Print | Login
graphs/graph_epfl.gif
anglais seulement
EPFL  >  Robotics@EPFL
title_robotics_center_2.jpg
RESEARCH GROUPS

School of Engineering

LIS Laboratory of Intelligent Systems Dario Floreano
BIOROB Biorobotics Laboratory Auke Jan Ijspeert
LASA Learning Algorithms and Systems Laboratory Aude Billard
LSRO1 Laboratory of Robotics Systems 1 Hannes Bleuler
LSRO2 Laboratory of Robotics Systems 2 Raymond Clavel
MOBOTS Miniature Mobile Robots Group Francesco Mondada
NEURO Center for Neuroprosthetics Jose Millan

School of Architecture, Civil and Environmental Engineering

DISAL

Distributed Intelligent Systems and Algorithms Laboratory

Alcherio Martinoli

Collaborating Laboratories

School of Life Sciences

LNMCLaboratory of Neural MicrocircuitryHenry Markram
UPNICUPNICMiguel Nicolelis

University of Lausanne

DEEDepartment of Ecology and EvolutionLaurent Keller



Welcome to the EPFL Robotics Portal. This website provides a single entry to all robotics activities at EPFL.

Robotics research at EPFL spans several fields, such as industrial and biomedical robotics, mobile robotics, educational robotics, bio-inspired robotics, human-robot interaction, collective robotics, neuro-prosthetic robotics, and robotics artificial intelligence.

Students at EPFL can specialize in robotics by taking the master in micro-engineering and/or the doctoral school in production and robotics systems.

   

UPCOMING SEMINAR

 
Hod Lipson

Hod Lipson
Analysis by Synthesis: From Cognitive Robotics to Computational Biology

Monday 6th of September 2010, 12:00 AM, INM202

Abstract:

Over the last few decades, evolutionary algorithms have become increasingly popular as a tool for automatically synthesizing solutions to open ended problems. The same process, however, can be reversed for analysis: Starting with an existing solution, evolutionary processes can be used as a reverse engineering tool: We evolve models rewarding those that exhibit behavior that is similar to an observed behavior. The resulting evolved models then essentially provide hypotheses about the hidden target object.

This talk will discuss this process, known as "analysis by synthesis", and demonstrate its application across a number of fields ranging from robotics to biology, where analysis challenges are plentiful. In particular, co-evolving tests can serve to disambiguate competing candidate models, essentially "asking questions" that help guide the analysis. Ultimately, can the machine generate new knowledge? We will see what happens when the machine discovers models that we cannot yet explain, giving a glimpse of what might be the future of science.

Biography:

Hod Lipson is an Associate Professor of Mechanical & Aerospace Engineering and Computing & Information Science at Cornell University in Ithaca, NY. He directs the Computational Synthesis group, which focuses on novel ways for automatic design, fabrication and adaptation of virtual and physical machines. He has led work in areas such as evolutionary robotics, multi-material functional rapid prototyping, machine self-replication and programmable self-assembly. Lipson received his Ph.D. from the Technion - Israel Institute of Technology in 1998, and continued to a postdoc at Brandeis University and MIT. His research focuses primarily on biologically-inspired approaches, as they bring new ideas to engineering and new engineering insights into biology. For more information visit http://www.mae.cornell.edu/lipson.


Please send seminar announcements to Sabine Hauert.




PREVIOUS SEMINARS

Previous seminars can be found here.

SEARCH TOOLS
 this site
 a person
 a place

  OK
EDUCATION
OPEN POSITIONS
[28 June 2010]
PhD position open at the Laboratory of Intelligent Systems.

EXPO'02 project
The Expo'02 Robotics project is no longer hosted on this website. The new URL can be found here.

CONTACTS

Robotics@EPFL
c/o
Ecole Polytechnique Fédérale de Lausanne
EPFL-STI-I2S-LIS
Station 11
CH-1015 Lausanne Switzerland

Phone: +41 21 693 59 66
Fax: +41 21 693 58 59

Secretary: Michelle Wälti

Visits
For lab tours of 5 or more people, please contact Jean-Christophe Zufferey with statement of motivation and list of visitors.
For smaller groups, please contact directly the laboratory that interests you most.