GraphBot Technical Program

8:30 - 8:40 Welcome Remarks Rudolph Triebel
Session 1: Graphical Models in SLAM I
8:40 - 9:10 The Bayes Tree and Inference in Large-Scale Graphical Models for SLAM and SFM Frank Dellaert
9:10 - 9:40 iSAM and the Bayes Tree Michael Kaess
9:40 - 10:00 Hybrid Hessians for Real-Time, Collaborative SLAM of Large Outdoor Environments Matthew Koichi Grimes and Yann LeCun
Session 2: Training and Inference in Graphical Models
10:20 - 10:50 Lifted Message Passing Kristian Kersting
10:50 - 11:20 Linear Programming Decompositions for Distributed, Anytime Inference in Graphical Models Fabio Ramos
11:20 - 11:40 An EM Algorithm for Affordance Learning with Probabilistic Clustering Pedro Osório, Alexandre Bernadino, Ruben Martinez-Cantin, and José Santos-Victor
11:40 - 14:00 Lunch Break
Session 3: Graphical Models in SLAM II
14:00 - 14:30 Graphical Models for visual SLAM Kurt Konolige
14:30 - 14:50 A Balanced Distributed Graph-based Framework for Multi-Robot Mapping
Video multimap.avi
Video pal1.avi
Dario Lodi Rizzini and Stefano Caselli
Session 4: Graphical Models for Robot Perception
15:30 - 16:00 Graphical Models for Machine Perception Edwin Olson
16:00 - 16:30 A Probabilistic Framework for Learning Kinematic Models of Articulated Objects Wolfram Burgard
16:30 - 16:50 Probabilistic Temporal Prediction for Proactive Action Selection Woo Young Kwon and Il Hong Suh
16:50 - 17:20 Panel Discussion Moderated by V. Ila, R. Triebel, and T. Vidal-Calleja

Legend: Invited Talk Peer-reviewed Paper