More on Google’s self-driving car program

Stanford’s Sebastian Thrun is my hero for steering the Stanford DARPA Urban Challenge project to success. Thrun is one of the hired-guns on Google’s high intensity project (think a bit on the technologies that might enable robo-cars: the synergy of AI + mobile + localization + GIS database). I am very curious how much of the Google robo-car algorithms depend on real-time data coming down from their cloud. Nobody can match Google’s cloud for auto-driving:

(…) So we have developed technology for cars that can drive themselves. 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.

Our automated cars 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.


Read more »

Google self-driving cars

Charles just sent us the link to this NYT Science article on Google’s self-driving car program. We’ve been following the Stanford-Volkswagen program — I did not know that Google was participating. Is Sebastian Thrun now a Google employee? Sebastian lead Stanford’s “Stanley” DARPA Grand Challenge project.

(…) During a half-hour drive beginning on Google’s campus 35 miles south of San Francisco last Wednesday, a Prius equipped with a variety of sensors and following a route programmed into the GPS navigation system nimbly accelerated in the entrance lane and merged into fast-moving traffic on Highway 101, the freeway through Silicon Valley.

It drove at the speed limit, which it knew because the limit for every road is included in its database, and left the freeway several exits later. The device atop the car produced a detailed map of the environment.

The car then drove in city traffic through Mountain View, stopping for lights and stop signs, as well as making announcements like “approaching a crosswalk” (to warn the human at the wheel) or “turn ahead” in a pleasant female voice. This same pleasant voice would, engineers said, alert the driver if a master control system detected anything amiss with the various sensors.

Astrobotic lander advances to all-composite design

If I were betting on this X Prize competition I would have to pick “Red” Whittaker’s team Astrobotic (the Carnegie Mellon University spinoff). They’ve been testing the third generation prototype of their Astrobotic Moon robot, Red Rover on a Pittsburgh slag heap. The cool photo above has obviously had Photoshop help with the background:-)

The Astrobotic lander has evolved to an all-composite design, with new locations to attach third-party payloads. The Payload Specifications document has been updated and can be downloaded here.

The all-composite design achieves gains in stiffness and reductions in mass. The added stiffness raises the frequency at which it resonates, so that lower-frequency vibrations from the launch vehicle won’t set up compounded shaking that would destroy the lander and rover. The mass required for the all-composite lander may be half that predicted for a metal or metal-composite hybrid. This savings is being booked as margin available to solve engineering issues, rather than as increased payload capability.

The lander will be constructed from just seven shapes, none of them larger than the walk-in oven the team is using to cure its composite parts.

And from today’s press release, more description of the Red Rover design and missions:

Astrobotic and CMU are now testing a prototype robot engineered to operate during extreme heat, and to survive lunar night. Soil temperatures at the lunar equator hit 224 degrees F at noon, cooking the rover from below as the Sun bakes it from above. The rover has a hot side with solar panels that it keeps pointed toward the Sun, and a cold side with a radiator that it keeps pointed at black sky. Cameras on top can turn 180 degrees so that operators on Earth can see the path ahead regardless of whether the rover is rolling forward away from the Sun or backward toward it. Lunar night is as cold as liquid nitrogen. Being able to survive lunar night extends the mission to another lunar day, and the Google competition pays a bonus for operating after enduring the night.

The rover weighs 160 lbs. and is about five feet tall. Its “Tranquility Trek” mission to the Apollo 11 site is expected to last 10-12 days, until sunset cuts off solar power and the rover hibernates at temperatures expected to go as low as minus 298 degrees F. The robot will awake for further exploration two weeks later when the Sun rises, unless the extreme cold has damaged the electronics.

Subsequent Astrobotic lunar expeditions will prospect for the water ice and other volatiles at the Moon’s poles, which can be transformed into propellant to refuel spacecraft for return flights to Earth, doubling the productivity of human missions. Astrobotic has just completed the first phase of a NASA contract to design lightweight robotic excavators that can remove the dry insulating soil that covers some of these valuable deposits.

Interview with Peter Diamandis

h+ Magazine has a short interview by Alex Lightman with X Prize founder Peter Diamandis. Most of the discussion is around Peter’s new project Singularity University. Web publishing of selected lecture videos sounds smart — it has worked well for TED:

h+: Is there a way that someone reading this article right now can get involved with SU?

PD: We’re going to allow people to participate online and view some of the lectures online, like TED does. And we’re going to encourage people to attend day and 10-day programs, as well as nine-week programs. The first nine-week graduate student program starts on June 27th, and runs through the end of August. And the first three-day and ten-day programs will take place probably in October.

Moon 2.0: the Google Lunar X Prize

“…and this time we’re planning to stay!”

Moon 1.0 was abandoned 35 years ago in 1972. Don’t miss the very, very cool rollout video for Moon 2.0. The $30 million Google Lunar X Prize is the largest total science-prize so far announced [see below for partial listing]. The competition guidlines:

To win the Google Lunar X PRIZE, a team must successfully land a privately funded craft on the lunar surface and survive long enough to complete the mission goals of roaming about the lunar surface for at least 500 meters and sending a defined data package, called a “Mooncast”, back to Earth.

PRIZES: The total purse of the Google Lunar X PRIZE is $30 million (USD).

• GRAND PRIZE: A $20 million Grand Prize will be awarded to the team that can soft land a craft on the Moon that roams for at least 500 meters and transmits a Mooncast back to Earth. The Grand Prize is $20M until December 31st 2012; thereafter it will drop to $15M until December 31st 2014 at which point the competition will be terminated unless extended by Google and the X PRIZE Foundation

• SECOND PRIZE: A $5 million Second Prize will be offered as well, providing an extra incentive for teams to continue to compete, and increasing the possibility that multiple teams will succeed. Second place will be available until December 31st 2014 at which point the competition will be terminated unless extended by Google and the X PRIZE Foundation

• BONUSES: An additional $5 million in bonus prizes can be won by successfully completing additional mission tasks such as roving longer distances (> 5,000 meters), imaging man made artifacts (e.g. Apollo hardware), discovering water ice, and/or surviving through a frigid lunar night (approximately 14.5 Earth days). The competing lunar spacecraft will be equipped with high-definition video and still cameras, and will send images and data to Earth, which the public will be able to view on the Google Lunar X PRIZE website.


So we now have another excellent test-bed for the power of science/technology prizes. Regular readers know we believe such prize competitions are hugely more effective than government-funded R&D. The success of the DARPA Grand Challenge and the Ansari X Prize provide anecdotal evidence of effectiveness. Over the next five years we should have more definitive evidence as we analyze the successes in relation to their public costs. Here’s a sampling of the announced competitions, some of which are multiple prizes:

• Google Lunar X Prize,
• Space Elevator Challenge
• DARPA Urban Challenge,
• Automotive X Prize,
• Lunar Lander Challenge,
• Archon X PRIZE for Genomics
• NASA’s Centennial Challenges

And Carnegie Mellon has already put their hat in the ring. Can Stanford’s AI Lab be far behind?