Laird, John E. and Yager, Eric S. and Tuck, Christopher M. and Hucka, Michael (1989) Learning in Tele-autonomous Systems using Soar. In: Proceedings of the NASA Conference on Space Telerobotics. NASA Jet Propulsion Laboratory , pp. 415-424. https://resolver.caltech.edu/CaltechAUTHORS:20130107-150307467
|
PDF
- Published Version
See Usage Policy. 722kB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20130107-150307467
Abstract
Robo-Soar is a high-level robot arm control system implemented in Soar. Robo-Soar learns to perform simple block manipulation tasks using advice from a human. Following learning, the system is able to perform similar tasks without external guidance. Robo-Soar corrects its knowledge by accepting advice about relevance of features in its domain, using a unique integration of analytic and empirical learning techniques.
| Item Type: | Book Section | ||||||
|---|---|---|---|---|---|---|---|
| ORCID: |
| ||||||
| Additional Information: | 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 5.0, and Mark Wiesmeyer for developing and implementing the Soar input and output interfaces. Without these extension to Soar, Robo-Soar would not have been possible. We also like to thank the staff of the Robotics Laboratory for help with the tele-autonomous software and hardware. Finally, we thank Paul Rosenbloom and Allen Newell for ideas relating to this work. | ||||||
| Funders: |
| ||||||
| Record Number: | CaltechAUTHORS:20130107-150307467 | ||||||
| Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20130107-150307467 | ||||||
| Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||
| ID Code: | 36210 | ||||||
| Collection: | CaltechAUTHORS | ||||||
| Deposited By: | Linda Taddeo | ||||||
| Deposited On: | 07 Jan 2013 23:31 | ||||||
| Last Modified: | 03 Oct 2019 04:35 |
Repository Staff Only: item control page
