Quick links

Mapping, Localization, and Self-Driving Vehicles

Date and Time
Tuesday, November 10, 2015 - 4:30pm to 5:30pm
Location
Computer Science Small Auditorium (Room 105)
Type
CS Department Colloquium Series

This talk will discuss the critical role of mapping and localization in the development of self-driving vehicles.  After a discussion of some of the recent amazing progress and open technical challenges in the development of self-driving vehicles, we will discuss the past, present and future of Simultaneous Localization and Mapping (SLAM) in robotics.  We will review the history of SLAM research and will discuss some of the major challenges in SLAM, including choosing a map representation, developing algorithms for efficient state estimation, and solving for data association and loop closure.  We will also present recent results on object-based mapping in dynamic environments and real-time dense mapping using RGB-D cameras.

Joint work with Sudeep Pillai, Tom Whelan, Michael Kaess, John McDonald, Hordur Johannsson, Maurice Fallon, David Rosen, Ross Finman, Paul Huang, Liam Paull, Nick Wang, and Dehann Fourie.

John J. Leonard is Samuel C. Collins Professor of Mechanical and Ocean Engineering and Associate Department Head for Research in the MIT Department of Mechanical Engineering.  He is also 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 (1994).  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 is the recipient of an NSF Career Award (1998) and the King-Sun Fu Memorial Best Transactions on Robotics Paper Award (2006).  He is an IEEE Fellow (2014).

Follow us: Facebook Twitter Linkedin