Fusing sonars and LRF data to perform SLAM in reduced visibility scenarios

Simultaneous Localization and Mapping (SLAM) approaches have evolved considerably in recent years. However, there are many situations which are not easily handled, such as the case of smoky, dusty, or foggy environments where commonly used range sensors for SLAM are highly disturbed by noise induced in the measurement process by particles of smoke, dust or steam. This work presents a sensor fusion method for range sensing in Simultaneous Localization and Mapping (SLAM) under reduced visibility conditions. The proposed method uses the complementary characteristics between a Laser Range Finder (LRF) and an array of sonars in order to ultimately map smoky environments. The method was validated through experiments in a smoky indoor scenario, and results showed that it is able to adequately cope with induced disturbances, thus decreasing the impact of smoke particles in the mapping task.

[1]  Maria Teresa Lazaro,et al.  Multi-robot SLAM using condensed measurements , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Lino Marques,et al.  Assessment of Laser Range Finders in risky environments , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Hugh F. Durrant-Whyte,et al.  Simultaneous localization and mapping: part I , 2006, IEEE Robotics & Automation Magazine.

[4]  R. Siegwart,et al.  Noise characterization of depth sensors for surface inspections , 2012, 2012 2nd International Conference on Applied Robotics for the Power Industry (CARPI).

[5]  Nuno M. Fonseca Ferreira,et al.  A fuzzified systematic adjustment of the robotic Darwinian PSO , 2012, Robotics Auton. Syst..

[6]  Rui P. Rocha,et al.  T-SLAM: Registering topological and geometric maps for robot localization in large environments , 2008, 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems.

[7]  Rui P. Rocha,et al.  T-SLAM: Registering Topological and Geometric Maps for Robot Localization , 2009 .

[8]  David Portugal,et al.  An evaluation of 2D SLAM techniques available in Robot Operating System , 2013, 2013 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).

[9]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[10]  Jorge Dias,et al.  Probabilistic Approaches to Robotic Perception , 2014, Springer Tracts in Advanced Robotics.

[11]  Paulo Menezes,et al.  The CHOPIN project: Cooperation between human and rObotic teams in catastrophic incidents , 2013, 2013 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).

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

[13]  Pedro J. Sanz,et al.  Multi-Sensor Localization and Navigation for Remote Manipulation in Smoky Areas , 2013 .

[14]  Viatcheslav Tretyakov,et al.  Range sensors evaluation under smoky conditions for robotics applications , 2011, 2011 IEEE International Symposium on Safety, Security, and Rescue Robotics.

[15]  Thierry Peynot,et al.  Laser-to-radar sensing redundancy for resilient perception in adverse environmental conditions , 2012, ICRA 2012.

[16]  Tobias Deissler,et al.  UWB SLAM with Rao-Blackwellized Monte Carlo data association , 2010, 2010 International Conference on Indoor Positioning and Indoor Navigation.