Out of sync from my experience usually means that either the device isn't being detected or the baud rates are different between the device and the PC. 1. Could u try different baud rates and see what happens? 2. Could u see whether the plugged-in device can be found at the serial ports? U could do that by just listing out the contents of the /dev directory. First you list the contents without the USB plugged into your PC, then with the USB plugged in and see if they are different.

@Rongzhong Li There were a couple of reasons behind that. 1. "Defining" the exact elbow joint is really hard because the shape of the contour varies a lot. Please note that I am not using any ML frameworks. It is just a clever manipulation of the image. Using pose estimation was an option, but that algorithm is computationally intensive-my i7 laptop was having a hard time running it. I couldn't make pose estimation run on a raspberry pi at all. The algorithm works by finding the centroid of the arm's contour and its highest point. Then it measures the angle with respect to the horizontal. The centroid is the rotation joint. 2. In the picture below (source:https://www.mathplanet.com/education/geometry/perpendicular-and-parallel/angles-parallel-lines-and-transversals), angles F,B are equal. Similarly, the angle at the elbow should be "approximately" equal to the angle at the centroid. A work around could be to forcibly displace the location of the centroid downwards in the image (i.e. increase its y-value. Please note that determining how to change the x-value is actually really complicated). However, the results are going to remain approximately similar-no significant difference in the angles read will be observed.

@Ronny Schönfeld I actually integrated opencv with the cat. In this video I am measuring the elbow angle and writing it to all of the motors of the cat. https://photos.app.goo.gl/KDK3xn98wBUDcaPR9 The code can be found here:https://github.com/BigPapaZ/OpenCat_CV_elbow

@franke At first we tried to use CMU sphinx, but their accuracy was just not as good as Google's API. Here it is in action: https://www.youtube.com/watch?v=17qozYvh1VQ. I would love to see your github code :)

@franke You are doing some incredible work man. I feel like you may want to take a look at some voice recognition stuff that we did. https://github.com/PetoiCamp/OpenCat/tree/serial/SerialMasterPython We are using the Speech Recognition framework and couldn't figure out how to put in that Hotword detection-in your case "Bella"- into it. Right now, the Nyboard makes a buzz sound and the user has to speak the command within a couple of seconds after that buzz.

cool

Hey, your project looks awesome. I see that Bela is your hot-word, how are you implementing hotword detection? Is this on github?