly the sensors and circuitry has been integrated: no large turret with laser scanners on the roof and no trunk full of CPU's:

http://www.technologyreview.com/news/523351/ces-2014-audi-shows-off-a-compact-brain-for-self-driving-cars/

CES 2014: Audi Shows Off a Compact Brain for Self-Driving Cars
A book-sized computer capable of driving a car could help the technology reach the mass market.

By Tom Simonite on January 7, 2014
WHY IT MATTERS

Automated cars are more likely to catch on if the technology doesn’t compromise sleek automotive designs.


Hands free: The Audi Sport Quattro Laserlight concept car features compact sensor and computing technology that lets the car pilot itself.

Carmaker Audi showed off a book-sized circuit board capable of driving a car on Monday at the International Consumer Electronics Show (CES). Audi claims the computer, called zFAS, represents a significant advance in automation technology because it is compact enough to fit into existing vehicles without compromising design.

Several different Audi vehicles equipped with zFAS drove themselves onto the stage during the presentation, and a new concept car designed to showcase it was also introduced.

The car, called the Audi Sport Quattro Laserlight, is capable of what Ulrich calls “piloted driving” but betrays no outward sign of being different from a conventional vehicle.

“At CES one year ago, the trunk of the demo cars was still full of cables and electronics,” said Audi’s chief technical officer, Ulrich Hackenberg, about the company’s automated driving technology. “The prototype period is almost over. Now it’s time to get ready for serious production.”

Long and mid-range radar systems, several video cameras, a laser scanner, and ultrasonic distance sensors on the front and sides of the car are all small enough to be hidden from view. The best known self-driving cars, the modified Lexus SUVs used by Google, have a large laser scanner visible on top (see “Data Shows Google’s Robot Cars Are Smoother, Safer Drivers Than You or I”).

Audi talked at CES last year about its engineers’ progress in shrinking down laser scanners and other sensors used to monitor the car’s environment (see “Audi Shrinks the Autonomous Car”). Hackenberg said yesterday that his company got help from chipmaker Nvidia on shrinking the zFAS. It is powered by two processors from Nvidia more typically used in tablet computers.

Audi didn’t say when its Piloted Driving technology would be available commercially. No details were provided on the capabilities of a zFAS-enabled car, beyond saying it could drive in traffic and park on its own.

Despite Google’s public cheerleading of automated vehicles, many established automakers have played down the idea that full automation is near, despite several having technology to match or beat Google’s (see “Driverless Cars Are Further Away Than You Think”). However, Audi chairman Rupert Stadler said that people will routinely let their car do the driving for them in the future, and a promotional video was shown in which a chauffeur sat in the passenger seat while the car did the driving. Stadler described Audi’s Piloted Driving technology as moving the company into new territory: “Today we see a period of major changes, in which we are moving from refining the automobile to redefining mobility.”

Audi also announced partnerships with mobile chipmaker Qualcomm, which will be providing 4G LTE wireless chips in some Audi vehicles, and also with Google. Audi is one of several carmakers that have teamed up with the company to develop a car-centric version of the Android mobile operating system, something Stadler said was already bearing fruit in a new interface for an upcoming concept car that customized itself to each driver. “Thanks to our joint efforts with Google, your interface will feel familiar because it is more intuitive than ever,” he said.

[Thucydides]

US army is experimenting with robotic vehicles in a much bigger way. The interesting thing about these tests is they are using kits attached to current vehicles rather than integrating the technology into new vehicles (or prototypes). This topic has also been looked at in the "Robotic Army" thread, and could be used as one approach to dealing with the manpower crunch. Self driving vehicles, robotic warehouse technologies and similar systems could relieve the manpower needs of the military "tail" while leaving the same numbers of men in the "tooth" end of the military:

http://news.cnet.com/8301-11386_3-57618149-76/driverless-trucks-get-in-shape-for-us-army-convoy-duty/?tag=nl.t720&s_cid=t720&ttag=t720&ftag=CADe856116

Driverless trucks get in shape for US Army convoy duty
Recent tests, says Lockheed Martin, show that fully autonomous convoys can safely navigate road intersections, oncoming traffic, stalled and passing vehicles, and pedestrians.

Jonathan Skillings by Jonathan Skillings  January 31, 2014 10:23 AM PST

Google may have the best-known driverless vehicles, but the US Army surely has the largest.

Defense industry heavyweight Lockheed Martin said Thursday that testing has wrapped up on a series of advanced tests in the Autonomous Mobility Appliqué System (AMAS) program for the US Army and US Marine Corps. The testing, Lockheed said, showed that fully autonomous convoys can operate in urban environments and with a mixture of vehicle types.

What challenges did these driverless vehicles face? The trucks had to navigate road intersections, oncoming traffic, stalled and passing vehicles, pedestrians, and traffic circles in test areas both rural and, with less margin for error, urban.

Somewhat like the jury-rigged systems seen on the first generation of robotized cars, the AMAS program for the Pentagon's ground troops uses standard-issue vehicles outfitted with a kit of gear including a high-performance LIDAR sensor and a second GPS receiver, locked and loaded with a range of algorithms. That gear, Lockheed said, could be used on virtually any military vehicle, but in these tests was affixed to the Army's M915 tractor-trailer trucks and to Palletized Loading System vehicles. (The photo above shows a pair of PLS road warriors followed by an M915.)

AMAS-equipped vehicles can still be operated manually by human drivers, and the sensing and control function in a truck in self-driving mode should alert its occupants to safety threats.

Consumers and businesses can't go out and buy robo-cars just yet, but the era of driverless rides is nearly upon us. Google has been front and center in the effort to integrate robo-cars into real-world environments, and a range of automakers, from Nissan and Lexus to Audi and GM, have been getting in on the game.

Meanwhile, a handful of states -- California, Nevada, and Florida -- have made it legal to test driverless cars on public roads. The latest round of AMAS testing, though, took place earlier this month in the wide open, and much less public, environs of Fort Hood, Texas.

Convoys are commonplace arrangements for military vehicles, of course, but research shows that similar platooning of civilian vehicles could save fuel, fit more cars on the road, and even improve road safety.

"The AMAS CAD hardware and software performed exactly as designed, and dealt successfully with all of the real-world obstacles that a real-world convoy would encounter," David Simon, AMAS program manager for Lockheed Martin Missiles and Fire Control, said in a statement. (In this case, CAD refers to the Capabilities Advancement Demonstration portion of the AMAS program, not to computer-aided design.)

The development and testing of the AMAS platform stems from an $11 million contract that Lockheed Martin received from the Defense Department in October 2012.

AMAS algorithms also are used to control the company's Squad Mission Support System, a more distinctive and less conventional six-wheeled unmanned ground vehicle that has been used by soldiers in Afghanistan.

[Thucydides]

Perhaps this could also go into a thread on politics or economics, but the large scale advent of self driving vehicles will have many knock off effects throughout society:

http://www.the-american-interest.com/blog/2014/01/25/robo-chauffeurs-could-kill-public-transit-as-we-know-it/

Robo-Chauffeurs Could Kill Public Transit As We Know It

Whether or not self-driving cars are the future of public transportation, at the very least they will change the logic of large public transportation projects: a fleet of robo-cars could one day deliver personalized, decentralized public transportation. But what does that mean for our cities’s buses and trains? The Atlantic Cities reports:

We make billion-dollar investments in new transit infrastructure because we expect to use it for decades. Metropolitan planning organizations are in the very business of planning 30 and 40 years into the future. The Washington Area Metropolitan Transit Authority recently released its dream map of subway service in the city for the year 2040. By then, autonomous cars – in some form – will surely be commonplace.

The question of what they’ll mean for transit was actually on the program this year at the Transportation Research Board annual meeting in Washington, where several thousand transportation officials and researchers met to talk about state-of-the-art asphalts, biker behavior, and the infrastructure of the future. In one packed session, I heard Jerome Lutin, a retired longtime New Jersey Transit planner, say something that sounded almost like blasphemy.

“We’re just wringing our hands, and we’re going to object to this,” he warned the room. “But the transit industry needs to promote shared-use autonomous cars as a replacement for transit on many bus routes and for service to persons with disabilities.”

A recent study by IHS Automotive predicted that nearly every car on the road in 2050 will be self-driving; in that kind of world, in which our nation’s highways are populated by hordes of self-driving vehicles packed tightly together at higher speeds and with greater fuel efficiency, massive investments in rail infrastructure or new bus networks won’t make much sense. But these investments are already being made in places like California, which is already massively over-budget on a high-speed rail project that will be obsolete from its first day of operation.

The pace of technological progress is accelerating, and city planners can’t keep up. Self-driving cars are the latest and greatest transportation option, but who can guess what will replace them in the coming decades? A nation criss-crossed with Hyperloops? Ubiquitous telepresence technology? In this respect, we’re more uncertain about the future than we ever have been, and that’s a huge problem for those making decisions about public transit. One thing is obvious, though: we shouldn’t be building for the future with technology that’s already outdated. Looking at you California.

[MCG]

The US is considering mandating that all cars include situational awareness technology to predict and avoid collisions.  It is not the self-driving vehicle, but this move (if it happens) will likely begin the advancement of the technology at a faster rate. 

U.S. may force cars to communicate with each other
 Computer would alert driver to impending collision
The Associated Press on CBC News
03 February 2014

Raising hopes of preventing many collisions, U.S. transportation officials say they'll propose requiring that automakers equip new cars and light trucks with technology that lets vehicles communicate with each other,

U.S. Transportation Secretary Anthony Foxx said Monday the technology holds the potential to significantly reduce crashes, injuries and deaths on the nation's streets and highways.

A radio transponder would continually transmit a vehicle's position, heading, speed and other information. Cars would receive the same information back from other vehicles, and a vehicle's computer would alert the driver to an impending collision.

The government will issue a report later this month outlining its research on the new systems, and will issue its proposed rule before the end of the Obama administration.

http://www.cbc.ca/news/technology/u-s-may-force-cars-to-communicate-with-each-other-1.2521562

[Thucydides]

Mods: not sure what happened but the thread seems to have been split into two self driving vehicle threads...

[Thucydides]

Going the next level: self driving personal air vehicles (AKA flying cars). The technology is there, but does a market yet exist?

http://www.bbc.com/future/story/20131031-a-flying-car-for-everyone

Why everyone may have a personal air vehicle
Technology Science & Environment Aircraft Automobile Robot Transport

The idea of having a part car, part plane, part drone parked outside your home may not be as far-fetched as it seems. There really aren’t any technological hurdles to this.

We are going to have personal air vehicles that are both cars and planes, at least that’s Missy Cummings’s vision of the future. It’s basically the intersection of a drone with a robotic car, so that your plane is also your car, but the big leap in technology is that you are actually driving neither, says the Associate Professor of Aeronautics and Astronautics at the Massachusetts Institute of Technology.

Drones have a negative bias in the media, says Cummings, because they are essentially seen as spy cameras. But most people don’t realise that when they are on a plane they are effectively travelling on a drone. The fly-by-wire technology that exists on all Airbus and many Boeing craft is the exact same technology that exists on drones.

The reason why drones are the answer to the future is that the truth is we are terrible drivers. Humans inherently have a half-second lag in almost any quick response that they need to have, like a ball rolling out in a street or seeing an aircraft in the sky and you have to take evasive action. Even a half-second delay can mean the difference between life and death, and computers and automated systems don’t have that – they have microseconds.

So, our transportation network of the future, both on the ground and in the air, will actually be safer when we turn it over to computers.

There really aren’t any technological hurdles to this idea, says Cummings. The biggest hurdles we have are psychological and cultural, in terms of giving up the car. But no new tech needs to be developed to have your own personal flying car. What we have to do is improve production and reduce manufacturing costs, and what that means is that we need more robots. So this is almost a self-circular process, where we need robots to build robots to make them cheaper.

Should we worry about the machines rising up and taking over? No, what Cummings says she is worried about is hackers and terrorists who want to do wrong. One of the things she is working on is trying to develop technology that allows any flying robot to be able to fend off any attack and be able to navigate itself without any GPS or any other external signal.

There are lots of different possibilities for what your personal air vehicle could look like. You could own your own in your driveway or garage, and you could jump in it. Or we could have a shared network like the plane version of Zipcar. People should be excited about this: it promises much in terms of safer travel, and in parts of the world where the road and air networks are poor, people will be able to get the goods and services they need.

So, when we look at globalising this concept of personal air vehicles, it means we will see the quality of life improve dramatically for everyone around the world.

For more World-Changing Ideas, click here.

[Thucydides]

More on why self driving vehicles would be a good fit for the military. Sending people on taskings in a self driving would reduce the risks of accidents and injury to our personnel, not to mention civilians or other forces sharing the roads:

http://reason.com/blog/2014/06/10/robot-cars-are-a-moral-imperative

Robot Cars Are a Moral Imperative
Ronald Bailey|Jun. 10, 2014 9:47 am

So tweeted tech venture capitalist Marc Andreessen after the crash that injured and killed comedians traveling on a New Jersey highway with Saturday Night Live star Tracy Morgan earlier this week. More than 90 percent of all traffic accidents are the result of human error. The New York Times is reporting the recent findings by Virginia Tech researchers who are estimating how many fewer deaths and accidents would occur with enhanced driving technologies. From the Times:

But two studies by researchers at Virginia Tech — H. Clay Gabler, a professor of biomedical engineering, and Kristofer D. Kusano, a research associate — suggest how much safer robot cars might be. They found that even cars that are not fully autonomous but which automate some of the most dangerous aspects of driving could have as big an effect as seatbelts have had...

They found that lane-departure warning systems would have prevented 30.3 percent of the crashes caused by lane drifting, and 25.8 percent of the injuries. Rear-end and collision warning systems and automatic braking would have prevented only 3.2 percent to 7.7 percent of crashes, but would have reduced their severity. The number of people injured or killed would have declined in the range of 29 to 50 percent, the researchers concluded.

By comparison, seatbelts have reduced injuries and fatalities by about 50 percent, and are considered the most beneficial auto safety measure of all time, Mr. Gabler said.

In 2012, more than 33,000 people were killed in traffic accidents in the United States. In April, the free-market think tank, the Competitive Enterprise Institute issued a report reviewing the effects that regulation might have on the introduction of self-driving vehicles and warned:

Policy makers must remember that their actions can produce harm. If automated vehicles are demonstrated to be significantly safer than manually driven vehicles, any misstep, convoluted law, or rule that leads to unnecessary higher costs or delays translates to increased injury and death.

The next generation will be shocked at the carnage that we tolerated during the primitive era in which people were actually allowed to drive themselves down highways.

[Tollis]

Obviously I'm all for saving lives, but all I can picture with this is me trucking myself through the mud to hook up a stuck Unmanned vehicle because I have no drivers to send into the hole during a recovery.

[Thucydides]

For field use, I think the vehicles will be in a "follow the leader" formation, with at least one maned truck and the remainder following. The other solution would be that crew is in the vehicle for duties like maintaining, manning the guns and loading/unloading, but driving is optional (and automated for the most part).