Abstract
Recurrent networks are proposed for designing neurocontrollers in robotic control systems. An evolutionary algorithm is used to develop a neurocontroller for a robot clearing an arena by pushing boxes to the enclosing walls. The number of boxes that the robot pushes to the walls, within an allocated time, is the measure of its fitness. The initially feedforward networks evolve and produce high fitness neurocontrollers with 30% (and sometimes even 70%) fewer recurrent links compared to networks fully recurrent from the start.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of the National Conference on Artificial Intelligence |
Editors | Anon |
Publisher | AAAI |
Pages | 1378 |
Number of pages | 1 |
Volume | 2 |
State | Published - 1996 |
Event | Proceedings of the 1996 13th National Conference on Artificial Intelligence. Part 2 (of 2) - Portland, OR, USA Duration: Aug 4 1996 → Aug 8 1996 |
Other
Other | Proceedings of the 1996 13th National Conference on Artificial Intelligence. Part 2 (of 2) |
---|---|
City | Portland, OR, USA |
Period | 8/4/96 → 8/8/96 |
All Science Journal Classification (ASJC) codes
- Software