Team Status Update for 04/04

This week we made a lot of progress on our manual mode – hopefully enough to have it semi-working by demo Wednesday!

Neeti has been working on the neural net classifier for the hand gesture (thumbs up and thumbs down). She realized earlier this week that she was training on a larger set of images that necessary, and that there were a few methods we could try to speed up the classifier, so she has been working on optimizing it. Once that is done, we should be able to begin to integrate it with the other parts we have done. We are on track to have this done this week.

Shrutika is working on the simulation. Since we decided to convert most of the physical components of our project to a Matlab simulation (except the sensors), we have decided to use Matlab’s Simulink and 3D World Editor. We are able to receive external signals and send it to Simulink, and rotate an object on the 3D World Editor. One challenge is figuring out how often to sample from the input (which in this case is the gesture). I think this will become clear as we work through the control loop. The simulation also is on track to be completed this week.

Later this week we plan to start playing with the microphones and testing different types of baffles, so we can get started on automatic mode next week.