GetRobo Blog English

The Next Big Thing? Cloud Robotics

 GetRobo is in Nashville covering the Humanoids 2010 conference where researchers from around the world presented papers about the latest in robots that look and/or behave like humans.

 Here, James Kuffner, Adjunct Associate Professor at Carnegie Mellon University and currently working full-time as part of the team developing the driveless car project at Google, made a new proposal to the community - Cloud Robotics.

 To quickly summarize his talk: 

 What is Cloud Robotics? Cloud Robotics is cloud computing applied to robots.  Just like thin clients, robots don't need to carry around all the information nor the computing power that they need to perceive the world and make decisions to move around if they can access them when neccessary. 

 

Why Cloud Robotics? Here's another slide that explains it all.

 
 To  give you a little background about where James is coming from, he spent 15 years in academia working on humanoid motion planning. (He and Rosen Diankov developed OpenRAVE.) So James' knowledge and expertise in this area went into making reliable cars drive themselves in traffic.

 One of the things that the team at Google was able to leverage to realize the self-driving car was its cloud infrastructure which is used to process all the data involved. That made James and some of his colleagues at Google start thinking about how the cloud can benefit robotics.

 Check out Google Goggles to take a glimpse of what may be possible in the future. With Google Goggles you can upload a photograph and search the web for similar images. Potentially a robot can upload an image of the environment and search for ways to grasp that object, avoid that obstacle, etc. And moreover, all the robots - independent of platforms - may potentially be able to share that database.  

 Robotic researchers have been working on this line of idea for a while. For example, there is the Remote Brain developed by Prof. Masayuki Inaba at Tokyo University. And there are teleoperated robots where the human is acting as the remote brain.

 But now with all the computing power available and the increasing reliability of the mobile broadband network, this may become into something really big.

 The roboticists I talked to at the conference seemed to be enthusiastic about this idea, but it would be great if others can share their thoughts and comments on this new proposal. What do you think?

Autonomous Car Masterminds Converge at Google

Stanford University Professor Sebastian Thrun led the team that built Stanley which won the DARPA Grand Challenge in 2005. Two years later, Christopher Urmson of Carnegie Mellon University was the team leader of the group that made Boss that won the DARPA Urban Challenge. And there’s Anthony Levandowski who had the robotic motorcycle in the first Grand Challenge and then went on to develop the unmanned Prius (Pribot) that drove on public roads to deliver pizza.

So how in the world did all three of them get together to develop the Google Car?

GetRobo sat down with the three of them to find out. Here is an edited transcript of a very informative conversation. (This interview took place on Oct. 28, originally for a column on the Wall Street Journal Japan. )

 

(Photo: From left, Sebastian, Anthony and Chris with the self-driving Prius at Google)

 Q. When and how did this project come about?

 S) It started about one and a half years ago here at Google. There was a general awareness of the topic of self-driving cars that came with the Grand Challenges. The Grand Challenges set the stage to communicate to the world, including Google, that there is some interesting technology that may be worth nurturing.

Anthony and I had been working on Street View and that really helped Google as a company build up the next technology and scale up the operation. So there was a general level of trust between Anthony and me and Google as a company. And the key moment was when we got together to discuss what the fundamental things that can shape the 21st century are. What are the big technological innovations that might not feel like immediate business tomorrow morning but where a company like Google should really place a bet on? Google’s mission is really to advance the technology for the better of humankind and (self-driving cars) fit that vision somehow. So the Google leadership basically decided that this is worthwhile to place a bet on and to push it with a sizeable but still a modest investment - good enough to really understand that this technology has potential.

And I like this because it really allowed us to bring together a set of people and a team and a operating procedure which was not possible at the same scale at an academic institution. So I would claim the progress that took place in the last 18 months at Google dwarfs the progress that took in my own lab.

Q. I read that there are 15 people on your team. How many of you are from universities?

 C) There’s Sebastian, me and James Kuffner (who left his position as associate professor of CMU to join Google).  I am on a sabbatical until next June. 

S) I am also on leave. My leave ends next March. Mike Montemerlo (who was the software lead on the Stanford team) now works at Google too. 

Q. All three of you had your own projects. How did they all converge? 

S) When the vision was set (for Google to pursue developing a self-driving car), I essentially made a couple of phone calls to the strongest engineers in the world for this kind of thing. The first person I called was Chris. The second person I didn’t have to call, because we already worked in the same office. 

A) At some point we all competed, but while there is a little bit of rivalry still, we’ve really gotten along. 

C) We competed in the past but we all shared a common vision in terms of where technology was going and we recognized each other’s strengths and we feel the real value in collaborating. In fact we’ve been talking since the second Grand Challenge when Sebastian’s team won about trying to find a way to work together.

Q. How did the new Google car combine the technology developed for  Stanley, Boss and Pribot? Did you use any one of those projects as a base to build upon? 

C) We took ideas from all of them - different concepts, sensor fusion, map building, etc. The architectures we kind of independently conceived of. Motion planning, we took the concepts and then started here.

Q. So the code was written from scratch? 

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.