Microsoft originally designed the Kinect controller as a way to play Xbox 360 games via gesture and spoken words, targeting the casual gamers who had made the Nintendo Wii such an enormous success. Launched last November, the device (shown below with the Xbox) features an RGB camera, a multi-array microphone, and an infrared depth sensor.

Microsoft's Kinect

In February, Microsoft noted that "Kinect for Xbox 360 and the potential seen within its core technology have captured the imaginations of the academic research and enthusiast communities." The company announced that it would release a non-commercial Kinect for Windows software development kit (SDK) in the spring, with a commercial version scheduled for "a later date."

The SDK, which actually became downloadable on Jun 16, includes application programming interfaces (APIs), device interfaces, source code samples, and documentation, according to Microsoft. It allows the Kinect to be used with a computer running Windows 7, for which programmers can code via C++, C#, or Visual Basic, the company adds.

Separately, Microsoft's Robotics Group had been evaluating the Kinect for its potential to act as the eyes and ears of robots based on the company's Windows-based Robotics Developer Studio platform.

"Obviously, we have to wait until the public release of the Kinect SDK before we can release anything because we have a dependency on the driver," Robotics Group Program Manager Trevor Taylor said in a March 13 forum posting. After the SDK was released June 16, he added, "There are people working on it right now, including me. Hang in there, not long to go."

Now, the resulting Kinect Services for Robotics Developer Studio software is freely downloadable, according to Stathis Papaefstathiou, General Manager of Microsoft Robotics. In a July 13 entry on the Microsoft Robotics Blog, he stated:

"Kinect Services for RDS is built on top of the Kinect for Windows SDK. We have wrapped in the core Kinect SDK capabilities so you can use them with the CCR/DSS programming model. However, this is only the beginning. Keep your eyes peeled for updates in the fall. We know that there are many practical issues for applying the Kinect technologies to robotics capabilities that we will be addressing in upcoming RDS releases."

According to an EETimes story by R. Colin Johnson, the enhancements will include new routines to directly support autonomous navigation tasks. Developers will also have access to the routines controlling the four-microphone array in the Kinect, including its sophisticated noise cancellation and beam steering operations, Papaefstathiou is quoted as adding.

In late 2010, Microsoft acquired Canesta, a maker of 3D-image sensor chips and camera modules. The company plans to replace the PrimeSensor chip (licensed from PrimeSense Ltd. of Israel) currently used in the Kinect with a Canesta-derived component, allowing the foot-long Kinect to be downsized to as little as a square centimeter, the EE Times story adds.

Microsoft's Trevor Taylor demonstrates Kinect Services for Robotics Developer Studio
(click to play)

Further information

Kinect Services for Robotics Developer Studio Release R3 is downloadable on the Microsoft Research website. Downloads of the Kinect for Windows SDK beta are offered, in both 32- and 64-bit versions, available here. Robotics Developer Studio Release R3 itself may be downloaded here for non-commercial use.

Jonathan Angel can be reached at jonathan.angel@ziffdavisenterprise.com and followed at www.twitter.com/gadgetsense.

---

Related stories:

• Microsoft to acquire Canesta, 3D tech patents
• 3-D image sensor lets devices "see and interact"
• Industry group aims to promote embedded vision technology
• Microsoft shows off 3D user interfaces
• Care robut uses Kinect for vision
• Microsoft gives away next-gen robotics tools