Dense Map Inference with User-Defined Priors: From Priorlets to Scan Eigenvariations

When mapping is formulated in a Bayesian framework, the need of specifying a prior for the environment arises naturally. However, so far, the use of a particular structure prior has been coupled to working with a particular representation. We describe a system that supports inference with multiple priors while keeping the same dense representation. The priors are rigorously described by the user in a domain-specific language. Even though we work very close to the measurement space, we are able to represent structure constraints with the same expressivity as methods based on geometric primitives. This approach allows the intrinsic degrees of freedom of the environment's shape to be recovered. Experiments with simulated and real data sets will be presented.

[1]  A. Ruszczynski,et al.  Nonlinear Optimization , 2006 .

[2]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[3]  Henrik I. Christensen,et al.  Applying domain knowledge to SLAM using virtual measurements , 2010, 2010 IEEE International Conference on Robotics and Automation.

[4]  Roland Siegwart,et al.  A lightweight SLAM algorithm using Orthogonal planes for indoor mobile robotics , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Andrea Censi,et al.  On achievable accuracy for pose tracking , 2009, 2009 IEEE International Conference on Robotics and Automation.

[6]  Nancy M. Amato,et al.  Algorithmic Foundation of Robotics VII , 2008 .

[7]  Paul Newman,et al.  On the Structure and Solution of the Simultaneous Localisation and Map Building Problem , 1999 .

[8]  Wolfram Burgard,et al.  Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters , 2007, IEEE Transactions on Robotics.

[9]  Simon J. Julier,et al.  Towards the exploitation of prior information in SLAM , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[11]  Wesley H. Huang,et al.  Inferring and Enforcing Relative Constraints in SLAM , 2006, WAFR.

[12]  Joseph J. LaViola,et al.  On Kalman Filtering With Nonlinear Equality Constraints , 2007, IEEE Transactions on Signal Processing.

[13]  Wolfram Burgard,et al.  Gaussian Beam Processes: A Nonparametric Bayesian Measurement Model for Range Finders , 2007, Robotics: Science and Systems.

[14]  Wolfram Burgard,et al.  Large scale graph-based SLAM using aerial images as prior information , 2009, Auton. Robots.

[15]  D. Mumford,et al.  Riemannian Geometries on Spaces of Plane Curves , 2003, math/0312384.

[16]  Ramón Galán,et al.  Consistency of SLAM-EKF Algorithms for Indoor Environments , 2007, J. Intell. Robotic Syst..

[17]  D. Kendall,et al.  The Riemannian Structure of Euclidean Shape Spaces: A Novel Environment for Statistics , 1993 .

[18]  Ramón Galán,et al.  Consistency improvement for SLAM - EKF for indoor environments , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[19]  Lindsay Kleeman,et al.  Sonar based map building for a mobile robot , 1997, Proceedings of International Conference on Robotics and Automation.