IROS gets earful on Google's self-driving cars (w/ video)

Google's self-driving car
Google's self-driving car

(PhysOrg.com) -- Lots of people now know about Google's self-driving car project. The latest stats find Google's fleet of robotic vehicles have done over 190,000 miles with only occasional human intervention. The company has welcomed favorable news inquiries, from mainstream TV interviews to newspaper reporters, that their self-driving cars can make it on their own on the roads, even in city traffic. How do the cars maintain safety amongst other vehicles, pedestrians, and traffic lights? What people generally know is that the vehicles are "cloud computing" cars that run along on sensors, cameras, artificial intelligence, and GPS.

The latest overview about these cars was presented recently in a keynote speech at the IEEE International Conference on and Systems in San Francisco. Stanford University professor Sebastian Thrun, who guides the project, and engineer Chris Urmson, who is the project’s tech lead, walked the audience through some performance specifics.

What, then, makes the so successful in obeying traffic rules and avoiding obstacles? A laser range finder mounted on the roof of the car is a core component. This is a Velodyne 64-beam laser that generates a detailed 3-D map of the environment. The car then combines the laser measurements with high-resolution maps of the world, producing different types of data models. The vehicle carries four radars, mounted on the front and rear bumpers, that allow the car to "see" far enough to deal with fast traffic on freeways; a camera near the rear-view mirror, that detects ; and a GPS, inertial measurement unit, and wheel encoder,

It’s quite possible, however, that some people may find it entirely difficult to believe driverless cars will be a part of the six o clock commute drive home, a part of the wearying ordeal of staying safe from erratic drivers, tricky intersections, and last-second decision makers in neighboring lanes.

At the IEEE event, the Google pair showed footage that makes a convincing case for the advantages of riding in self-driving cars. The audience saw the on-board computer and how it detects other cars, pedestrians, and traffic lights. The video shows also how the car behaves at an intersection. After the light turned green, the car starts to make a turn, but if cross, the car yields to them. The car also yields to a man who decides to cross at the last minute. At a four-way intersection, the car yields to other vehicles based on road rules; if other cars do not reciprocate, it advances a bit to show to the other drivers its intention. Without programming that kind of behavior, Urmson said, it would be impossible for the robot car to drive in the real world.

Thrun, who came to work on the Google project from Stanford, has all along hammered home a message that driving accidents are the number one cause of death for young people and many of the accidents are due to human error. Thrun believes that robotics, not humans, can do the better job in making driving decisions and sparing lives.

That does not sound so crazy to the state of Nevada, which earlier this year passed a law authorizing the Department of Transportation to develop rules to govern driverless cars. Nevada’s bill sets the framework for "authorizing... the operation of, and a driver’s license endorsement for operators of, autonomous vehicles."

Thrun and Urmson talk of many challenges ahead in the future of driverless vehicles, including sorting out legal and liability issues. Still, there’s no looking back.


Explore further

With human behind wheel, Google's self-driving car crashes

More information: via IEEE Spectrum

© 2011 PhysOrg.com

Citation: IROS gets earful on Google's self-driving cars (w/ video) (2011, October 19) retrieved 15 September 2019 from https://phys.org/news/2011-10-iros-earful-google-self-driving-cars.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
0 shares

Feedback to editors

User comments

Oct 19, 2011
eventually autonomous vehicles will have to arbitrate for priority (at intersections and for lane changes). Buses are better for the environment in terms of efficiency, and will be bus masters (release on request). I foresee human nature intervening and rich people buying higher priority.

Oct 19, 2011
Driving isn't fun. There's lots of stuff I'd rather be doing. I'm looking forward to when this sort of technology is available. I wonder how hard the hard parts are going to be?

For instance:

A ball rolls out from between two parked cars.

A paper bag is blown out from between two parked cars.

A bunch of leaves are blown out from between two parked cars.

Oct 19, 2011
A ball rolls out from between two parked cars.

This would probably be handled like the case described in the article about a man making a last second decision to cros the road.

A paper bag is blown out from between two parked cars. I#d hate to become a statistic.

A bunch of leaves are blown out from between two parked cars.

Neither of these are frequent (or even modestly infrequent) situations. But I would suspect that if the radar detects something that is not connected to the ground it could well assume that the object isn't massive and simply keep going.

Thi would, however, mean that the car doesn't evade the occasional bowling ball / steel girder falling off a truck...But those incidences are also so rare that we might be able to accept the 'collateral damage' if the overall number of fatal accidents decreases sharply.

The only thing I find difficult to accept is that accidents then become a matter of statistics - not driver quality.


Oct 19, 2011
Quite impressive.

I'd love if they talked some about instances where the system has failed or more generally, areas the system currently has trouble with.

Oct 19, 2011
PHYSORG MODERATORS:

Please do not let Peter Cao turn into another Omatumr. If you don't stop him now he will take over every topic that is even tangentially related to Google. How often does this site publish articles on google? A lot.

Oct 19, 2011
*facepalm* talk about spam. There should be a limit to the number of posts you can make in a given time frame/sequence on one topic. I'm not even going to bother reading what he said.

Dug
Oct 20, 2011
I'm thinking of numerous software issues that have plagued both MS and Apple OS and programs - some for decades without being addressed, corrected or resolved, and are still there in spite of almost universal complaints by knowledgeable users. I wonder how many of these kinds of glitches will show up in driverless car software? I suspect there will be a lot of unacceptable collateral damage - that we will be ignored by mfgrs. - just as we are with current computer software programs and OS malfunctions. If you want to be a passenger in a vehicle that is essentially driverless - take a train.

Oct 31, 2011
It probably uses a weak radar but I fear the results if every car on the road had four radar transmitters mounted to it. At some point, our abilities to withstand EM radiation might be exceeded by the amount we produce

Nov 07, 2011
Hey Peter, I think your time would be better spent complaining about a company who is hoarding money and negatively impacting our world. Google is helping to build the technology we will come to rely on over the course of our future. Their x-prize creates incentive to pursue world changing technologies. Their privacy infringing behaviors make searching the web a lot easier. *rolls a ball past you towards Monsanto* Ohh, look at the ball, what's that company, it's a bad company, even worse than Google, go get the ball.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more