Robo-Soar: An Integration of External Interaction, Planning, and Learning using Soar
This chapter reports progress in extending the Soar architecture to tasks that involve interaction with external environments. The tasks are performed using a Puma arm and a camera in a system called Robo-Soar. The tasks require the integration of a variety of capabilities including problem solving with incomplete knowledge, reactivity, planning, guidance from external advice, and learning to improve the efficiency and correctness of problem solving. All of these capabilities are achieved without the addition of special purpose modules or subsystems to Soar.
Additional Information© 1991 Elsevier Science Publishers B.V. This research was sponsored by grant NCC2-517 from NASA Ames and ONR grant N00014-88-K-0554. We would like to thank Karen McMahon for implementing Soar 5, and Mark Wiesmeyer for developing and implementing the Soar input and output interfaces. Without these extensions to Soar, Robo-Soar would not have been possible. We also like to thank Mike Walker and Joe Dionese for help with the Puma robot control system and Terry Weymouth for help with the vision system. Finally, we thank Paul Rosenbloom and Allen Newell for ideas relating to this work.
Draft - laird_1993.pdf