Abstract:

    VisionPSU is a human interactive robot with voice and audio recognition capabilities. It is being designed and developed to differentiate between a specific set of users based on video and audio input in an ideal environment.

    The recognition is solely limited to the five group members and project mentors. The system attempts to recognize the person in front of the camera, and the name of that person is displayed through a LCD mounted on the system. The robot is capable of responding to users by physical movements. This project is being integrated with six separate modules: Robotics, Communication Layer, RTS (real time control system), Audio Processing Layer, Image Processing Layer and Neural Network. Designing a human interface device with a high accuracy rate will likely lead to more sophisticated systems in the future.