IROS03 Workshop Robot Progamming by Demonstration

IROS-2003 WORKSHOP ON

Robot Programming by Demonstration

Friday 31st of October 2003, 12pm-6pm

IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems IROS 2003

Bally's Las Vegas Hotel, October 27 - 31, 2003

Overview

Objectives
Call for Papers (The call is now closed)
Important Dates
Instructions for Final Submissions Updated!

Objectives

Programming by demonstration has become a key research topic in robotics. It impacts both fundamental research and application-oriented studies. Work in that area tackles the development of robust algorithms for motor control, motor learning, gesture recognition and visuo-motor integration. While the field existed for more than twenty years, recent developments, taking inspiration in biological mechanisms of imitation, have brought a new perspective, which this workshop aims at assessing.

Studies of imitation in biological systems stressed a number of key issues that are, also, of concerns to Robotics. These are the need to define a metric of imitation performance and the need to determine a representation common to visual and motor systems.

The workshop will address the following key questions:>

- What should the robot imitate, i.e. which features of the task should be reproduced?

- Can imitation use known motor learning techniques or does it require the development of new

learning and control policies?

- How could the metric drive the choice of learning technique?

- Does imitation speed up skill learning in robots?

- What are the costs of imitation learning?

- How could we define a general metric of imitation performance?

- Are there skills that could not be acquired without demonstration?

- Should gesture recognition and motor learning algorithms be context-specific?

- Can one find a level of representation of movement common to both gesture recognition and motor control?

- How can models of human kinematics, used in gesture recognition, drive the reproduction of the task?

Call for Papers

We solicit papers relevant to the general workshop theme in the three categories:

research papers

application papers

challenge/position statements (typically only 1 or 2 pages)

Relevant workshop topics include (non-exhaustive list):

Programming by Demonstration
Imitation learning
Task and Skill Learning
Motor control
Motor learning
Visuo-motor Integration
Gesture recognition

Important Dates

August 4, 2003	Deadline for paper submission
August 15, 2003	Notification of acceptance
August 30, 2003	Deadline for final contributions
October 31, 2003	Workshop

Final Submission Instructions

New! Instructions for authors invited to submit their paper for publication in the special issue on "Robot Learning by Demonstration" of the Robotics and Autonomous Systems journal can be found here.

Program (Preliminary)

TIME	TITLE
12:00	Welcome and overview, Aude Billard & Roland Siegwart
PART 1: Invited Speakers
12:10	Rudiger Dillmann Teaching and Learning of Robot Tasks via Observation of Human Performance
12:30	Helge Ritter, Robotics: A data mining perspective
12:50	Jianwei Zhang Self-Valuing Learning and Generalization of Visually Guided Grasping
13:10	Ales Ude Using motion capture techniques to program high degree of freedom humanoid robot motion
13:30	Jun Nakanishi, Learning from Demonstration and Adaptation of Biped Locomotion
13:50	Auke Jan Ijspeert, Imitation of Human-Demonstrated Movements with Nonlinear Dynamical Systems in Humanoid Robots
14:10	Aude Billard, Common Issues to Robotics and Biological Approaches to Imitation Learning
14:30	Coffee break (30 min)
PART 2: Accepted Papers
15:00	Leveraging on a Virtual Environment for Robot Programming by Demonstration Jacopo Aleotti, Stefano Caselli, Monica Reggiani
15:20	A Posture Sequence Learning System for an Anthropomorphic Robotic Hand Ignazio Infantino, Antonio Chella, Haris Džindo, Irene Macaluso
15:40	Motor Representations for Hand Gesture Recognition and Imitation Manuel Cabido Lopes & Jose Santos-Victor
16:00	Improving Robot Programming Flexibility through Physical Human Robot Interaction M. Frigola, J. Poyatos , A. Casalsand J. Amat
16:20	Learning Issues in a Multi-Modal Robot-Instruction Scenario J. J. Steil, F. Rothling, R. Haschke, and H. Ritter
16:40	Towards Integrating Learning by Demonstration and Learning by Instruction in a Multimodal Robot. Stefan Wermter, Mark Elshaw, Cornelius Weber, Christo Panchev, Harry Erwin
17:00	Learning From Observation and Practice Using Primitives Darrin C. Bentivegna, Christopher G. Atkeson, Gordon Cheng
17:20	Teaching Bayesian Behaviours to Video Game Characters Ronan Le Hy Anthony Arrigoni Pierre Bessi`ere Olivier Lebeltel
17:40	Towards Robot Intermodal Matching Using Spiking Neurons Emachi Eneje & Yiannis Demiris
18:00	Wrap-up and Goodbye ---- Aude Billard & Roland Siegwart

Organizers

Program Chairs
Aude Billard & Roland Siegwart

Autonomous Systems Lab
Swiss Federal Institute of Technology - EPFL
CH-1015 Lausanne, Switzerland
tel: +41 (21) 693.54.64
fax: +41 (21) 693.78.06
email: aude.billard@epfl.ch

Program Committee

Luc Berthouze, AIST, Japan

Henrik Christensen, KTH, Sweden

Kerstin Dautenhahn, University of Hertfordshire, UK

Yiannis Demiris, Imperial College London, UK

Rudiger Dillmann, University of Karlsruhe, Germany

Auke Jan Ijspeert, EPFL, CH

Helge Ritter, University of Bielefeld, Germany

Stefan Schaal, University of Southern California, USA

Ales Ude, ATR, Japan

Jianwei Zhang, University of Hamburg, Germany

Proceedings

A hard copy of the workshop proceedings will be distributed at the Workshop (Pdf File is 9Mb!)
A selected number of papers presented in this workshop will appear in a special issue of the Robotics and Autonomous Systems journal, to be published in Spring 2004.

Last update: 17.10.03/ab