This week, the final design for the actual mount was completed. I did a final revision, adding a front plate, the neoprene padding, and using black and smoke grey acrylic (to make it look less suspicious). I also found a way to mount the Wifi+Bluetooth module, although it is not the most secure way of doing it (though necessary due to space constraints).
The IMU integration needs to be finalized, with resync signals based on drift and finding the new walk sign. This should not be too bad, but it requires us to find accurate angles based on the detected traffic lights from the Object Detection ML model, which involves some math based on the bounding box location and the camera’s field of view (FOV).
Regarding the schedule, I am in sync with the Gantt Chart. I need to finalize some things with the IMU, but it’s good for the most part. Another component is finalizing the audio signals. We are currently using a Python text-to-speech library, but it may also be better to have some pre-recorded audio signals to just play (including beeps and whatnot).