Aude Billard received her B.Sc. (1994) and M.Sc. (1995) in Physics from EPFL, with specialization in Particle Physics at the European Center for Nuclear Research (CERN), a MSc. in Knowledge-based Systems (1996) and a Ph.D. in Artificial Intelligence (1998) from the Department of Artificial Intelligence at the University of Edinburgh. She worked as Research associate (1999-2000) and then as Research Assistant Professor (2000-2004) at the department of Computer Science at the University of Southern California, where she retained an adjunct faculty position to this day. She was then an Assistant Professor at EPFL (2002-2004), where she became Associate Professor in January 2006.
Research at LASA seeks to push the barriers that prevent robots from getting out of the fully predetermined industrial world to the unpredictable, human-inhabited, world. To this end, we shy away from using simple and easy to handle objects, and tackle manipulation of complex and fragile objects, such as wine and champagne glasses. We visit realistic situations, in which robots get bumped around (e.g. while carrying a half-filled glass) and must recover from this perturbation adequately (e.g. to avoid spilling the liquid, while absorbing the shock to avoid hurting the human who bumped into it).
Industrial robots move extremely rapidly but with "unnatural" saccadic motions, with so-called "robotic" motions. We aim to develop robots that will no longer "move like robots".
Interacting with humans and acting in our daily environment requires robots to display a flexibility and compliance that industrial robots lack, but which is core to the way humans control their motions.
The controllers we develop allow robots to move seamlessly with smooth and human-like motions. These motions are more predictable for humans and participate in making the interaction safer and in enabling humans and robots to perform collaborative tasks.