Designing the HRTeam framework lessons learned from a rough-and-ready human/multi-robot team

• Published in: Proceedings of the 10th international conference on Advanced Agent Technology pp. 232 - 251
• Main Authors: Sklar, Elizabeth, Ozgelen, A. Tuna, Munoz, J. Pablo, Gonzalez, Joel, Manashirov, Mark, Epstein, Susan L., Parsons, Simon
• Format: Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer-Verlag 02.05.2011
• Series: ACM Conferences
• ISBN: 9783642272158; 3642272150
• DOI: 10.1007/978-3-642-27216-5_15

In this workshop paper, we share the design and on-going implementation of our HRTeam framework, which is constructed to support multiple robots working with a human operator in a dynamic environment. The team is comprised of one human plus a heterogeneous set of inexpensive, limited-function robots. Although each individual robot has restricted mobility and sensing capabilities, together the team members constitute a multi-function, multi-robot facility. We describe low-level system architecture details and explain how we have integrated a popular robotic control and simulation environment into our framework to support application of multi-agent techniques in a hardware-based environment. We highlight lessons learned regarding the integration of multiple varying robot platforms into our system, from both hardware and software perspectives. Our aim is to generate discussion amongst multi-robot researchers concerning issues that are of particular interest and present particular difficulties to the multi-robot systems community.