1st Workshop on

Robust and Multimodal Inference

in Factor Graphs


Workshop Motivation and Objectives

This full-day workshop at ICRA13 brings together researchers working in different fields of robotics to discuss novel concepts and ideas for robust as well as multimodal or non-Gaussian inference in factor graphs.

The workshop features two tutorials by Frank Dellaert and Michael Kaess that introduce the state of the art to participants without previous experiences in the field. Two invited talks by Andrew Davison and Edwin Olson and a number of contributed talks discuss the newest developments, concepts and ideas in the areas covered by the workshop topics. These topics comprise novel techniques for outlier detection and rejection as well as modeling and inference with multimodal or non-Gaussian measurement likelihoods and posteriors. A special interest of the workshop are the challenges arising from incremental applications of inference, such as information fusion in dynamic systems.

The workshop very explicitly aims at a larger audience and beyond the usual pose graph SLAM applications of factor graphs.


  1. May 1st: Updated workshop program is online.

  2. May 4th: The contributed papers are online.

Important Dates

  1. May 10th 2013    The workshop takes place in the room „Kleiner Saal“ in the „Konzerthaus“.


Bildquelle: Stadt Karlsruhe