Anita: Intelligent Humanoid Robot with Self-Learning Capability Using Indonesian Language

Abstract

Research and development on Intelligent humanoid robot for general purpose focuses on speech recognition systems to be able to interact with people naturally. In this research, we would like to propose humanoid robot with the self-learning capability based on Indonesian language and small vocabularies for accepting and giving response from people based on Natural Language Processing (NLP). This kind of robot can be used widely in schools, universities and public services. The humanoid robot should consider the style of questions and conclude the answer through conversation under unreliable automatic speech in noisy environment. In our scenario, robot will detect user's face and accept commands from the user to do an action, where the answer from user will be processed to the Google Translator and the result will be compared with vocabularies defined on the system. We describe how this formulation establish a promising framework by empirical results using subjects randomly. The comparative experiments with samples from user were presented.