HUMAN INTERACTION CONTROLLED ROBOT WITH ARTIFICIAL INTELIGENCE

Human Interaction based interfaces are changing the way we interact with computers, giving us a more intuitive way to control devices. Taking into account certain motions and speech recognition are easy and intuitive to perform, allowing an unprecedented level of control over the surrounding devices. Cameras and sensors translate movements of our bodies without the need of remotes or hand held tracking tools. As the underlying technologies evolve, a variety of approaches to gesture-based input are being explored. The most common applications for gesture based computing are for computer games, file and media browsing, and simulation and training. Controlling a computer applications can to brought to new level using speech recognition. The robot is having artificial intelligence to a level that it can interact with speech response.

                                                The proposed embedded system consists of a robotic arm supported with a vehicle at the base. Our aim is to deliver a user interface (UI) that enables the user to interact with the computer using Hand Gestures and Speech Recognition. For this we track the colour rings placed on the user's fingers using Matlab. The gesture recognition enables the user to control the arm movements by getting the positions of the colour rings. The total system can be controlled through voice recognition system using matlab.

We perform Voice recognition, an extremely complex visual task, almost instantaneously and our own recognition ability is far more robust than any computer's software can hope to be. We are able to recognize the voice of several thousand individuals whom we have met during our lifetime.

This current research is focused towards developing a sort of unsupervised pattern recognition scheme that does not depend on excessive geometry and computations like deformable templates. Neural network approach seemed to be an adequate method to be used for recognition due to its simplicity, speed and learning capability, also it was chosen because it has proved to be highly robust in pattern recognition tasks and because it is relatively simple to implement.

Speaker recognition using Neural Network approach was developed in Matlab technical computing language on a Microsoft Windows personal computer. The Database library was created manually and recognition were done and displayed