IOCoViST05

Postgraduate Studies and Continuing Education

 

International Online Course on Visual Servoing Techniques

October 17th - December 15th, 2005

Introduction

Visual servoing techniques use the information provided by one or several cameras in order to control the motions of a robotic system. By controlling between one and all the degrees of freedom of a system, we can carry out a great number of positioning tasks, or mobile target tracking. Whatever the sensor configuration, which can vary from one on-board camera to several free-standing cameras, the aim is to select the best set of measurements allowing to control the desired degrees of freedom, and to elaborate a control law so that these measurements reach a desired value.

Though the first systems date back to the late 1970s and early 1980s, it is not until the mid 1990s that there is a sharp increase in publications and working systems, due to the availability of fast and affordable vision processing systems. The issue has raised much attention from the main journals in vision and robotics, with the publication of special issues: 1996 IEEE Tr. on R&A 12(5) 1996, IEEE R&A Magazine 5 (4), 1998, IJCV 37 (1), 2000), IJRR 22(10-11) 2003, R&A (CFP 2004). Also Workshops, tutorials, invited sessions, have been organized in the framework of the most important robotics conferences throughout the world: ICRA, IROS, ICAR. The principal objective of this course is to provide a comprehensive overview of the key topics and state of the art in visual servoing techniques to last year engineering, master and PhD students. The course includes fundamental knowledge of image processing, robot control and visual feedback control. Also the last advanced issues in visual servoing systems will be presented.

The materials and practical exercises have been prepared and supervised by top-level researchers in this topic.

Aims and scope

This course aims to provide a global vision of the concepts and the state-of-the-art in visual servoing. Computer vision, sensor feedback, and robot control are multidisciplinarily considered. Theoretical concepts will be applied in simulations and real teleoperated robots.

Building upon previous successful events, namely EURON'02 Summer School on visual servoing and IROS'04 Tutorial on Advanced Visual Servoing, this course presents an e-learning experience aimed to students and researchers in visual control of robots.

Contents

 
Lecture 1: Introduction to Visual Servoing
  1.1.- Introduction
  1.2.-Visual Servoing schemes
  1.3.-Homogeneous transformations
  1.4.-Rigid body motion
  1.5.-Computer vision fundamental
  1.6.-Dynamic and kinematic control of robots
  1.7.-Sensor-based control: Task Function Approach
  1.8.-Overview in Visual Servoing and Applications
Lecture 2: Modelling in Visual Servoing
  2.1.-2D visual features
  2.2.-Path planning in the image
  2.3.-3D Features
  2.4.-Omni-directional vision
  2.5.-Coupling vision and structured light
Lecture 3: Classical approaches
  3.1.-Image based visual servoing
  3.2.-Position based visual servoing
Lecture 4: Hybrid approaches
  4.1.-2 ½D
  4.2.-Partitioned approach to 2D visual servoing
  4.3.-Switching approach
  4.4.-E2D visual servoing
Lecture 5: Advanced approaches to vision-based control
  5.1.-Intrinsic-free visual servoing
  5.2.-Visual servoing using efficient second-order minimization
  5.3.-Tasks sequencing for visual servoing
Lecture 6: Dynamic visual servoing
Lecture 7: Robustness
  7.1.-Introduction to robustness issue in visual servoing
  7.2.-Visibility constraint
  7.3.-Image Outliers
  7.3.-Real features integration for Visual Servoing

Lecture 8: Applications

 

Organization

 
Contact persons:
Enric Cervera
Jaume-I University, Spain
enric.cervera@icc.uji.es
 
Nicolas M. Garcia Aracil
Miguel Hernandez University, Spain
nicolas.garcia@umh.es

Advisory Committee:

  • Prof. Philippe Martinet (IFMA – France)
  • Dra. Danica Kragic (KTH – Sweden)
  • Prof. François Chaumette (IRISA – France)
  • Prof. Gregory D. Hager (JHU – USA)
  • Dr. Ezio Malis (INRIA – France)
  • Prof. Seth Hutchinson (UIUC – USA)
  • Prof. Peter Corke (CSIRO – Australia)
  • Prof. Koichi Hashimoto (IC - Japan)