The Kinect game accessory, which enables video game interaction through full-body gestures, has found a number of uses in the hacking community and Microsoft’s addition of Kinect services to robotics extends the popular product even farther. But Kinect’s future could be in even more intelligent smartphones.
Canesta’s engine is said to outperform the PrimeSensor which Microsoft is currently licensing from PrimeSense Ltd. (Tel-Aviv, Israel) for its Kinect. When Microsoft commercializes the Canesta-invented chip-level work-alike of the PrimeSensor, it will be able to downsize the foot-long Kinect to about a square centimeter, enabling tiny robots and other mobile devices, such as the Windows Phone, to perform sophisticated gesture recognition for natural user interfaces, autonomous navigation and many other tasks.
Connectivity to the cloud, a smartphone must-have, expands the “brains” of a robot by allowing for nearly limitless information. Sure, you can store a fair amount of data on a smartphone with 32 GB of storage capacity, but access to the vast information bases of Wikipedia, Google and other sites bring even more smarts to a smartphone-powered robot. What’s missing then is what Kinect hardware and software can bring: strong gesture and object recognition.
Ironically, Microsoft isn’t the first to integrate its own Kinect product with robotics even though it has had a robotics software platform since 2006. Robot enthusiasts have already done so on their own by accessing the raw data stream from the Kinect’s USB connection. Willow Garage also offers the Turtlebot kit (shown above), complete with Kinect and a Windows-powered netbook.