Pattern Recognition and Text-Dependent Recognition for a Mobile Robot

Pattern Recognition and Audio Processing are important aspects in the control and behavior of mobile robots. Mobile robot's action depends on the recognition of visual and audio stimuli in order to reflect intelligent behavior of the robot. This work presents two recognition systems developed using morphological operations and Linear Predictive Coding (LPC) with Backpropagation Neural Networks (BNN) to process visual and audio data respectively. The objective is to design a person tracking system for a mobile robot with text dependent pitch recognition and a visual pattern recognition mechanism. The BNN will awake the robot from the idle position, while the visual stimulation will be used to track the person given the command.

[1]  M.G. Bellanger,et al.  Digital processing of speech signals , 1980, Proceedings of the IEEE.

[2]  A. Torige,et al.  Human-interface by recognition of human gesture with image processing-recognition of gesture to specify moving direction , 1992, [1992] Proceedings IEEE International Workshop on Robot and Human Communication.

[3]  Jae Wook Jeon,et al.  Multiple mobile robot interface using a low cost voice recognition chip , 1997, Proceedings 6th IEEE International Workshop on Robot and Human Communication. RO-MAN'97 SENDAI.

[4]  M. Bodruzzaman,et al.  A neural network-based text independent voice recognition system , 1994, Proceedings of SOUTHEASTCON '94.

[5]  G. K. Venayagamoorthy,et al.  Voice recognition using neural networks , 1998, Proceedings of the 1998 South African Symposium on Communications and Signal Processing-COMSIG '98 (Cat. No. 98EX214).

[6]  Wolfram Burgard,et al.  Position Estimation for Mobile Robots in Dynamic Environments , 1998, AAAI/IAAI.