A Multi-agent Efficient Control System for a Production Mobile Robot

This paper presents the results of the experiments of a multi-agent control architecture for the efficient control of a multi-wheeled mobile platform. Multi-agent system incorporates multiple Q-learning agents, which permits them to effectively control every wheel relative to other wheels. The learning process was divided into two steps: module positioning – where the agents learn to minimize the error of orientation and cooperative movement – where the agents learn to adjust the desired velocity in order to conform to the desired position in formation. From this decomposition every module agent will have two control policies for forward and angular velocity, respectively. The experiments were carried out with a real robot. Our results indicate the successful application of the proposed control architecture for the real production robot.

[1]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[2]  Anton Kabysh,et al.  INFLUENCE LEARNING FOR MULTI-AGENT SYSTEM BASED ON REINFORCEMENT LEARNING , 2014 .

[3]  Y. Charlie Hu,et al.  Energy-efficient motion planning for mobile robots , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[4]  Ralf Stetter,et al.  Development, Realization and Control of a Mobile Robot , 2010, Eurobot Conference.

[5]  Ralf Stetter,et al.  A multi-agent reinforcement learning approach for the efficient control of mobile robot , 2013, 2013 IEEE 7th International Conference on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS).

[6]  Anton Kabysh,et al.  GENERAL MODEL FOR ORGANIZING INTERACTIONS IN MULTI-AGENT SYSTEMS , 2014 .

[7]  Y. Charlie Hu,et al.  Energy-efficient mobile robot exploration , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[8]  Achim Gottscheber,et al.  Research and Education in Robotics - EUROBOT 2010 - International Conference, Rapperswil-Jona, Switzerland, May 27-30, 2010, Revised Selected Papers , 2011, Eurobot Conference.

[9]  A. Garulli,et al.  Collective circular motion of multi-vehicle systems with sensory limitations , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[10]  Andrea Garulli,et al.  Collective circular motion of multi-vehicle systems , 2008, Autom..

[11]  Anibal T. de Almeida,et al.  Energy efficiency improvements in electric moters and drives , 1997 .

[12]  Andrea Garulli,et al.  Experimental validation of collective circular motion for nonholonomic multi-vehicle systems , 2010, Robotics Auton. Syst..

[13]  Wei Ren,et al.  Distributed coordination architecture for multi-robot formation control , 2008, Robotics Auton. Syst..

[14]  Emadi Ali,et al.  Energy-efficient electric motors , 2005 .