An effective personal mobile robot agent through symbiotic human-robot interaction

Abstract

Several researchers, present authors included, envision personal mobile robot agents that can assist humans in their daily tasks. Despite many advances in robotics, such mobile robot agents still face many limitations in their perception, cognition, and action capabilities. In this work, we propose a symbiotic interaction between robot agents and humans to overcome the robot limitations while allowing robots to also help humans. We introduce a visitor's companion robot agent, as a natural task for such symbiotic interaction. The visitor lacks knowledge of the environment but can easily open a door or read a door label, while the mobile robot with no arms cannot open a door and may be confused about its exact location, but can plan paths well through the building and can provide useful relevant information to the visitor. We present this visitor companion task in detail with an enumeration and formalization of the actions of the robot agent in its interaction with the human. We briefly describe the wifi-based robot localization algorithm and show results of the different levels of human help to the robot during its navigation. We then test the value of robot help to the visitor during the task to understand the relationship tradeoffs. Our work has been fully implemented in a mobile robot agent, CoBot, which has successfully navigated for several hours and continues to navigate in our indoor environment.