Events Calendar

CS Colloquium: Michael Kaess (CSAIL, MIT)

Speaker: Michael Kaess, CSAIL, MIT

Talk Title: Robust and Efficient Real-time Mapping for Autonomous Robots

Series: CS Colloquium

Abstract: We are starting to see the emergence of autonomous robots that operate outside of controlled factory environments in various applications ranging from driverless cars, space and underwater exploration to service robots for businesses and homes. One of the very first challenges encountered on the way to autonomy is perception: obtaining information about the environment that allows the robot to efficiently navigate through, interact with and manipulate it. Moreover, in many such applications, models of the environment are either unavailable or outdated, thus necessitating real-time robotic mapping using onboard sensors.

In this talk I will present my recent research on efficient optimization techniques for robotic mapping, and in particular focus on the recently developed incremental nonlinear least-squares solver, termed incremental smoothing and mapping (iSAM2). Based on our new probabilistic model called the Bayes tree, iSAM2 efficiently updates an existing solution to a least-squares problem after new measurements are added. I will describe some of the key aspects of my work and also address robustness in optimization. Lastly, I will present applications enabled by iSAM2 including our long-term visual mapping and Kintinuous -- our recent work on dense mapping with RGB-D cameras.

Biography: Michael Kaess is a Research Scientist in the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology (MIT), where he previously also was a Postdoctoral Associate. He received the Ph.D. and M.S. degrees in computer science from the Georgia Institute of Technology in 2008 and 2002, respectively. His research focuses on probabilistic methods for robot perception. He was one of the two runner-ups for the 2012 Volz dissertation award for the best U.S. Ph.D. thesis in robotics and automation that takes into account impact four years after publication.

Host: Fei Sha

Location: Seaver Science Library (SSL) - 150

Audiences: Everyone Is Invited

Contact: Assistant to CS chair