Abstract
This paper proposes an image-based visual servoing (IBVS) method for making a mobile robot follow a straight line path. The IBVS seems to be a human-like approach in the viewpoint that it controls robots based on the information of camera images without using the position of the robots. In order to determine the control input from the image information, a multilayered neural network-based controller that mimics the human brain is designed. A training method for the controller uses a back-propagation algorithm. The proposed method is evaluated by some simulations.
| Original language | English |
|---|---|
| Pages | 1306-1309 |
| Number of pages | 4 |
| Publication status | Published - Jan 1 2013 |
| Event | 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 - Nagoya, Japan Duration: Sept 14 2013 → Sept 17 2013 |
Other
| Other | 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 |
|---|---|
| Country/Territory | Japan |
| City | Nagoya |
| Period | 9/14/13 → 9/17/13 |
Keywords
- Image-based visual servoing
- Multilayered neural network
- Path following
ASJC Scopus subject areas
- Control and Systems Engineering
- Computer Science Applications
- Electrical and Electronic Engineering