The Teleworkbench: A Platform for Performing and Comparing Experiments in Robot Navigation

Experiments are essential ingredients of science to compare, validate or refute theories, methodologies, hypotheses and approaches. However, in robotics, the comparison of methods using experiments is difficult because of the variety of robotic platforms and experiment environments. In this paper we describe the Teleworkbench and discuss the role it can take on the quest of creating repeatable and reproducible experiments in robot navigation, obtaining com- parable results as well as evaluating and analysing results. The Teleworkbench can control up to 64 mini-robots simultaneously, log user defined quantities for post-experiment analysis and monitor the experiments via cameras mounted in the ceiling. A web interface makes the Teleworkbench accessible for remotely located users. Thus, the Teleworkbench is a platform that robotic scientists can use in order to evaluate the developed approaches quantitatively and qualitatively as well as to com- pare their methods amongst each other.

[1]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Spyros G. Tzafestas,et al.  Web-Based Control and Robotics Education , 2009 .

[3]  Ulrich Rückert,et al.  Teleworkbench: A Teleoperated Platform for Multi-Robot Experiments , 2005, AMiRE.

[4]  Richard T. Vaughan,et al.  The Player/Stage Project: Tools for Multi-Robot and Distributed Sensor Systems , 2003 .

[5]  Anil K. Jain,et al.  Handbook of Face Recognition, 2nd Edition , 2011 .

[6]  B. Caputo,et al.  Cold: the Cosy Localization Database Cold: the Cosy Localization Database , 2009 .

[7]  Howie Choset,et al.  A multi-hypothesis topological SLAM approach for loop closing on edge-ordered graphs , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Ulf Witkowski,et al.  MPEG-4-Based Interactive Visualization as an Analysis Tool for Experiments in Robotics , 2006, MSV.

[9]  Sebastian Thrun,et al.  Simultaneous Localization and Mapping , 2008, Robotics and Cognitive Approaches to Spatial Mapping.

[10]  Frédéric Maire,et al.  Topological SLAM using neighbourhood information of places , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Cyrill Stachniss,et al.  On measuring the accuracy of SLAM algorithms , 2009, Auton. Robots.

[12]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[13]  Sebastian Thrun,et al.  Probabilistic Algorithms in Robotics , 2000, AI Mag..

[14]  Giulio Fontana,et al.  Rawseeds ground truth collection systems for indoor self-localization and mapping , 2009, Auton. Robots.

[15]  Ulrich Rückert,et al.  BeBot: A Modular Mobile Miniature Robot Platform Supporting Hardware Reconfiguration and Multi-standard Communication , 2009, FIRA RoboWorld Congress.

[16]  Ulrich Rückert,et al.  Effect of global position information in unknown world exploration - A case study using the Teleworkbench , 2009, Robotics Auton. Syst..

[17]  Ulrich Rückert,et al.  Teleworkbench: A Teleoperated Platform for Experiments in Multi-robotics , 2009 .

[18]  Monica Reggiani,et al.  An insightful comparison between experiments in mobile robotics and in science , 2009, Auton. Robots.

[19]  Shulamith Kreitler,et al.  The role of the experiment in science education , 1974 .