Simulation of Lidar-Based Robot Detection Task using ROS and Gazebo

Year 2019, Special Issue 2019, 513 - 529, 31.10.2019

Zahir Yılmaz Levent Bayındır

https://doi.org/10.31590/ejosat.642840

Cited By: 5

Abstract

In the last few decades, the robotics world has seen great progress at all levels, from personal assistant robots to multi-robotic and intelligent swarm systems. Simulation platforms play a critical role in this improvement due to efficiency, flexibility, and fault tolerance they provide during the cycles of developing and testing new strategies and algorithms. In this paper, we model a new mobile robot equipped with a 2D Lidar using Robot Operating System (ROS) and use this robot model to develop a robot detection method in Gazebo simulation environment. Detecting surrounding objects and distinguishing robots from these objects (kin detection) are essential in multi-robot and swarm robotic applications. In this paper, we use Lidar to handle this task by applying the following steps: (1) acquisition of laser data and pre-processing, (2) segmentation of data using the point-distance-based segmentation method, (3) classification of segments by applying two levels of filtering: filtering by segment diameter which aims to eliminate segments that don’t fit a certain size (Lidar size) using features for each segment, filtering by segment shape to check remaining segments to test if they fit the Lidar's shape (which is a circle with known radius) or not by using the circle fitting method and (4) identify the position of kin relative to the observer robot. Two different scenarios are discussed in the experiments section. In the first scenario, many cylindrical objects with radius different from the robot’s Lidar were used in addition to a robot, and thus objects are distinguished from the robot in the first level of filtering without using the second one which may be a complex operation. In the second scenario, various objects with a similar radius were used, and due to the similarity in the radius between the Lidar and the objects, it was necessary to apply all the method’s steps to detect the kin robots. It was noticed from experiments that the accuracy of the results depends on two main factors: the distance between the observer robot and other objects or robots and the amount of noise in the Lidar measurements.

Keywords

Robot detection, Kin detection, Lidar, ROS, Gazebo, Robotics

ROS ve Gazebo Kullanarak Lidar Tabanlı Robot Tespit Görevinin Simülasyonu

Abstract

Son birkaç on yılda, robotik dünyası, kişisel asistan robotlardan çoklu robotik ve akıllı sürü sistemlerine kadar her seviyede büyük ilerleme gördü. Simülasyon platformları, yeni stratejiler ve algoritmalar geliştirme ve test etme döngüleri sırasında sağladıkları verimlilik, esneklik ve hata toleransı nedeniyle bu gelişmede kritik bir rol oynamaktadır. Bu makalede, Robot İşletim Sistemi'ni (ROS) kullanarak 2D lazerli telemetre ile donatılmış yeni bir mobil robot modelliyoruz ve bu robot modelini Gazebo simülasyon ortamında bir robot algılama yöntemi geliştirmek için kullanıyoruz. Çevredeki nesneleri algılamak ve robotları bu nesnelerden ayırt etmek (kin algılama), çoklu robot ve sürü robotik uygulamalarda çok önemlidir. Bu makalede, robot algılama görevini yerine getirmek için Lidar kullanılarak aşağıdaki adımları uygulamaktadır: (1) lazer verilerinin elde edilmesi ve ön işleme, (2) nokta-mesafeye dayalı segmentasyon yöntemini kullanarak verinin segmentlere ayrılması, (3) iki filtreleme seviyesi uygulayarak segmentlerin sınıflandırılması: her bölüm için özellikler kullanarak belirli bir boyuta (Lidar boyutu) uymayan bölümleri ortadan kaldırmayı amaçlayan bölüm çapına göre filtreleme yapmak, kalan parçaları Lidar'ın şekline uyup uymadığını (bilinen yarıçapı olan bir daire) test etmek için segment şekline göre filtreleme ve (4) gözlemci robota göre komşu robotun pozisyonunu tanımlar. Deneyler bölümünde iki farklı senaryo ele alınmıştır. İlk senaryoda, bir robotun yanı sıra, robotun Lidar'ından farklı yarıçapa sahip birçok silindirik nesne kullanılmış ve bu nedenle nesneler, ikinci bir karmaşık işlem olabilecek ikinci filtreyi kullanmadan, ilk filtreleme düzeyinde robottan ayrılmıştır. İkinci senaryoda, benzer yarıçapa sahip çeşitli nesneler kullanıldı ve Lidar ile nesneler arasındaki yarıçaptaki benzerlik nedeniyle, kin robotları tespit etmek için tüm yöntemin adımlarını uygulamak gerekliydi. Deneylerden, sonuçların doğruluğunun iki ana faktöre bağlı olduğu gözlenmiştir: gözlemci robotu ile diğer nesneler veya robotlar arasındaki mesafe ve Lidar ölçümlerindeki gürültü miktarı.

Keywords

Robot tespiti, Soydaş tespiti, Lidar, ROS, Gazebo, Robotik

References

• Şahin, E. (2004, July). Swarm robotics: From sources of inspiration to domains of application. In International workshop on swarm robotics (pp. 10-20). Springer, Berlin, Heidelberg.
• Arvin, F., Samsudin, K., & Ramli, A. R. (2009). Development of a miniature robot for swarm robotic application. International Journal of Computer and Electrical Engineering, 1(4), 436-442.
• McLurkin, J., McMullen, A., Robbins, N., Habibi, G., Becker, A., Chou, A., ... & Kim, S. (2014, September). A robot system design for low-cost multi-robot manipulation. In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 912-918). IEEE.
• Gupta, M., & Singh, K. (2010, November). AutoBot: a low-cost platform for swarm research applications. In 2010 3rd International Conference on Emerging Trends in Engineering and Technology (pp. 33-36). IEEE.
• Arvin, F., Murray, J., Zhang, C., & Yue, S. (2014). Colias: An autonomous micro robot for swarm robotic applications. International Journal of Advanced Robotic Systems, 11(7), 113.
• Kernbach, S., Thenius, R., Kernbach, O., & Schmickl, T. (2009). Re-embodiment of honeybee aggregation behavior in an artificial micro-robotic system. Adaptive Behavior, 17(3), 237-259.
• Turgut, A. E., Çelikkanat, H., Gökçe, F., & Şahin, E. (2008). Self-organized flocking in mobile robot swarms. Swarm Intelligence, 2(2-4), 97-120.
• Mondada, F., Bonani, M., Raemy, X., Pugh, J., Cianci, C., Klaptocz, A., ... & Martinoli, A. (2009). The e-puck, a robot designed for education in engineering. In Proceedings of the 9th conference on autonomous robot systems and competitions (Vol. 1, No. CONF, pp. 59-65). IPCB: Instituto Politécnico de Castelo Branco.
• Hilder, J., Naylor, R., Rizihs, A., Franks, D., & Timmis, J. (2014, September). The pi swarm: A low-cost platform for swarm robotics research and education. In Conference Towards Autonomous Robotic Systems (pp. 151-162). Springer, Cham.
• Castillo-Pizarro, P., Arredondo, T. V., & Torres-Torriti, M. (2010, October). Introductory survey to open-source mobile robot simulation software. In 2010 Latin American Robotics Symposium and Intelligent Robotics Meeting (pp. 150-155). IEEE.
• Quigley, M., Conley, K., Gerkey, B., Faust, J., Foote, T., Leibs, J., ... & Ng, A. Y. (2009, May). ROS: an open-source Robot Operating System. In ICRA workshop on open source software (Vol. 3, No. 3.2, p. 5).
• W. Garage, ROS: Robot Operating System, 2011[J]. URL: http://www. ros.org, 2011
• Koenig, N., & Howard, A. (2004, September). Design and use paradigms for gazebo, an open-source multi-robot simulator. In 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)(IEEE Cat. No. 04CH37566) (Vol. 3, pp. 2149-2154). IEEE.
• Quigley, M., Gerkey, B., & Smart, W. D. (2015). Programming Robots with ROS: a practical introduction to the Robot Operating System. O'Reilly Media, Inc..
• Hershberger, D., Gossow, D., & Faust, J. RViz, 3D visualization tool for ROS. URL: http://wiki. ros. org/rviz [cited 06-08-2016].
• Kunze, L., Roehm, T., & Beetz, M. (2011, May). Towards semantic robot description languages. In 2011 IEEE International Conference on Robotics and Automation (pp. 5589-5595). IEEE.
• Lee, K. H., Woo, H., & Suk, T. (2001). Data reduction methods for reverse engineering. The International Journal of Advanced Manufacturing Technology, 17(10), 735-743.
• Miyahara, K., & Okada, Y. (2009, March). COLLADA-based File Format Supporting Various Attributes of Realistic Objects for VR Applications. In 2009 International Conference on Complex, Intelligent and Software Intensive Systems (pp. 971-976). IEEE.
• http://gazebosim.org/tutorials?tut=ros_gzplugins
• Pugh, J., & Martinoli, A. Local Range and Bearing Sensing Using Infrared Transceivers in Mobile Robotics.
• Rivard, F., Bisson, J., Michaud, F., & Létourneau, D. (2008, May). Ultrasonic relative positioning for multi-robot systems. In 2008 IEEE International Conference on Robotics and Automation (pp. 323-328). IEEE.
• Bolla, K., Kovacs, T., & Fazekas, G. (2010, May). Compact image processing-based kin recognition, distance measurement and identification method in a robot swarm. In 2010 International Joint Conference on Computational Cybernetics and Technical Informatics (pp. 419-424). IEEE.
• Wa̧sik, A., Ventura, R., Pereira, J. N., Lima, P. U., & Martinoli, A. (2016). Lidar-based relative position estimation and tracking for multi-robot systems. In Robot 2015: Second Iberian Robotics Conference (pp. 3-16). Springer, Cham.
• Teixidó, M., Pallejà, T., Font, D., Tresanchez, M., Moreno, J., & Palacín, J. (2012). Two-dimensional radial laser scanning for circular marker detection and external mobile robot tracking. Sensors, 12(12), 16482-16497.
• Zhou, X., Wang, Y., Zhu, Q., & Miao, Z. (2016, November). Circular object detection in polar coordinates for 2D LIDAR data. In Chinese Conference on Pattern Recognition (pp. 65-78). Springer, Singapore.
• Laser range scanner RPLIDAR A1 Datasheet is available online at: https://download.slamtec.com/api/download/rplidar-a1m8-datasheet/2.1?lang=en
• Trianni, V., Groß, R., Labella, T. H., Şahin, E., & Dorigo, M. (2003, September). Evolving aggregation behaviors in a swarm of robots. In European Conference on Artificial Life (pp. 865-874). Springer, Berlin, Heidelberg.
• Sahin, E., Labella, T. H., Trianni, V., Deneubourg, J. L., Rasse, P., Floreano, D., ... & Dorigo, M. (2002, October). SWARM-BOT: Pattern formation in a swarm of self-assembling mobile robots. In IEEE International Conference on Systems, Man and Cybernetics (Vol. 4, pp. 6-pp). IEEE.
• Turgut, A. E., Çelikkanat, H., Gökçe, F., & Şahin, E. (2008). Self-organized flocking in mobile robot swarms. Swarm Intelligence, 2(2-4), 97-120.
• Moré, J. J. (1978). The Levenberg-Marquardt algorithm: implementation and theory. In Numerical analysis (pp. 105-116). Springer, Berlin, Heidelberg.
• Gazebo: The Player Project, Free Software Tools for Robot and Sensor Applications. http://playerstage.sourceforge.net/
• Rohmer, E., Singh, S. P., & Freese, M. (2013, November). V-REP: A versatile and scalable robot simulation framework. In 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 1321-1326). IEEE.
• Michel, O. (2004). Cyberbotics Ltd. Webots™: professional mobile robot simulation. International Journal of Advanced Robotic Systems, 1(1), 5.
• AnyKode Marilou - Modeling and simulation environment for Robotic. Anykode.com. Retrieved October 3, 2019, from http://www.anykode.com
• 4D-virtualiz Simulator. 4d-virtualiz.com. Retrieved October 3, 2019, from https://www.4d-virtualiz.com
• Gazebo and ROS Integration. Retrieved October 3, 2019, from http://gazebosim.org/tutorials/?tut=ros_overview
• Premebida, C., & Nunes, U. (2005). Segmentation and geometric primitives extraction from 2d laser range data for mobile robot applications. Robotica, 2005, 17-25.
• Rusu, C., Tico, M., Kuosmanen, P., & Delp, E. J. (2003). Classical geometrical approach to circle fitting--review and new developments. Journal of Electronic Imaging, 12(1), 179-194.