A Robust Human-Robot Communication System Using Natural Language for HARMS

摘要

This paper presents a robust human-robot communication system using natural language for HARMS (Human, Agent, Robot, Machine, Sensor). HARMS is a unique model designed for multi-agent systems. The human-robot communication system focuses specifically on allowing humans to easily and naturally communicate with other agents in the multi-agent system. The communication system uses specially designed algorithms that can accept any input, classify the input as one of the three message types in HARMS, and interpret the input to machine readable commands to be transmitted to other agents. The communication system is robust because it does not rely on a specific set of input (i.e. direct commands) or syntax. The user does not need any prior training and can communicate with the system naturally. Tests were performed on the system for each of the three sentence types (imperative, interrogative, and declarative) with an overall accuracy of 96.6%.