CRV 2010

Joint conference information

CRV 2010 SLAM Camp

8:30am - 3:30pm, Saturday, 29 May 2010

University of Ottawa, SITE Building, Room ST E C0136

A free 'SLAM camp' will be held on Saturday May 29, 2010 in conjuction with the CRV conference.

Simultaneous Localization and Mapping (SLAM) is a probabilistic technique that attempts to accurately localize a vehicle (without the aid of GPS) while generating a map of its environment. Unique environmental features (landmarks) are extracted from sensor data (laser scanner, LIDAR, video CCD, for example) and are tracked across time and used as constraints to improve a robot's pose estimate. This improved pose estimate is, in turn, used to improve the estimated pose/position of the unique landmarks. SLAM has been actively investigated in the robotics industry for the last 15 years.

Location: Room ST E C0136 (SITE Building, UOttawa Campus). The SITE building is located at the south end of campus (opposite from downtown and hotels). Here is a map , pan down to the bottom of the map. Below the program is an embedded map.

Program

08:30-08:45 Workshop Welcome/Overview
08:45-09:20 Kalman Filters Mark Fiala (Ryerson University) - slides , - 1D gaussian demo - video: wmv, mp4, ogg
09:20-09:55 SLAM Techniques and Algorithms Jack Collier (Defence R&D Canada) - slides - video: wmv, mp4, ogg

09:55-10:10 Coffee Break

10:10-10:45 On the Representation and Estimation of Spatial Uncertainty Tim Barfoot (University of Toronto) - slides - video: wmv, mp4, ogg
10:45-11:20 Bundle Adjustment Paul Furgale (University of Toronto) - slides - video: wmv, mp4, ogg

11:20-12:00 Lunch

12:00-12:35 Data Association and Outlier Rejection Techniques for SLAM Chi Hay Tong (University of Toronto) - slides - video: wmv, mp4, ogg
12:35-13:10 Multi-Robot SLAM Keith Leung (University of Toronto) - slides - video: wmv, mp4, ogg
13:10-13:45 Appearance Only SLAM, Other topics Jack Collier (Defence R&D Canada) - slides - video: wmv, mp4, ogg
13:45-14:00 Coffee Break

14:00-14:35 The Unscented Kalman Filter for Pose Estimation Colin McManus (University of Toronto) - slides - video: wmv, mp4, ogg
14:35-15:10 Exploration Ioannis Rekleitis (McGill University) - slides - video: wmv, mp4, ogg
15:10-15:30 Robot Path Planning Alex Ufkes (Ryerson University) - slides - video: wmv, mp4, ogg

Description

A full day workshop exploring Simultaneous Localization and Mapping (SLAM) will be held in conjunction with the Seventh Canadian Conference on Robot Vision (CRV 2010). The workshop will explore concepts related to SLAM including basic formulation through to current state of the art techniques. Math is to be kept to a minimum with the focus on practical examples and key concepts. Goals of the workshop are to familiarize researchers with the core concepts of SLAM, to generate interest in academia for the SLAM problem, and to bring together Canadian SLAM researchers to explore possible collaborations.

Please find a PDF version of this invitation here .

Here is a map from Google to walk from the Novotel hotel to the SITE building.
View Larger Map

This workshop was organized by Jack Collier (jack.collier@drdc-rddc.gc.ca) and Mark Fiala (mark.fiala@ryerson.ca).