Abstract
Biological control systems have long been studied as possible inspiration for the construction of robotic controllers. The cerebellum is known to be involved in the production and learning of smooth, coordinated movements. In this paper, we present a model of cerebellar control of a muscle-actuated, two-link, planar arm. The model learns in a trial-and-error fashion to generate the appropriate sequence of motor signals that accurately bring the arm to a specified target. The motor signals produced by the cerebellum are specified in muscle synergy space. When the cerebellum fails to bring the arm to the target, an extra-cerebellar module performs low-quality connective movements, from which the cerebellum updates its program. In learning to perform the task, the cerebellum constructs an implicit inverse model of the plant. This model uses a combination of delayed sensory signals and recently-generated motor commands to compute the new output motor signal.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA |
Publisher | IEEE |
Pages | 6-12 |
Number of pages | 7 |
State | Published - Jan 1 1997 |
Event | Proceedings of the 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA - Monterey, CA, USA Duration: Jul 10 1997 → Jul 11 1997 |
Other
Other | Proceedings of the 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA |
---|---|
City | Monterey, CA, USA |
Period | 7/10/97 → 7/11/97 |
ASJC Scopus subject areas
- Computational Mathematics