EPFL

EPFL is a leading technical research university. It covers disciplines such as mathematics, physics, chemistry, engineering science, life science, and information technology. EPFL is also the host of large national centres of competence and research, particularly in communication systems and photonics. EPFL is well known in mobile robotics thanks to success stories such as the Khepera robots, and the multiple laboratories involved in robotics-related research. These laboratories belong to the Schools of Engineering and of Computer and Communication Sciences. The total number of people working in robotics at EPFL is approximately 100, of whom 6 are professors. Their laboratories cover a large range of topics including mechatronic design, navigation, locomotion, learning, perception, and rehabilitation. They share state-of-the art facilities and workshops.

In ANGELS, EPFL will deploy two laboratories:

BIRG (Biologically Inspired Robotics Group) : The Biologically Inspired Robotics Group (BIRG) is composed of 1 professor (Auke Ijspeert), 1 postdoc, 5 PhD students, 1 programmer, and 1 technician. BIRG carries out research on locomotion and movement control in biologically inspired robots, in learning, as well as in computational neuroscience. The types of robots used for research at BIRG include amphibious snake robots, salamander robots, quadruped robots, and humanoid robots. Particularly relevant for this project is the Amphibot II robot, a lamprey/snake robot capable of swimming and crawling, and Salamandra robotica, a salamander robot capable of swimming and walking. Various models of lamprey and salamander central pattern generators (CPGs) developed at BIRG exploit leaky-integrator neural networks and systems of coupled non-linear oscillators. In ANGELS, BIRG will be responsible for designing the locomotion and navigation controllers for the robots (WP3 and 6). It will also provide several prototypes of Amphibot, a lamprey-like swimming robot that will be used as starting point for design the new robot of ANGELS.

CVLab (Computer Vision Laboratory): The research activities of the Computer Vision Laboratory (CVLab) focus on shape and motion recovery from video sequences. This includes human body modeling, fast object detection, and real-time reconstruction of deformable 3D surfaces. CVLab also provides undergraduate and graduate teaching and performs technology transfer to both established and start up companies. CVLab’s current staff includes one professor, three post-doctoral fellows and twelve doctoral students. They are funded in part by the Swiss Federal Institute of Technology, the National Swiss Research Foundation, and the Federal Office for Education and Science and in part by several European Union projects. In ANGELS, CVLab will focus on giving the robots the ability to perceive and interpret their environment based on their electric sense. Particularly relevant for this project is a new research effort in modeling the electric sense of electric fishes that has been started in collaboration with biologists at IIBCE and UDELAR in Montevideo, Uruguay. CVLab is developing electrolocation techniques using electrostatic tomography algorithms coupled with statistical learning techniques.

Key personnel for EPFL-BIRG-CVLab

Prof. Auke Ijspeert is the director of the Biologically Inspired Robotics Group (BIRG) in the School of Computer and Communication Sciences at EPFL. He is also affiliated to the University of Southern California. His research interests are at the intersection between robotics, computational neuroscience, nonlinear dynamical systems, and machine learning. He uses numerical simulations and robots to get a better understanding of the functioning of animals, and inspiration from biology to design novel types of robots and adaptive controllers. He has published over 60 peer-reviewed articles (some of them in high impact journals such as Science), and is regularly invited to give presentations on these topics. With his colleagues, he has received the Best Paper Award at ICRA2002, the Industrial Robot Highly Commended Award at CLAWAR2005, and Best paper award at Humanoids 2007. He was the Technical Program Chair of 5 international conferences (BioADIT2004, SAB2004, AMAM2005, BioADIT2006, EPFL-LATSIS2006), and has been a program committee member of over 35 conferences.

Prof. Pascal Fua received a degree from the Ecole Polytechnique, Paris, in 1984 and a Ph.D. in Computer Science from the University of Orsay in 1989. He joined EPFL in 1996 where he is now a Professor in the School of Computer and Communication Science. Before that, he worked at SRI International and at INRIA Sophia-Antipolis? as a computer scientist. His research interests include human body modelling from images, optimization-based techniques for image analysis and synthesis, and using information theory in the area of model-based vision. In 2006/2007, he spent a sabbatical year in Montevideo, Uruguay working on the perception of electric fish. He has (co)authored over 200 publications in refereed journals and conferences. He is a member of the editorial board of the IEEE journal Transactions for Pattern Analysis and Machine Intelligence and has been a program committee member of several major vision conferences.

Dr. V. Lepetit received engineering and master degrees in Computer Science from the ESIAL in 1996, and a doctorate in Computer Vision in 2001 from the University of Nancy, France, after working in the ISA INRIA team. He then joined the Virtual Reality Lab at EPFL (Swiss Federal Institute of Technology) as a post-doctoral fellow and became a founding member of the Computer Vision Laboratory. He has received several awards in Computer Vision including the best paper award at CVPR 2005. His research interests include vision-based Augmented Reality, 3D camera tracking, and 3D detection in monocular sequences.

References

• http://www.epfl.ch/
• http://birg.epfl.ch/
• http://cvlab.epfl.ch/

---