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?