Bill Morris wrote: On Sat, 2010-11-13 at 18:17 -0800, Curt Meyers wrote: > On Sat, Nov 13, 2010 at 4:37 PM, Bill Morris > wrote: > On Sat, 2010-11-13 at 16:12 -0800, Curt Meyers wrote: > > Does this frequently crash for anyone else? ... > > There is working code for the accelerometer and the tilt motor > so > integrating it into ROS should be easy once it's supported by > libfreenect. > > As far as I know, the code for the accelerometers and tilt motors has > not been released yet. Have you seen this code? This code will work to control the motor and get accelerometer data. https://github.com/adafruit/Kinect/blob/master/usbmotor.py In that git repo there is also enough usb traces for someone to figure out the audio. http://www.adafruit.com/blog/2010/11/09/kinect-hacking-video-and-data-dump/ > I have not seen any code yet for the microphones, but I really > want to > HARK working. > > http://www.willowgarage.com/blog/2010/03/25/hark-texai > > I worked on that and I don't think HARK will work well with the > microphone placement here. It is very sensitive to the shape of the > object that the mics are placed on, a big rectangular box is not > ideal. That's disappointing, it would be interesting to see if there is someway to get speaker detection with the 4 microphones. _______________________________________________ ros-users mailing list ros-users@code.ros.org https://code.ros.org/mailman/listinfo/ros-users Sorry for interrupting the Kinect ROS node discussion. But, about the HARK system, the newest official HARK release will be in the very near future, and the next version of HARK can realize seamless connection with ROS. The speaker location (with 4 microphones like you want) can also be published as a ROS topic from HARK. Please keep in mind that we are working for all your requests. Thanks. Keisuke --------------------------------- Get the new Internet Explorer 8 optimized for Yahoo! JAPAN