Learning control of robot

The emulation of human learning has long been among the most sought after goals in the research of robotics and artificial intelligence. Human beings have the ability to learn from experience. A mechanical robot today can also learn from the past operation data to improve its performance. In this pr...

Full description

Saved in:
Bibliographic Details
Main Author: Lo, Kenneth Yih Hung.
Other Authors: Cheah Chien Chern
Format: Final Year Project
Language:English
Published: 2011
Subjects:
Online Access:http://hdl.handle.net/10356/45651
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:The emulation of human learning has long been among the most sought after goals in the research of robotics and artificial intelligence. Human beings have the ability to learn from experience. A mechanical robot today can also learn from the past operation data to improve its performance. In this project, a learning controller based on neural network will be designed and implemented on an industrial robot. Given a desired trajectory in task space, the learning controller is able to learn and eventually drive the closed loop system to follow the trajectory as the actions are repeated.