University of Minnesota
University Relations
http://www.umn.edu/urelate
612-624-6868
myU OneStop


Go to unit's home.

Home | Seminars and Symposia | Past seminars/symposia: Tuesday, April 2, 2013

DTC Science and Technology Innovators Lecture Series

Toward Life-long Visual Localization and Mapping

by

John Leonard
MIT Computer Science and Artificial Intelligence Laboratory

Tuesday, April 2, 2013
3:30 p.m. reception
4:00 p.m. lecture

401/402 Walter Library

View webcast of this seminar

LeonardThis talk will describe recent work on localization and mapping for autonomous mobile robots. The first part of the talk will describe a system for temporally scalable visual SLAM using a reduced pose graph representation. Unlike previous visual SLAM approaches that maintain static keyframes, our approach uses new measurements to continually improve the map, yet achieves efficiency by avoiding adding redundant frames and not using marginalization to reduce the graph. To evaluate our approach, we present results using an online binocular visual SLAM system that uses place recognition for both robustness and multi-session operation. We demonstrate long-term mapping in a large multi-floor building, the MIT Stata Center, using approximately nine hours of data collected over the course of six months. In the second part of the talk, we will describe Kintinuous, a spatially extended KinectFusion algorithm that permits dense mesh-based mapping of extended scale environments in real-time. This is achieved by allowing the region of space being mapped to vary dynamically, extracting a dense point cloud from the regions that leave the KinectFusion volume due to this variation, and incrementally adding the resulting points to a triangular mesh representation of the environment. We also describe the integration of dense GPU-based RGB-D visual odometry and fused real-time surface coloring. Extensive experimental results are provided for a variety of environments. Joint work with Hordur Johannsson, Tom Whelan, Michael Kaess, Maurice Fallon and John McDonald. For more information see:

 

John J. Leonard is Professor of Mechanical and Ocean Engineering in the MIT Department of Mechanical Engineering and a member of the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). His research addresses the problems of navigation and mapping for autonomous mobile robots. He holds the degrees of B.S.E.E. in Electrical Engineering and Science from the University of Pennsylvania (1987) and D.Phil. in Engineering Science from the University of Oxford (formally 1994). With his students and collaborators, he has developed several state-of-the-art robot navigation and mapping systems for robots operating in underwater and terrestrial environments. He was team leader for MIT's DARPA Urban Challenge team, which was one of eleven teams to qualify for the Urban Challenge final event and one of six teams to complete the race. He has served as an associate editor of the IEEE Journal of Oceanic Engineering and of the IEEE Transactions on Robotics and Automation. Currently, he serves as Area Head for Ocean Science and Engineering in the MIT Department of Mechanical Engineering and as Co-Director of the Ford-MIT Alliance. He is the recipient of an NSF Career Award (1998), an E.T.S. Walton Visitor Award from Science Foundation Ireland (2004), and the King-Sun Fu Memorial Best Transactions on Robotics Paper Award (2006).