On-Line Reconfigurable Machines

Authors

  • Lara S. Crawford Palo Alto Research Center (PARC)
  • Minh Binh Do Palo Alto Research Center (PARC)
  • Wheeler S. Ruml University of New Hampshire
  • Haitham Hindi Accuray, Inc.
  • Craig Eldershaw Palo Alto Research Center (PARC)
  • Rong Zhou Palo Alto Research Center (PARC)
  • Lukas Kuhn Qualcomm R&D
  • Markus P. J. Fromherz Xerox
  • David Biegelsen Palo Alto Research Center (PARC)
  • Johan de Kleer Palo Alto Research Center (PARC)
  • Daniel Larner Google

DOI:

https://doi.org/10.1609/aimag.v34i3.2387

Keywords:

real time systems, planning, control, diagnosis, reconfigurable, manufacturing, intelligent machines, distributed, on-line, modular

Abstract

A recent trend in intelligent machines and manufacturing has been toward reconfigurable manufacturing systems, which move away from the idea of a fixed factory line executing an unchanging set of operations, and toward the goal of an adaptable factory structure. The logical next challenge in this area is that of on-line reconfigurability. With this capability, machines can reconfigure while running, enable or disable capabilities in real time, and respond quickly to changes in the system or the environment (including faults). We propose an approach to achieving on-line reconfigurability based on a high level of system modularity supported by integrated, model-based planning and control software. Our software capitalizes on many advanced techniques from the artificial intelligence research community, particularly in model-based domain-independent planning and scheduling, heuristic search, and temporal resource reasoning. We describe the implementation of this design in a prototype highly modular, parallel printing system.

Author Biographies

Lara S. Crawford, Palo Alto Research Center (PARC)

Lara Crawford is with the Intelligent Systems Lab (ISL) at the Palo Alto Research Center. She received a Ph.D. in biophysics and an M.S. in electrical engineering science from the University of California at Berkeley. Her research interests include control and coordination of distributed, embedded systems, the interface between planning and control, modeling, simulation, robotics, and energy systems.

Minh Binh Do, Palo Alto Research Center (PARC)

Minh Do is with ISL at the Palo Alto Research Center.
He received a Ph.D. in computer science from the Arizona State University. His main research interest is in automated planning with concentration on online continual planning for manufacturing systems with complex temporal and resource constraints. He has also worked on other topics in planning such as partial-satisfaction planning, integrating planning
and diagnosis, and constraint-based planning.

Wheeler S. Ruml, University of New Hampshire

Wheeler Ruml is an Assistant Professor at the University of New Hampshire (UNH). He received a Ph.D. in Computer Science from Harvard University in 2002. Before joining UNH in 2007, he was a Member of the Research Staff and Area Manager for Embedded Reasoning at the Palo Alto Research
Center. His research interests include heuristic search
and planning, with an emphasis on time-aware decisionmaking.

Haitham Hindi, Accuray, Inc.

Haitham Hindi is with Accuray, Inc. He was with ISL
at Palo Alto Research Center from 2003-2011. He holds a B.Sc. from Imperial College in Physics, and an M.S. and Ph.D. from Stanford University in Electrical Engineering. His research is in control and optimization, and their application to real-world problems, including: radiation treatment optimization; energy management systems; dynamic pricing; networked and hybrid control; printing and manufacturing networks; particle accelerators and disk drives.

Craig Eldershaw, Palo Alto Research Center (PARC)

Craig Eldershaw is with the Hardware Systems Laboratory at the Palo Alto Research Center. He received a D.Phil. from The University of Oxford on the topic of robot motion planning. His specialty is integrating mechanical, electrical and software designs within a complex, distributed, system. The work described in this paper was a natural extension of his previous NASA and US Defense funded work on modular robotics.

Rong Zhou, Palo Alto Research Center (PARC)

Rong Zhou is with ISL at the Palo Alto Research Center. He received a Ph.D. in computer science from Mississippi State University. His main research interests include combinatorial optimization and automated planning with concentration on large-scale graph search using parallel and memory hierarchy aware search methods. He has also worked on user interface design and human factors.

Lukas Kuhn, Qualcomm R&D

Lukas Kuhn is currently a Senior Engineer at Qualcomm R&D. He received a Ph.D. and a diploma (eq. to Master) in computer science from the Technical University of Munich and the University of Munich, respectively. Before joining Qualcomm in 2010, he was a Research Assistant with the Embedded Reasoning Area at the Palo Alto Research Center,
where he worked on the integration of model-based diagnosis and planning. His current work focuses on reasoning for contextual awareness and behavior modelling.

Markus P. J. Fromherz, Xerox

Markus Fromherz is currently Chief Innovation Officer,
Healthcare, at Xerox. He received his Ph.D. in Computer Science from the University of Zurich, Switzerland, and his M.S. in Computer Science from ETH Zurich. His research interests were in the domain of intelligent embedded software include constraint-based modeling; model-based planning,
scheduling, and control; and model-based design analysis and optimization.

David Biegelsen, Palo Alto Research Center (PARC)

David Biegelsen was a charter member of Xerox PARC
and is currently a Research Fellow. His fields of expertise include acousto-optic interactions, electron spin resonance and fundamental aspects of disordered semiconductors, laser-induced thin-film crystallization, scanning tunneling microscopy, heteroepitaxial growth, and new fabrication methods and use of complex “smart matter” systems.
David holds over 100 US patents. He is a Fellow of the APS and has been an Editorial Board Member of Applied Physics Letters and Divisional Associate Editor of Physical Review Letters. David gets his kicks from learning new concepts and using them in novel ways.

Johan de Kleer, Palo Alto Research Center (PARC)

Johan de Kleer is Area Manager and Principal Scientist
in the Intelligent Systems Laboratory. He recieved his Ph.D. and S.M. from the Massachusetts Institute of Technology. Dr. de Kleer’s interests include large-scale inference, qualitative reasoning, knowledge representation, model-based diagnosis
and truth maintenance systems. He is a fellow of
the American Association for the Advancement of Artificial Intelligence and the Association of Computing Machinery.

Daniel Larner, Google

Dan Larner has a B.S. in mechanical engineering and B.S. in computer science and engineering from MIT, and a M.S. in computer science from Stanford. He has worked on a variety of systems in both physical and software areas. He is currently a mechanical engineer on autonomous vehicles at Google.

Downloads

Published

2013-09-15

How to Cite

Crawford, L. S., Do, M. B., Ruml, W. S., Hindi, H., Eldershaw, C., Zhou, R., Kuhn, L., Fromherz, M. P. J., Biegelsen, D., de Kleer, J., & Larner, D. (2013). On-Line Reconfigurable Machines. AI Magazine, 34(3), 73-88. https://doi.org/10.1609/aimag.v34i3.2387

Issue

Section

Articles