Collaborative Exploration for a Group of Self-Interested Robots

Abstract

This paper presents and new approach to robot exploration and mapping using a team of cooperative robots. This approach aims to exploit the increase in sensor data that multiple robots offer to improve efficiency, accuracy and detail in maps created, and also the lower cost in employing a group of inexpensive robots. The exploration technique involves covering an area as efficiently as possible while cooperating to estimate each other's positions and orientations. The ability to observe objects of interest from a number of viewpoints and combine this data means that cooperative robots can localize objects and estimate their shape in cluttered real world scenes. Robots in the system act as social agents, and are motivated to cooperate by a desire to increase their own utility. Within this society, robots form coalitions to complete tasks that arise which require input from multiple robots. The coalitions involve the adoption of certain roles or behaviors on the part of the different robots to carry out these tasks.