Skip to content Skip to navigation
Faculty Candidate Talk
3/30/2015 10:30 am
CoRE Lecture Hall (Room 101)

Robot Learning: Algorithms and Applications

Abdeslam Boularias, National Robotics Engineering Center, Carnegie Mellon University

Faculty Host: Dimitris Metaxas

Abstract

Machine learning provides powerful tools for solving problems in robotics that, due to their complexity, cannot be addressed solely by engineering. Object recognition is a prime example of a robot vision problem that can hardly be solved without any learning. Grasping and manipulating unknown objects is another type of a robotic task that is difficult to solve by hand-coding. Robotics also provides researchers in machine learning with interesting new challenges. For instance, the field of reinforcement learning has been deeply shaped by problems that typically arise in robotics, such as partial observability. Another example is learning by demonstration, which is a particular type of supervised learning that is specific to robotics.

The research area at the intersection of machine learning and robotics is known as robot learning. The question driving research in this area is: How can a robot learn from experience to perform complex tasks? My talk will focus on problems in machine learning that originate from robotics. In particular, I will present challenging problems related to reinforcement learning and to learning by demonstration. I will show how these problems can be efficiently solved by formulating them as optimization ones, derived from high principles such as entropy minimization. I will also show how the proposed algorithms were applied in robotics.

Bio

Abdeslam Boularias is a Postdoctoral Fellow at Carnegie Mellon University's National Robotics Engineering Center in Pittsburgh. He works on machine learning for sequential decision-making, and on robot learning in particular. Abdeslam received a Bachelor of Engineering degree in computer engineering in 2004 from the École Nationale Supérieure d’Informatique (Algeria). He received a Master's degree in computer science from Paris-Sud University (France) in 2005, and a Ph.D. degree from Laval University (Canada) in 2010. During his studies at Paris-Sud, Abdeslam was a research assistant with the INRIA Saclay Institute, where he developed tools for assessing fault tolerance in Grid Computing. During his Ph.D., he proposed several novel algorithms for reinforcement learning and planning in partially observable environments. Prior to joining Carnegie Mellon University in May 2013, Abdeslam was a research scientist at the Max Planck Institute for Intelligent Systems in Tuebingen (Germany) from August 2010 to April 2013, where he worked in the Empirical Inference department with Jan Peters and Bernhard Schoelkopf.