January 04, 2012      

If you have been following the robotics news this year, you may have heard that researchers are working to create “an Internet for robots.” I’m one of these researchers. RoboEarth (www.roboearth.org), the name of the project I’m involved with, is an initiative by five universities and an industrial partner funded by the European Union. Its goal is to develop a repository of knowledge robots can share, thereby greatly speeding up learning and, ultimately, allowing robots to perform well beyond their preprogrammed behaviors.

As one of its first demonstrators, RoboEarth has shown that robots with different hardware can share maps. Another demonstrator allowed a complex service robot to download hardware-independent object models from the RoboEarth database and use them for perception and manipulation. And a third demonstrator has shown how a service robot can identify, download, and use high-level task descriptions to serve a drink.

Since the start of RoboEarth in late 2009, a number of other groups have begun work on allowing robots to use large, online knowledge repositories. Google announced the formation of a Cloud Robotics team at its Google I/O conference earlier this year. Its main thrust is leveraging existing Google Web services. In a joint talk with Willow Garage Inc., the new Google team also introduced the first pure Java implementation of Willow Garage’s Robot Operating System (ROS). The software, currently in alpha testing, will enable integration of Google’s Android operating system for mobile phones with ROS.

Finally, Motoman launched its Web-based remote monitoring service, MyMotoman, in August 2011. It not only enables customers to monitor and update their robots’ status via mobile devices, but also uses historical data to enhance its service offering with predictive maintenance trend data on concerning situations.

The above examples mark a wider trend toward harnessing Internet technology for robotics. And this is not surprising: Both the personal computing and mobile phone industries are intimately connected to robotics. Personal computers continue to underpin robot software and act as an important enabler by providing ever-increasing computing power. Mobile phone technology, on the other hand, continues to drive down prices for sensors, including cameras, accelerometers, gyroscopes, GPS sensors, as well as for enabling technologies like wireless networks. In addition, personal computers and mobile phones are natural entry points for human-robot interaction for developers as well as B2B clients and, increasingly, B2C customers. And both fields have benefitted immensely from Internet connectivity, raising the question if the Internet may, in time, have a similar effect on robotics.

And there is a likely starting point for such a transformation. The performance of solutions to the field’s main challenge—robot vision—is tightly coupled with the available computational resources and databases. Web services that allow outsourcing computation and data storage to the cloud therefore offer clear cost benefits for connected robots by replacing expensive local processing capacity and battery power with more powerful cloud services.

One such service is the Google Goggles mobile phone app. Snap a picture with your mobile phone, and you will receive related information from Google product search for objects, translation services for text, or geo information for landmarks within seconds. Vision is not the only robot task that could greatly benefit from Web services. Speech-to-text-to-speech services could vastly improve human-robot interaction. Optical character recognition could help robots to understand text in all its forms. And any roboticist who has used the turn-by-turn directions offered by a navigation system can appreciate how useful a similar service could be for outdoor or indoor robot navigation.

A transformation like the one seen in the personal computing and mobile phone industries, however, is unlikely to result from mere adoption and adaptation of old technology. Just as the killer application for mobile phones was not email, it seems unlikely that robotics will be driven by an app store. The app store’s business model, with app sales feeding product sales feeding app sales, may be brilliant. But although the first robot apps are already available for Android phones, the number of consumers required to successfully kick-start a similar virtuous cycle for robotics seems rather high for today’s robots, even for a B2B variant.

Another candidate is the use of pooled knowledge to improve robot learning. Kiva Systems, in North Reading, Mass., has pioneered this approach for a homogeneous multirobot system, and it is no coincidence that one of Kiva Systems’ co-founders is one of my RoboEarth colleagues.

One belief RoboEarth partners share is that human environments are too nuanced and complicated to be summarized within a limited set of specifications. This is why RoboEarth’s focus is on robot learning. Sharing knowledge allows robots to perform such learning faster. As described in more detail in an article that appeared in the June 2011 issue of the IEEE Robotics and Automation Magazine, an online knowledgebase that links data, such as the CAD model of an object, its semantic descriptors (e.g., the object’s English name), the object’s properties (e.g., object weight), its relation to other objects (e.g., belongs to the class “bottle”), or instructions for manipulating the object (e.g., grasp points) can immediately allow a robot to access a wealth of useful information.

As it turns out, a fair amount of knowledge robots learn is easily exchangeable by updating a joint knowledge repository. And, unlike humans, robots excel at generating such knowledge. While most information found on today’s Internet was created by humans via a keyboard and mouse, robots are capable of rapid, systematic, and accurate data collection.

This provides unprecedented opportunities for obtaining consistent and comparable data as well as for performing large-scale systematic analysis and data mining.

Connecting robots worldwide is a challenging task beyond the scope of any individual initiative. RoboEarth is currently collaborating with related research initiatives in Europe and the United States, as well as with a number of companies through its Industrial Advisory Committee. To join the discussion, feel free to have a look at the RoboEarth website and to get in touch via [email protected]

Editor’s Note: Markus Waibel is a senior researcher with ETH, a science and technology university located in Zurich.