Situation aware human robot interaction

• Main Author: Ng, Chong Soon.
• Other Authors: School of Electrical and Electronic Engineering
• Format: Final Year Project
• Language: English
• Published: 2011
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Medical electronics
• Online Access: http://hdl.handle.net/10356/46408
• Institution: Nanyang Technological University

The project is to explore Situation Aware Human Robot Interaction and to develop a proof of concept software. The software is able to make decisions and to identify the intention of a human’s request, therefore understanding the situation and making appropriate use of information and answer the human’s request. The software was inspired by multiple research papers especially Ontology-based Multi-Layered Robot Knowledge Framework, Development of a Cognitive Model of Humans in a Multi- Agent Framework for Human Robot Interaction. The software is a Multi-Agent System and some of the libraries used are JADE, Stanford NLP Library and OWL API. The software has four stages, input, parsing, intention retrieval, and output stage. The software gets its knowledge of the environment through an ontology. The software also refers to the WordNet to have better understanding of words. The software consists of two versions. The first version does not implement the Stanford parser and it faces problems such as infinite looping. The second version implements the Stanford parser but requires reworking of some key agents within the software. Improvements were suggested to allow the software to be more intelligent.