Spring 2011 GRASP Seminar - Siddhartha Srinivasa, Intel Labs Pittsburgh, "Enabling Mobile Manipulation in the Real World"

Abstract: Robots are extremely effective in environments like factory floors that are structured for them, and currently ineffective in environments like our homes that are structured for humans. At the Personal Robotics Lab, we are developing building blocks of perception, navigation, manipulation, and interaction to enable robots to perform useful tasks in environments structured for humans.

In this talk, I will focus on our work on manipulation: extending randomized planners to constraint manifolds, and leveraging the mechanics of manipulation for planning under clutter and uncertainty. I will also describe our learnings from integrating our algorithms on our robot HERB, a bi-manual mobile manipulator that we built, comprised of two Barrett WAM arms on a Segway base equipped with a suite of image and range sensors.

Presenter's biography

Dr. Siddhartha Srinivasa is a Senior Research Scientist with Intel Labs Pittsburgh.  He founded the Personal Robotics Lab (http://personalrobotics.intel-research.net/) at Intel Pittsburgh and co-directs the Manipulation Lab at CMU.  Dr. Srinivasa's research focus is on developing perception, planning, and learning algorithms that enable robots to accomplish useful manipulation tasks in dynamic and cluttered indoor environments. He co-founded the IEEE RAS Technical Committee on Mobile Manipulation in 2010, is an Associate Editor of IEEE ICRA 2010, 2011, and an Area Chair for RSS 2011. Dr. Srinivasa's work won the Best Paper Award at HRI 2010, and was a Finalist at IEEE ICRA 2009 and 2010, and IROS 2010.