---
title: "Integrating Knowledge-Based System and Neural Network Techniques for Robotic Skill Acquisition"
authors:
  - "David Handelman"
  - "Stephen H. Lane"
  - "Jack Gelfand"
doi: ""
url: "https://ijcai.org/proceedings/1989/31"
pdf: "https://ijcai.org/proceedings/1989/0031.pdf"
venue: "Proceedings of the Eleventh International Joint Conference on Artificial Intelligence"
year: 1989
pages: "193-197"
track: "Parallel and Distributed Processing"
keywords:
---

# Integrating Knowledge-Based System and Neural Network Techniques for Robotic Skill Acquisition

David Handelman, Stephen H. Lane, Jack Gelfand

*Proceedings of the Eleventh International Joint Conference on Artificial Intelligence*, pages 193-197.

## Abstract

Thi s pa per describes an approach to robotic contr ol that is patterned after models of human skill acqulSlt.lOn. The intent is to develop robots ca pabl e oflearning how to accomplish complex tasks us ing designer-supplied instructions and se lf induced practice. A simulation is presented in which a rule-based system supervises the training of a n e ural network and controls the operation of the system during the learning process . Simulation results show the interaction between rul e -based and network-based system compon e nts during various phases of training and s up e rvision .