3D Geometry meets Learning

Speaker:  Peyman Moghadam – Brisbane, QLD, Australia
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Abstract

In this lecture, I will give an overview of current Deep Learning methods for lidar-based place recognition. Place recognition aims to associate input lidar data to a global map or database of previously visited places in an environment. This task is essential for loop closure during Simultaneous Location and Mapping (SLAM) or global relocalization of an autonomous robot in an existing map. I will then discuss new challenges for current learning methods such as long-term re-localization, and domain shifts. 

About this Lecture

Number of Slides:  50
Duration:  60 minutes
Languages Available:  English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.