Building Ubiquitous Robot Systems: A hands-on tutorial

BACKGROUND

A clear trend is emerging in the field of autonomous robotics, toward the integration of this field with the fields of ambient intelligence and ubiquitous computing. The inclusion of networked robotic devices in smart environments, which often goes under the names "Network Robot Systems" or "Ubiquitous Robotics", provides a radically new way to build intelligent robot systems in the service of people. Correspondingly, ubiquitous robot systems require a new way of thinking on the part of the designers of such systems, as well as new tools to build them.
This tutorial will provide the attendees with a clear understanding of the general concepts and principles that underlie ubiquitous robot systems, and with practical knowledge on how to design and program an ubiquitous robot system. A large part of this tutorial will be devoted to the presentation of an open-source toolkit for ubiquitous robotics, the "PEIS-Ecology Middleware", richly illustrated by practical examples. At the end of the tutorial, the attendees should be able to use this toolkit to start building their own ubiquitous robot systems.

MOTIVATION AND OBJECTIVES

Ubiquitous robotics is quickly becoming a major trend in the field of autonomous robotics. More and more researchers realize the innovative potential of integrating robotic technologies with technologies from the fields of ubiquitous and pervasive computing, sensor networks, and ambient intelligence. Many companies also realize the great application potential of this integration, and large marked-oriented projects are already under way.

In spite of this development, there is little shared knowledge about how to practically build an ubiquitous robot system. The topic is too novel to be covered by traditional university courses, and no introductory book is yet available. Researchers and practitioners who wish to enter this field have to develop their own understanding of the main principles and concepts of ubiquitous robotics, by eliciting them from the research literature. Also, when these researchers and practitioners decide to build their ubiquitous robot system, they discover that they need tools from different fields, including robotics, networking, and pervasive computing. To find, learn and combine the right tools is often a painful and ineffective process.

The goal of this tutorial is to get people who are interested in ubiquitous robotic "kick started" in the right way, by providing them with: (1) a clear introduction to the main concepts and principles of ubiquitous robotics, (2) a toolkit for developing ubiquitous robotic systems, and (3) a practical introduction to the use of this toolkit, illustrated by a rich set of examples. At the end of the tutorial, the attendees should be able to go back to their laboratories and start right away to build their own ubiquitous robot systems. The toolkit used in this tutorial, called "PEIS-Ecology Middleware", is opensource and available on the Internet.

TUTORIAL OUTLINE

This tutorial will be structure in two main consecutive sections, separated by a coffee break.

1. Theoretical session: the PEIS-Ecology approach

• The concept of ubiquitous robotics
• Difference between ubiquitous robotics and other related fields
• Main current approaches to ubiquitous robotics
• The PEIS-Ecology approach

• Concepts and implementation
• Practical use and examples
• Running of different platforms (including motes)

INTENDED AUDIENCE

The primary audience will be researchers and practitioners in autonomous robotics who want to start doing practical work in the field of ubiquitous robotics. These include people who wish the get started in this field, as well as people who are already familiar with this field but want to get a deeper and more practical understanding. The tutorial addresses both researchers from academia and from industry. The secondary audience will be all researchers in autonomous robotics who want to get a concrete understanding of what's going on in the field of ubiquitous robotics.

BIOGRAPHIES OF INSTRUCTORS

Alessandro Saffiotti, PhD, is a full professor of computer science at Orebro University, Sweden. He has published more than 100 papers in international journals and conferences, on the subjects of autonomous robotics, artificial intelligence, and fuzzy logic. He is the inventor of the concept of PEIS-Ecology, a new approach to ubiquitous robotics. He is also the project manager of a project about PEIS-Ecology sponsored by the Korean "Ubiquitous Robot Companion" program, in cooperation with ETRI, Korea.

Mathias Broxvall, PhD, is a lecturer at Orebro University, Sweden. His research interests encompass autonomous robotics, artificial intelligence, and networking. He is the Principal Investigator of the above PEIS-Ecologyproject. He is also the main developer of the PEIS-Ecology middleware, which will be used in this tutorial.