Society of Robots - Robot Forum
Electronics => Electronics => Topic started by: airman00 on June 29, 2007, 06:16:14 AM
-
How can a robot go to a person after a person says "come here" The only way this would work would be to triangulate the sound using microphones. But that would only work if the robot and the person were in the same room. Any ideas on how to make a robot come to me if I call its name( how can it find me in an entire house)
Please reply and email me
-
There are certainly chips and circuits that will support your need for speach recognition. Localizing the voice source (especially if you are not in the same room) is going to be a bit complex to solve... I wouldn't know where to start for that part... how about you focus on simple voice recignition (the robot responds to a specific command) first, then go from there.
-
I already know how to use voice recognition. There is a kit called the SR06 voice recognition kit and a kit called the SRI03 interface kit. They are available from IMAGES SI inc. It is very simple to use and to set up. The voice recognition is not a problem and finding a person based on voice( in the same room) is not a problem. But in another room I would need to use RF transmitters by the door of every room which listen for the commands and relay those commands to the robot.
Once I know which room and cardinal direction( ex. North, East, Southwest) I could have the robot autonomously go there, and avoid obstacles. A bit complex but I have it figured out.
-
I will put some pics of my Butler Robot on my blog if any1 is interested. Look for it within the next week.
http://erobots.blogspot.com/ (http://erobots.blogspot.com/)
-
its kinda difficult even for humans to know where someone is in an unknown house based solely on their voice, you might have to do like a trial and error, like you say come here a couple of times and it measures the dB level and decides which place it took the reading from was louder.
-
After the robot recognizes the Come Here command, it should scan it's vecinity using a camera and a PIR sensor (maybe a distance sensor also) trying to locate the place where the person is. If the voice recognition software is voice trained, the robot will know the person that initiated the command and will search for it's face recognition. The PIR sensor will make the difference from a picture and the real person, and a distance sensor or stereo vision can find the distance to the person.
If the person is not in the room but is still audible, the robot can look for entrances and go to them and locate the person with the above method. Or, it can say Please specify your location! You should definitely do that if you talk to your robot using a wireless mic.
Now if the voice software is not user trained (can recognize any voice) AND in the room are more persons, finding the right one will be more difficult. Now it will be necessary to triangulate the sound source.
-
Remember to always search the forum before asking:
http://www.societyofrobots.com/robotforum/index.php?topic=1125.0
;D