SELF-ORGANIZING MOBILE ROBOTS BASED ON MULTI-AGENT COORDINATION TECHNIQUES IMPLEMENTED WITH AERIAL VISION AND COMMUNICATION GATEWAY BETWEEN WIFI AND RF
Resumen
Abstract
This paper presents the development of mobile robots that have the abilities of search and retrieval of obstacles in a maze-like environment. The algorithm embedded in the robots was designed based upon principles of coordination and self-organization, i.e., a group of autonomous agents coordinate their actions in order to search and retrieve obstacles from the environment through cooperation. To do this, two types of agents were designed, organizers and operators. Organizers try to coordinate the actions of the operators, and these last, try to retrieve all obstacles in the environment. Five four-wheeled robots were built from scratch using Arduino Uno for the operators, and Arduino Nano plus NXP i.MX53 Quick Start Boards for the organizers. Also, an aerial camera (attached to the ceiling) was used to provide visual perception to the robots. The communication was made through a gateway between 8bit channel RF and WiFi, for the operators and organizers respectively.
Keywords: Computer vision, mobile robots, self-organization.
ROBOTS MÓVILES AUTOORGANIZADORES BASADOS EN TÉCNICAS DE COORDINACIÓN MULTIAGENTE IMPLEMENTADAS CON VISIÓN AÉREA Y PUERTA DE ENLACE DE COMUNICACIONES ENTRE WIFI Y RF
Resumen
Este artículo presenta el desarrollo de robots móviles que poseen la capacidad de búsqueda y recuperación de obstáculos en un entorno de laberinto. El algoritmo incorporado en los robots fue diseñado con base en principios de coordinación y autoorganización, es decir, un grupo de agentes autónomos coordinan sus acciones para buscar y recuperar obstáculos del entorno a través de la cooperación. Para ello, se diseñaron dos tipos de agentes, organizadores y operadores. Los organizadores tratan de coordinar las acciones de los operadores, y estos últimos, tratan de recuperar todos los obstáculos en el medio ambiente. Cinco robots de cuatro ruedas fueron construidos desde cero utilizando Arduino Uno para los operadores, y Arduino Nano y NXP i.MX53 Quick Start Boards para los organizadores. Además, se utilizó una cámara aérea (fijada al techo) para proporcionar percepción visual a los robots. La comunicación se realizó a través de una pasarela entre el canal de 8bit RF y WiFi, para los operadores y los organizadores, respectivamente.
Palabras Claves: Autoorganización, robots móviles, visión computacional.
Texto completo:
286-299 PDFReferencias
Chen, G., Yang, Z., He, H., and Goh, K. M., Coordinating multiple agents via reinforcement learning, Autonomous Agents and MultiAgent Systems, vol. 10, no. 3, pp. 273–328, 2005.
Criado, N., Using norms to control open multi-agent systems, AI Commun., pp. 317–318, 2013.
Brambilla, M., Ferrante, E. Birattari, M., Dorigo, M. Swarm Intell Swarm robotics: a review from the swarm engineering perspective. Swarm Intelligence, Springer, 7 (1), pp.1-41, 2013.
Di Marzo, K. M., Serugendo, M., Gleizes, P., and Karageorgos, A., Self-organization in multi-agent systems, Knowl. Eng. Rev., vol. 20, no. 2, pp. 165–189, 2005.
Dimopoulos, Y. and Moraitis, P., Multi-agent coordination and cooperation through classical planning, in 2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, pp. 398–402, 2006.
Evangelidis, G. Arma library: Pattern Tracking for Augmented Reality: https://sites.google.com/site/georgeevangelidis/arma at June 2017.
Gomez-Sanz, J. J., and Pavon, J., Defining coordination in multi-agent systems within an agent oriented software engineering methodology, in Proceedings of the 2006 ACM Symposium on Applied Computing, pp. 424–428, 2006.
Jacyno, M., Bullock, S., Geard, N, Payne, T. R., and Luck, M., Self-organizing agent communities for autonomic resource management, Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems, vol. 21, no. 1, pp. 3–28, 2013.
Mataric, M. J., Designing emergent behaviors: From local interactions to collective intelligence, in Proceedings of the Second International Conference on From Animals to Animats 2: Simulation of Adaptive Behavior: Simulation of Adaptive Behavior, pp. 432–441, 1993.
Muñoz Salinas, R., Aguirre, R., García-Silvente, M., and Gomez, M., A multi-agent system architecture for mobile robot navigation based on fuzzy and visual behaviour, Robotica, vol. 23, no. 6, pp. 689–699, 2005.
Peng, Z., Wen, G., and Rahmani, A., Leader-follower formation control of multiple nonholonomic robots based on backstepping, in Proceedings of the 28th Annual ACM Symposium on Applied Computing, pp. 211–216, 2013.
Turner, J. R., Multiagent systems as a team member, International Journal of Technology, Knowledge & Society, vol. 9, no. 1, pp. 73–90, 2013.
Yoshida, T., Cooperation learning in multi-agent systems with annotation and reward, Int. J. Know. -Based Intell. Eng. Syst., vol. 11, no. 1, pp. 19–34, 2007.
URL de la licencia: https://creativecommons.org/licenses/by/3.0/deed.es
Pistas Educativas está bajo la Licencia Creative Commons Atribución 3.0 No portada. 
TECNOLÓGICO NACIONAL DE MÉXICO / INSTITUTO TECNOLÓGICO DE CELAYA
Antonio García Cubas Pte #600 esq. Av. Tecnológico, Celaya, Gto. México
Tel. 461 61 17575 Ext 5450 y 5146
pistaseducativas@itcelaya.edu.mx