Author Archives: driverlessuser

Intelligent vehicle symposium showcases advances in driverless technology

Posted on by

Driverless technology researchers gathered at the beginning of June for the IEEE Intelligent Vehicles Symposium. With almost 200 presentations from more than 600 authors probably no aspect of this technology was left untouched.

This was not just an academic get-together: many of the papers involved major car makers (BMW, Toyota, Daimler, Renault, Volvo, Opel, Volkswagen, General Motors, Hyundai) or automotive suppliers (Delphi, Bosch).

The conference started with a reportedly captivating keynote presentation by Google’s Chris Urmson. Unfortunately, I have not been able to obtain more detailed information about its content. Please contact me if you were there!! Robert Bertini (Intelligent Transportation Systems Lab) gave another keynote on the environmental issues related to intelligent transportation which took the perspective beyond technical issues towards societal and environmental impacts.

It is hard to pick out the most interesting papers. But Daimler presented a new approach for improving stereo vision using a ‘Stixel’-based approach for object recognition. They claim that they are able to reduce false positives by a factor of 8 over the state of the art while reducing the computational costs by a factor of 10.

China  also seems to be moving ahead with driverless technology. Two papers (1, 2) were presented from participants of the annual Chinese driverless vehicle competition (‘ Future Challenge of Intelligent Vehicles’) funded by their National Nature Science Foundation.

Several papers focused on pedestrian modeling and recognition. Volkswagen described their approach to systematically drive an autonomous car at the vehicle’s handling limits. DLR presented an approach to apply autonomous vehicles localization technology to trains.

The symposium was located in Alcala de Henares, Spain. It also included demonstrations of autonomous vehicle systems.

Stanford course on the Future of the Automobile

Posted on by

Intelligent vehicles were the main topic of a 1-unit Stanford course from April to June. The course included guest lectures from Volkswagen Research (pdf), Hyundai (pdf), Volvo (pdf) and Bosch (pdf) and addressed technical, legal and some societal aspects of autonomous vehicle technology.

The course was offered by Sven Beiker and Chris Gerdes, both from Stanford’s Center for Automotive Research (CARS). Some of the key insights provided in the class:

  • Carsharing would benefit a lot – autonomous vehicles could be used by carsharing service providers as soon as 2018
  • Completely autonomous vehicles might be available by 2030 (this somewhat contradicts expected use in carsharing by 2018)
  • Over your lifetime you will spend about 1000 days in a car!
  • Autonomous cars and inter-car communication systems should evolve together; however it is difficult to impose new standards
  • The technology is advancing quickly

It is interesting, however, that the economic and business impacts of driverless technology seem to have been mostly absent from the course presentations (with the exception of a few bullet points in the final session). Issues such as how driverless technology might impact the cost of mobility,  what impacts driverless cars would have on the structure of the car industry, and on new business models and services were not addressed.

Nevertheless this has been an excellent course. I highly recommend taking a look at the  syllabus and the many excellent course presentations in PDF format.

 

 

Traffic accidents are among top leading causes of death

Posted on by

A recent study by the National Highway Traffic Safety Administration (NHTSA) shows how dangerous motorized traffic is: Traffic accidents continue to be the leading cause of death for the age groups from 8 to 24 years! If the number of years lost are considered, then traffic deaths are at positions four in the year 2008 and five in 2009 among the leading causes of death for all age groups. Many accidents involve alcohol or human error. Many such accidents would not occur if the development and introduction of autonomous vehicle technology would be accelerated.

We should stop thinking about incremental measures to reduce traffic deaths by a few percent. Instead, we should aim to reduce it by at least a factor of three. Autonomous vehicle technology clearly has this potential!

Click the graphic to enlarge the image. Source: NHTSA

 

Automakers trying to slow down Google

Posted on by

Does Google’s driverless car technology threaten established car manufacturers? They clearly seem to think so: Lobbyists of the Alliance of Automobile Manufactures have succeeded in throwing a wrench into the process of legalising autonomous cars in California. Because of their concerns about liability issues, the Senate Transportation Committee decided to route the bill to the Rules Committee where it will possibly be assigned to another panel for further review on liability. This could mean a significant delay for California’s bill and puts into question whether California could become a key state in driverless car introduction. It looks like Nevada will keep this crown for some time.

Google has repeatedly lamented that car manufacturers show little interest in driverless car technology. This is not surprising because driverless cars will greatly reduce the total number of cars needed. Given that private vehicles currently sit idle more than 95 percent of the time, the total number of cars needed could conceivably shrink by a factor of 10!

This action by the Alliance of Automobile Manufactures is only a harbinger of things to come. As driverless technology matures, the fight will get nastier. But the public can only benefit from driverless cars: Countless lives saved, lower total transportation costs and greater mobility for the elderly and young. Automakers need to prepare for this future now. Closing the eyes and trying to prevent the inevitable is the wrong strategy.

Blind driver: Self-driving cars give me the indepence to go where I want to go

Posted on by

Steve Mahan, a blind person, makes a strong appeal for driverless cars in a video released by Google. The video shows Mr Mahan in the driver’s seat of their autonomous Prius completing what for others may look like everyday chores but what for some groups of our society is extremely hard: Pickung up laundry from the cleaners, fetching something to eat at an arbitrary fast-food restaurant.

The freedom to move is a great accomplishment of modern society. Young people anxiously look forward to the time when they can drive around on their own, going wherever they want. But we forget that large groups are excluded from this freedom: Those with disabilities, the elderly (who may find it hard to continue living in their own home when they can no longer drive a car), the young (whose parents often find themselves in the role of personal chauffeur) and the poor who can not afford their own car.


Source: ABC News

Google’s low-cost PR video clearly outlines a major benefit of self-driving vehicles and is an attempt at shaping the public debate. This is crucial for any company before bringing a new technology into the market. While the Google car may still be a few years away, this video shows that the strategists at Google are carefully laying the groundwork for that occasion.

Continental tests its autonomous vehicle technology in Nevada

Posted on by

Driverless cars are heading to Nevada: Continental Automotive Group, a subsidiary of the German automotive technology supplier, revealed last week that it has started test driving a modified Volkswagen Passat on Nevada’s streets (both city roads and highways). The Passat has been equipped with Continental’s technology for highly automated driving. It has driven more than 6000 miles on city streets and highways, 90% in autonomous mode. Once it passes the state-required 10 000 mile minimum test-drive limit, the car could become one of the first to receive an autonomous car license in the Silver State.

Continental's Automated Passat

(Image source: Continental)

In contrast to the Google car, the Passat is not intended for autonomous operation at all times. It is a test bed for for Continental’s automated highway and traffic jam technology which can alleviate the human driver from boring driving situations. The close-to-production technology is also much cheaper than Google’s driverless car technology because it does not involve a costly LIDAR sensor.

With Continental another major player has publicly entered the race for driverless car technology. Whereas car makers are still dragging their feet on the technology because of doubts about cannibalizing their product lines, the business case is much more favorable for automotive technology suppliers. Delphi, Valeo and the likes will not be far behind…

 

 

 

HDI Gerling first insurance company to insure a driverless car

Posted on by

Liability is often seen as one of the Achilles heels for driverless cars: Even if they are vastly safer than human-driven cars, any accident could lead to huge claims. Many fear that this may make it difficult for obtaining an insurance policy for autonomous vehicles.

Current autonomous car prototypes already operate in various countries in test mode and for them the issue of obtaining appropriate insurance is very real. We have just learned that the German MIG (‘Made In Germany’) prototype driverless vehicle which currently roams the roads of Berlin is being insured by HDI Gerling Industrial Insurance for damages of up to 100 Mio Euros. HDI Gerling, a subsidiary of the European Talanx insurance conglomerate, may thus have become the first insurer worldwide to insure a driverless vehicle.

Of course this policy is for test driving only and requires a backup driver behind the wheel who is able to take over from autonomous mode at any time. Nevertheless, the policy shows that insurance companies are beginning to take notice and marks another step forward in the push to market for driverless vehicles.

The fact that the Autonomo team (directed by Raúl Rojas) developing the prototype was able to secure a policy for its car shows that the huge claims problem may be over-rated: Insurers world wide are experts at calculating risk. They will not shrink from insuring autonomous cars. Once their safety has been tested and certified they will most likely be glad to insure autonomous cars. The cars will pose  much lower risks than human driven vehicles but – at least initially – the insurers will be able to over-emphasize the huge claims problem and command very healthy premiums, making this a very profitable business.

INRIA aiming to develop driverless car in Paris

Posted on by

French research powerhouse INRIA intensifies their research on autonomous vehicles. Having participated in various EU projects (Cybercar, Cybercars2, HaveIT) which looked at intelligent transport systems where coordination between cars played a major role and various aspects of driver-assistance systems, they appear to readjust their focus on individual autonomous cars driving in urban traffic. They are offering a 3-year research position for developing a prototype (and completing a doctoral thesis). This work will include cooperation with business partner Valeo, a one-stop provider of all types of sensors needed for autonomous driving.

The project’s initial goal is to develop an autonomous vehicle for driving at slow speeds in urban settings on private roads around Paris. They will have a lot of work to do to catch up to Google’s self-driving car.

Don’t stop at the stoplight: Intersection management for driverless cars

Posted on by

Driverless cars will fundamentally change mobility in more ways than we can imagine today. Researchers from the University of Texas at Austin have taken a hard look at how driverless cars could best negotiate intersections: The classic stoplight would be highly inefficient in a world comprised of only driverless cars. Therefore they have developed algorithms for managing the flow of cars at busy intersections. Cars would signal their arrival at an intersection to an intersection manager and request to pass the intersection. The intersection manager then looks for conflicts with other cars and allocates a time slot for for passing the intersection at a specified speed. This approach is over a 100 times more efficient than the classic stoplight and could greatly reduce congestion, driving times, and petrol consumption in city traffic. A simulation is shown below:

It will certainly take decades until only driverless cars will roam the streets. But intersection management could be implemented long before that time: Once a significant percentage of cars are autonomous, intersection managers could be added to stoplights and issue permissions to those autonomous cars that are at the front of the queue.

Overall this research by Peter Stone and his co-workers shows that driverless car technology holds much potential for improving traffic flow and reducing resource consumption.

More information: Article, Autonomous Intersection Management web site

Hawaii and California driverless car legislation picking up speed

Posted on by

A resolution to ask the Department of Transportation to review policies and offer suggestions for driverless car legislation prior to 2013 has been introduced by 20 members of Hawaiis House of Representatives.

Driverless vehicle home-state California may be moving ahead quicker: Senator Padilla has introduced bill SB 1298 to remove remaining hurdles for testing and operating autonomous cars in California. The bill would allow the operation of driverless cars on public roads, provided that “the manufacturer certifies that the vehicle meets all of the safety standards and performance requirements to be specified by the department [of the California Highway Patrol]”.

If this bill is adopted, California could leap-frog Nevada to become the key state for operating driverless cars. Nevada already has approved legislation for the operation of driverless cars, but this is limited to state highways whereas the California bill does not contain such a restriction. California is not only the home-state of the Google driverless car group but also has has research groups from major automotive manufacturers such as BMW and Volkswagen.

Europe still seems to be asleep. Although the European Union has long encouraged the development of driverless technology, and France, Italy and Germany have very active research groups, they may have hard a time catching up once the train is out of the station.