A.T.R. Audio Test Robot Above: The robot has a microphone on a short boom on the rear end, and the mic amp/signal conditioner is the small board on the other side rear. The eventual goal is for the robot to understand a small vocabulary of word commands. Updated 6/5/16 Key Search Words: ROBOT, ROBOTICS, ROBOTIC VISION, ARTIFICIAL INTELLIGENCE, AI
The first step in getting your robot to understand verbal commands and recognize background sound events is to simply respond to the audio by sampling it periodically with the micro controllers A/D converter and triggering a response when a minimum threshold is reached. Then after that response, sit and wait until the next sound event.
To accomplish this, the robot first takes a reading when the power switch is first turned on, and sets that background level + a small tolerance as the reference level. Then any sound sampled after that over that reference triggers the response. In this case, the small DC offset measures around 45 ADU's and so we add 5 for a reference threshold of 50 or so. The robot is programmed to beep when it hears such a sound, then move forward a few inches in response. Then it waits for the next event.
Notice Im saying different words to trigger the robot! It does not yet know different words but only hears sound levels of ANY word.
You Tube Movie Clip of voice activation HERE This very short clip shows the robot responding to my voice three times, using different words.This is the first step in the process of many to get the device to understand the spoken word and respond per instructions.
Previous Uploads on this robot: 1. The sound envelope waveforms with the mic amp board