IEEE ICMA2006 Conference

Plenary Talk

Towards Autonomous Systems: From Control Systems to Intelligent Control to Intelligent Behavior Generation to Cooperative Autonomy

Kevin L. Moore, Ph.D., P.E.
G.A. Dobelman Distinguished Chair and Professor of Engineering
Division of Engineering

Colorado School of Mines , U.S.A.

Abstract:

Today a number of enabling technologies have matured to the point that it is possible to build robots and intelligent machines that are physically capable of autonomous behavior. However, to achieve the promise of autonomy, we also need equivalently-mature information-processing and decision systems to exploit these physical capabilities. In this talk we discuss the problem of devising truly autonomous systems in three parts, describing several threads of research from the speaker乫s experience.  In Part 1, we begin with a discussion of intelligent control, including its promise and reality, introducing specifically the paradigm of iterative learning control (ILC). After highlighting and critiquing the history and accomplishments of ILC, we posit that in fact intelligent control has not achieved its promise and argue that as we try to develop increasingly autonomous systems we need better understandings of the purpose (goals), the components (memory, learning), and organization of intelligence (models, language, architecture). From this motivator, in Part 2 we consider how to move beyond conventional intelligent control to develop intelligent behavior generators for single-system autonomy, focusing on mobile robots operating in semi-structured environments. We present an intelligent, reactive command and control system that uses a multi-resolution, hierarchical task-decomposition strategy based on a grammar of atomic actions. The effectiveness of the strategy is demonstrated in actual tests with real robots in which the path-planning and control algorithms are implemented in a distributed processing environment. We show the use of the behavior generator for ODIS, a low-profile omni-directional (ODV) robot developed for under-vehicle inspections at security checkpoints that has recently been commercialized, and for the T2 and T4 robots, larger ODV vehicles that can serve as marsupial mother-ships for the ODIS robots as part of a multi-robot, integrated parking area security system. This part of the talk concludes with comments on extensions to include learning and synthesis of reactive behaviors within the behavior generator. Part 3 of the talk looks to the next frontier of autonomy: cooperative behavior of multiple autonomous entities. We discuss this notion from the idea of what we call a dynamic resource network, in which mobile, autonomous actuators and sensors cooperate to accomplish a global objective in a spatial-temporal domain. We present a number of motivating examples of such networks, including cooperative UAVs for data exfiltration, landslide detection, and center-pivot irrigator control for farming. We then introduce a control-theoretic framework that can be used for mobile actuator and sensor networks when the underlying phenomena are diffusion processes. Preliminary results from a Mote-based experimental testbed are presented to illustrate the ideas and the technical and theoretical challenges posed by the problem are discussed, which point to a number of exciting new directions for systems and control researchers.

Kevin L. Moore is the G.A. Dobelman Distinguished Chair and Professor of Engineering in the Division of Engineering at the Colorado School of Mines. He received the B.S. and M.S. degrees in electrical engineering from Louisiana State University and the University of Southern California, respectively. He received the Ph.D. in electrical engineering, with an emphasis in control theory, from Texas A&M University in 1989. He was a senior scientist at Johns Hopkins University's Applied Physics Laboratory during a one-year research leave of absence, where he worked in the area of unattended air vehicles, cooperative control, and autonomous systems (2004-2005); an Associate Professor at Idaho State University (1989-1998); and a Professor of Electrical and Computer Engineering at Utah State University, where he was the Director of the Center for Self-Organizing and Intelligent Systems, directing multi-disciplinary research teams of students and professionals developing a variety of autonomous robots for government and commercial applications (1998-2004). He also worked in industry for three years pre-Ph.D as a member of the technical staff at Hughes Aircraft Company. He is a seminal contributor and active researcher in the area of iterative learning control. His other research interests include autonomous systems and robotics, and applications of control to industrial and mechatronic systems. He is the author of the research monograph Iterative Learning Control for Deterministic Systems and co-author of the book Sensing, Modeling, and Control of Gas Metal Arc Welding. He is a professional engineer, involved in several professional societies and editorial activities, and is interested in engineering education pedagogy, particularly capstone senior design. He is a senior member of IEEE and serves as a member of the IFAC Technical Committee on Computers, Communications, and Telematics and of the IEEE Control System Society Technical Committee on Intelligent Control.