First International Workshop on LEarning and data Mining for Robotics (LEMIR 2009)

Sep 7, 2009 in conjunction with ECML/PKDD-2009

Flyer (pdf, txt), Proceedings in pdf

Submission page (closed) (Springer Verlag LNCS format <= 15 pages)

Program
9:20- 9:30	Opening (Michèle Sebag and Einoshin Suzuki)
9:30-10:30	Invited talk (Chair: Shin Ando)
	Controlling Humanoid Robots by means of Genetic Programming (Hitoshi Iba)
10:30-11:00	(coffee break)
11:00-12:00	3 presentations (Chair: Hitoshi Iba)
	Quantification and Minimization of the Simulation-Reality-Gap on a BRIO(R) Labyrinth Game (Constantin Bergatt, Jan Hendrik Metzen, Elsa Kirchner, and Frank Kirchner)
	Toward Using Symbolic Discovery in Designing Controllers of Autonomous Swarm Robots (Einoshin Suzuki, Shigeru Takano, and Hiroshi Hirai)
	Robotics in Planetary Exploration (Lorenza Saitta, Attilio Giordana, and Ugo Galassi)
12:00-14:00	(lunch)
14:00-15:00	Invited talk (Chair: Kristian Kersting)
	A Road Map for Motor Skill Learning (Jan Peters)
15:00-15:20	(coffee break)
15:20-16:00	2 presentations (Chair: Jan Peters)
	Solving deterministic policy (PO)MDPs using Expectation-Maximisation and Antifreeze (Thomas Furmston and David Barber)
	Robot Control Learning in Continuous State and Action Spaces using 2 Actors and 1 Critic (Victor Uc-Cetina and Hans-Dieter Burkhard) (no show)
16:00-17:00	Panel
	Challenges of Machine Learning-based Autonomous Robotics (Chair: Michèle Sebag, Panelists: Jose L. Balcázar, Kristian Kersting, Jan Peters, Einoshin Suzuki)

Key Dates
Deadline for papers	June 15, 2009 (Extended)
Notification of the results	July 6, 2009 (Delayed. We apologize for this.)
Camera readies due	August 15, 2009 (9am JST)
Workshop	Sep 7, 2009

Overview
This workshop, collocated with the 19th European Conference on Machine Learning and the 12th Conference on Principles and Practice of Knowledge Discovery in Databases in Bled, Slovenia, aims at fostering research in Machine Learning and Data Mining applied to Robotics. All contributions related to

• Bayesian and probabilistic robotics,
• reinforcement learning and apprenticeship learning,
• learning from sensor data and logs (non exhaustive list)

are welcome. All contributions discussing issues such as:

• how to learn with/without a simulator, and how to face the reality gap
• how to build controllers that are robust with respect to motor/sensor failures
• how to derive self-driven criteria/goals for the robot
• how to deal with swarm robotics, distributed decision making and frugal communication,

are equally welcome. Finally, all contributions related to

• the exploitation of the robotic logs in order to debug/reverse engineer the controller

are welcome.

Program Committee
Einoshin Suzuki	Chair	(Kyushu University, Japan)
Michèle Sebag	Chair	(CNRS & Université Paris-Sud, France)
Shin Ando		(Gunma University, Japan)
Jose L. Balcázar		(Technical University of Catalonia, Spain)
Aude Billard		(Ecole Polytechnique Fédérale de Lausanne, Switzerland)
Nicolas Bredèche		(Université Paris-Sud, France)
João Gama		(University of Porto, Portugal)
Peter Grünwald		(CWI, Netherlands)
Hitoshi Iba		(University of Tokyo, Japan)
Kristian Kersting		(Fraunhofer IAIS & University of Bonn, Germany)
Jan Peters		(Max Planck Institute for Biological Cybernetics, Germany)
Marc Schoenauer		(INRIA & Université Paris-Sud, France)
Marc Toussaint		(Technical University of Berlin, Germany)
Takashi Washio		(Osaka University, Japan)

Related links
JST-ANR project, SYMBRION project, PASCAL Network of Excellence

Sponsors
Japan Science and Technology Agency(JST), Agence Nationale de la Recherche (ANR) PASCAL Network of Excellence