Identification of Cognitive Navigational Commands for Mobile Robots Based on Hand Gestures and Vocal Commands

摘要

Assistive robots are developed to uplift living standards of human beings. An assistive robot needs to be friendly, reliable, and understandable in order to be a human like companion. A robot should be able to navigate in an environment according to users' commands. Users' commands can be vocal or gestures. Combining users' command types to identify the navigation information will enhance the user-robot interaction and makes navigation more effective and purposeful. Moreover, understanding the relationship between the navigation commands makes the robot a more human friendly companion. A robot should be capable of interpreting spatial information in uncertain terms. Moreover it should be able to improve the knowledge through communicating with the user, itself. The Cognitive Map Creator (CMC) has been introduced to create a cognitive map of direct navigational commands to enhance the interaction between the human and the robot which will help to make a robot more human-friendly. The Conversation Management Module (CMM), Spatial Data Interpreter (SDI) and Navigational Command Identifier (NCI) have been introduced in order to create a cognitive map of navigational commands. The capabilities of the robot have been demonstrated and evaluated from experimental results.