Stanford’s Robot Car to Drive from SF to LA Next Spring
Prof. Sebastian Thrun at Stanford University is world famous for leading a team of students and engineers to develop an autonomous car that won the DARPA Grand Challenge in 2005. The history making car “Stanley” now resides at the Smithsonian.
Since then, his next mission was set to develop a vehicle that can achieve urban driving. The team went on to develop “Junior” and during that process in 2007, won second place in the Urban Challenge. But the goal had always been grander – to create a car that can drive itself from downtown San Francisco to downtown Los Angeles without human intervention.
GetRobo got to chat with Prof. Thrun on the phone to get an update on this project and learned that he now plans to accomplish this goal by next spring. The following is an edited version of the interview. (Photograph from Oct. 2007)
Q. The last time we talked, you were working on developing a fully autonomous vehicle that can drive on its own from San Francisco to Los Angeles. Can you give us an update on this project?
A. The project is underway and we are making good progress. For example, we are now able to handle traffic lights and to localize reliably on highways, which is important for lane keeping. We can now speed up the vehicle in traffic. Also we are much better able to track the other cars around us and we can find and identify pedestrians.
There are a few open problems that we haven’t solved including merging and lane changing that need some work. Then we have to start doing large-scale experiments on the road to see what other problems exist.
Q. Has your car already been driving autonomously on regular roads?
A. Yes, we have done many experiments on public roads. We always have a safety driver in the car who can take over just by grabbing the steering wheel. And he can disengage any point in time. And we have a safety computer engineer on board, who monitors the systems. There has never been a close call or anything like that. It is totally safe to do this.
Q. Has the car already attempted a trip from SF to LA?
A. No. We are gearing up for this. We are making good progress but we are not there yet. Certain behaviors on highways, such as mergers, lane shifts and exiting, entering ramps are still not ready. And I’m sure as we start tackling long distances, we will find more and more problems that we have to solve.
Q. If you were to measure your progress on a scale of one to ten, and your goal being ten, where are you at now? And when do you plan to do the full-blown experiment from SF to LA?
A. We are at seven. And we plan on doing it by spring of next year.
Q. Once you are ready, do you need to get permission from some entity to go ahead?
A. We will inquire with the university to make sure everything is fine. Last time we inquired, the belief was that this was actually very consistent with the existing law because there is a driver behind the steering wheel and the driver can take control of the vehicle anytime. That means the driver is fully responsible. Our system is basically the same as cruise control except that ours has the steering wheel involved. We had an internal finding with Stanford Risk Assessment and what they found seems to be that this was going to work and that it does not require special approval.
Q. How different is the new car compared to Junior that competed in the Urban Challenge?
A. The car basically is Junior. We had 2 versions of Junior. The original Junior is with Volkswagen of Germany. But we had an identical replica and that is what we are using right now. What we’ve done is we’ve added a few more sensors. In particular we now have more radars and we are using them more extensively. We have a new stereo camera system too.
Q. So what you are doing is writing more and more code to make Junior more intelligent.
A. Exactly.
Q. Will we as reporters be able to cover this event?
A. I hope so.
Q. Will you be announcing beforehand on when you will be doing this?
A. We have not discussed that far in terms of what may happen. It might be a case where we drive it just among us and make a public event afterwards. Our partners, including Bosch and Volkswagen, need to make the assessments.
Q. Are you aware of any other projects in the world where they are developing autonomous cars for urban driving?
A. There are a number of research labs that pursue a world toward more autonomous cars. There are German companies working on lane keeping technologies now, and if you put lane-keeping and adaptive cruise control technology together, you effectively have a system where you can stay in the lane at moderate speed. I have zero clue on where these people are testing, but people are testing.
Q. In 2007, you predicted that it would take about 20 years for a fully autonomous car to be commercialized. Has that view changed?
A. Yes, the number is shrinking. The question is what “fully” means. I believe we are going to see in the next 7 to 8 years, products that assist people on highways in a fully autonomous fashion, where you get on a highway, stay on the lane, get to a predetermined exit without you doing anything.
The more difficult application is going to be the urban driving part - driving inside the city. There are a number of reasons why the city is more difficult. The diversity of objects is much more complex, the difference of speed between different vehicles is much larger and there is the element of unpredictability - kids running around on the streets. In this area it’s going to be 20 years out. There’s no question about that.
Q. Tell us about Stanford’s new center CARS.
A. The center was created about a year ago and I am one of the 3 founding professors. Our mission is to bring together people from different disciplines including humanities to really understand how to change car based transportation. Research areas would include autonomous driving, safer cars and energy-efficient cars. Also the center will study human factors like what type of vehicles people will actually want to have or problems that may occur when you put technology into normal day driving.
We figured that the best way to do this is to have a center where we teach interdisciplinary classes and get students to work on these really hard problems. We’ve been well funded. We have a number of membership companies that pay annual dues to us and interact with us very closely.
(Stories about other Volkswagen R&D with Stanford here and here.)
Q. You are a Senior Advisor at Charles River Ventures. What is your role there? Is CRV interested in investing in the robotics area?
A. I advise CRV on certain business investment decisions. I think there is a general interest in getting opinions from someone who comes from a somewhat different background than most partners in the partnership. It involves essentially looking at companies across the board (and not just robotics).
I find it important to have good connections with a venture firm because so much of Silicon Valley is made from VC investment and startups.
Q. Eventually are you thinking of starting your own company or becoming a full-time venture capitalist?
A. Eventually I want to maximize my impact on society. And I believe the part that I am working on right now, which is working on safer and more efficient transportation technology, has the potential to have a major impact on society. That’s my current goal.
(You can read an update on Prof. Thrun's project here.)
its appreciable and amazing on for the mit….
i have leart about certain other bread of “Driverless car” and i find this king of a design quite closely pertaining to it
http://upgradedgadget.blogspot.com/2010/05/iris-autonomous-transport.html
Posted by: Abhishek | May 31, 2010 at 10:43 AM
Thank you John for reading and commenting. Yes, this area is moving very fast and I too agree that time is ripe to start discussing not just from technological standpoint but also from transportation policies. Please check back to read future articles on this topic.
Posted by: Norri Kageki | March 01, 2010 at 09:12 AM
I have been starting to track auto-pilot car technology on my blog. I am amazed as it appears this problem will be solved within the next 10 years -- yet, it doesn't seem to register at all with transit planners most of whom see 19th century rail technology as the only type of "transit" worth considering. I envision auto-pilot cars that can be owned or used as low cost taxis (so that parking spaces are minimized), or high speed autos on roadways that can replace trains.
Why are planners ignoring this near-ready-to-go technology!?!
(Here's my skimpy thread on auto-pilot cars:
http://yrihf.com/viewtopic.php?t=3937&sid=43c5c0a1bf02fd042cf3e7cd0fe75ce5
)
Posted by: John Bailo | February 28, 2010 at 10:24 PM
Well, this must be a good news.I read & enjoyed.
Posted by: Fog Light | February 24, 2010 at 03:57 AM