A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
Compliant robot motion: I. A formalism for specifying compliant motion tasks
International Journal of Robotics Research
Knowledge-based artificial neural networks
Artificial Intelligence
An introduction to fuzzy control (2nd ed.)
An introduction to fuzzy control (2nd ed.)
On the design of a multimodal cognitive architecture for perceptual learning in industrial robots
MICAI'05 Proceedings of the 4th Mexican international conference on Advances in Artificial Intelligence
Learning and fast object recognition in robot skill acquisition: a new method
MCPR'10 Proceedings of the 2nd Mexican conference on Pattern recognition: Advances in pattern recognition
Experience-based optimization of universal manipulation strategies for industrial assembly tasks
Robotics and Autonomous Systems
Hi-index | 0.00 |
Industrial robots in poorly structured environments have to interact compliantly with this environment for successful operations. In this paper, we present a behaviour-based approach to learn peg-in-hole operations from scratch. The robot learns autonomously the initial mapping between contact states to motion commands employing fuzzy rules and creating an Acquired-Primitive Knowledge Base (ACQ-PKB), which is later used and refined on-line by a Fuzzy ARTMAP neural network-based controller. The effectiveness of the approach is tested comparing the compliant motion behaviour using the ACQ-PKB and a priori Given-Primitive Knowledge Base (GVN-PKB). Results using a KUKA KR15 industrial robot validate the approach.