Meystel, Alexander M.
Dr. Alexander M. Meystel is Professor, Emeritus at Drexel University and retired Director of the Laboratory of Applied Machine Intelligence & Robotics (LAMIR) and retired Director of the IMPACT Center at Drexel. Dr. Meystel received his Ph.D. from ENIMS (Experimental Scientific Research Institute of Machine Tools) in Moscow, USSR in 1965. Dr. Meystel's current research are in the areas of intelligent control, autonomous robots, learning systems, computer architectures for cognitive machines and manufacturing, and the theory of knowledge representation.
In 1983-87, Dr. Meystel developed an outdoor autonomous mobile robot (based on a Dune-Buggy and funded by the U.S. Army). In 1987-90 he and his students developed the Intelligent Material Processing System for OSPREY Machine. This spray-casting machine is an example of the class of objects for which the intelligent controllers are especially advantageous since the system to be controlled is not completely known. OSPREY machines manufacture preforms of complicated configurations by spraying hot metal which solidifies on a substrate moving in a sophisticated way by a robotic arm. The process variables are being measured by numerous sensors, nevertheless the process is still not adequately represented.
Computer controller has been developed at LAMIR which is using principles of artificial intelligence combined with control theory techniques and provides joint control of mechanical motion of the robotic arm as well as thermal and hydrodynamic processes of the metal spray. The research team of LAMIR has developed a system for off-line planning, simulation and animation of the OSPREY processes, and an on-line fuzzy controller. The OSPREY process had never before been controlled without ACTIVE involvement of a human operator. This intelligent controller can be applied for a variety of other systems with incomplete and/or inadequate knowledge representation.
His current research projects include the development of massively parallel computer architectures for multiresolutional "multigranular" knowledge processing in Intelligent Control Systems, learning, planning, and control of systems with incomplete and/or inadequate knowledge representation.
He and his students have developed a Nested Hierarchical Architecture for on-line robot learning control (re: project "Baby Robot"). A similar nested hierarchical control system is being explored for the project "Smart Plant" (partially funded by Fluor Daniel via IMPACT Center).
Selected publications
On Statistical Conceptual Learning
- A. Meystel, "Multiresolutional Autonomy", Proc. of the 1998 IEEE Int`l Symp. on Intelligent Control, A Joint Conference of the Science and Technology of Intelligent Systems, Sept. 14-17, NIST, Gaithersburg, MD, 1998, pp. 516-519
- A. Lacaze, M. Meystel, A. Meystel, "Multiresolutional Schemata for Unsupervised Learning of Autonomous Robots for 3D Space Application", Proc. of the 1994 Goddard Conference on Space Applications of AI, Greenbelt, MD, 1994, pp. 103-112
- A. Meystel, "Multiresolutional Schemata For Motion Control", Proc. of the Workshop on Neural Architectures and Distributed AI: From Schema Assemblages to Neural Networks", Los Angeles, CA 1993
Joint Research with NIST on Robotics, Decision Support, and Learning
- A. Meystel, “Learning-Planning-Control Continuum,” Ed. by H. S. Sarjoughian, et al, 2000 AI, Simulation and Planning in High Autonomy Systems, SCS, San Diego, CA, 2000, pp. 3-23
- A. Meystel, Y. Moskovitz, E. Messina, "Mission Structure for an Unmanned Vehicle", Proc. of the 1998 IEEE Int'l Symp. on Intelligent Control, A Joint Conference of the Science and Technology of Intelligent Systems, Sept. 14-17, NIST, Gaithersburg, MD, 1998, pp. 36-43
- James Albus, A. Meystel, Behavior Generation in Intelligent Systems, NISTIR 6083, Gaithersburg, MD, October 1997, 219 p.
- J. Albus, A. Lacaze, N. DeClaris, A. Meystel, "Neural Network Based Planner-Learner for Control Systems", in Proceedings of the 1997 International Conference on Intelligent Systems and Semiotics, Gaithersburg, MD, 1997, pp. 75-81
- A. Meystel, A. Lacaze, "Unified Learning/Planning Automaton: Generating and Using Multigranular Knowledge Hierarchies", in Proceedings of the 1997 International Conference on Intelligent Systems and Semiotics, Gaithersburg, MD, 1997, pp. 117-123
- J. Albus, A. Lacaze, A. Meystel, "Multiresolutional Planning with Minimum Complexity", in Proceedings of the 1997 International Conference on Intelligent Systems and Semiotics, Gaithersburg, MD, 1997, pp. 151-156
- A. Meystel, "Learning Algorithms Generating Multigranular Hierarchies", Eds. B. Mirkin et al, Mathematical Hierarchies and Biology, DIMACS Series in Discrete Mathematics and Theoretical Computer Science, Vol. 37, American Mathematical Society, 1997, pp. 357-384
- J. Albus, A. Meystel, "A Reference Model Architecture for Design and Implementation of Intelligent Control in Large and Complex Systems", International Journal of Intelligent Control and Systems, Vol.1, No. 1, 1996, pp. 15-30