Automated Testing of Workshop Robot Behavior

Authors: Arne Hitzmann, Philipp Wentscher, Alexander Gabel, Reinhard Gerndt

Abstract:

Autonomous mobile robots can be found in a wide field of applications. Their types range from household robots over workshop robots to autonomous cars and many more. All of them undergo a number of testing steps during development, production and maintenance. This paper describes an approach to improve testing of robot behavior. It was inspired by the RoboCup @work competition that itself reflects a robotics benchmark for industrial robotics. There, scaled down versions of mobile industrial robots have to navigate through a workshop-like environment or operation area and have to perform tasks of manipulating and transporting work pieces. This paper will introduce an approach of automated vision-based testing of the behavior of the so called youBot robot, which is the most widely used robot platform in the RoboCup @work competition. The proposed system allows automated testing of multiple tries of the robot to perform a specific missions and it allows for the flexibility of the robot, e.g. selecting different paths between two tasks within a mission. The approach is based on a multi-camera setup using, off the shelf cameras and optical markers. It has been applied for test-driven development (TDD) and maintenance-like verification of the robot behavior and performance.

Keywords: Supervisory control, Testing, Markers, Mono Vision, Automation.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1092321

References:

[1] Saddek Bensalem, Laindra de Silva, Flix Ingrand, and Rongjie Yan. A verifiable and correct-by-construction controller for robot functional levels. Journal of Software Engineering for Robotics, 2(1):1-19, September 2011.
[2] J.J. Aguilar, and F. Torres, M.A. Lope. Stereo vision for 3D measurement: accuracy analysis, calibration and industrial applications. Measurement, 193200, Volume 18, Issue 4, August 1996.
[3] M. Fiala. ARTag Revision 1. A Fiducial Marker System Using Digital Techniques. NRC 47419, pages 46, November 24, 2004.
[4] G. D. Hager. A modular system for robust positioning using feedback from stereo vision. Robotics and Automation, IEEE Transactions, 582-595, Volume 13, Issue 4, August 1997.
[5] H. K.Nishihara. PRISM: A Practical Real-Time Imaging Stereo Matcher. Optical Engineering, Volume 23, no. 5, 1984.
[6] M. Bertozzi, A. Broggi, A. Fascioli, and S. Nichele.Stereo Vision-based Vehicle Detection. IEEE Intelligent Vehicles Symposium, 2000.
[7] Jung-Rye Son, Tae-Yong Kuc, Jong-Loo Park, and Hong-Seak Kim. Simulation based functional and performance evaluation of robot components and modules. Information Science and Applications (ICISA) International Conference, 1-7, IEEE, April 2011.
[8] Enrique Medinaa, Eduardo Parrillaa, Alvaro Pagea, Jose Olasoa, Juan Carlos Gonzleza, and Helios De Rosarioa. A new non-invasive and low cost method for the characterisation of pronation patterns by using AR-markers and functional classification. Footwear Science, Volume 5, Supplement 1, 2013.
[9] Gontje C. Claasen, Philippe Martin, and Frederic Picard. High-Bandwidth Low-Latency Tracking Using Optical and Inertial Sensors. 5th International Conference on Automation, Robotics and Applications, Wellington, New Zealand, 2011.
[10] Kuanhao Zheng, Dylan F. Glas, Takayuki Kanda, Hiroshi Ishiguro, and Norihiro Hagita. Supervisory Control of Multiple Social Robots for Navigation. International Conference on Human-Robot Interaction (HRI), 2013 8th ACM/IEEE, 17-24, 2013.
[11] Yun Koo Chung and Sun-Myung Hwang. Software testing for intelligent robots. International Conference on Control, Automation and Systems 2007, 2344-2349, IEEE, 2007.
[12] Aitor Arrieta, Irune Agirre, and Ane Alberdi. Testing Architecture with Variability Management in Embedded Distributed Systems. Actas de las IV Jornadas de Computacin Empotrada (JCE), September 2013.
[13] G. Biggs .Applying regression testing to software for robot hardware interaction. Robotics and Automation(ICRA) 2010, IEEE International Conference, 4621-4626,2010.
[14] Jae-Hee Lim, Suk-Hoon Song, Jung-Rye Son, Tae-Yong Kuc, Hong-Seong Park, and HongSeak Kim. An automated test method for robot platform and its components. International Journal of Software Engineering and its Applications, 4(3):9-18, July 2010.
[15] S. Peters, D. Thomas, M. Friedmann, and O. Von Stryk. Multilevel testing of control software for teams of autonomous mobile robots. Simulation, Modelling, and Programming for Autonomous Robots, 183-194, 2008.
[16] S. J. Ahn, and M. Schultes. A new circular coded target for the automation of photogrammetric 3D-surface measurements. Optical 3-D Measurement Techniques IV, 225-234, 1997. Fig. 4 Software structure of the approach components (see Fig. 4). The camera stream component Fig. 5 Screenshot of tracking visualisation using rviz
[17] S. J. Ahn, Wolfgang Rauh, and Matthias Recknagel. Circular Coded Landmark for Optical 3D-Measurement and Robot Vision. International Conference on Intelligent Robots and Systems, 1128-1133, 1999.
[18] G. Kraetzschmar, W. Nowak, N. Hochgeschwender, R. Bischoff, D. Kaczor, F. Hegger. RoboCup@Work Rulebook. http://www.robocupatwork.org/download/rulebook-2013-06-08.pdf, 2013.
[19] Nguyen Hai, Ciocarlie Matei, Hsiao Kaijen, and Kemp Charles. ROS Commander: Flexible Behavior Creation for Home Robots. ICRA , 05/2013, 2013.
[20] Prof. Dr. Erwin Prassler. Cooperations of the Locomotec GmbH. http://www.locomotec.com/en/cooperations, 11.03.2014.