Versatile and Massive Experimentation of Robot Swarms in Industrial Scenarios

This paper aims to present an automated experimentation platform designed to work with multiple mobile robots into industrial scenarios using Robot Operating System (ROS). Robot swarm is a system with complexity proportional of group size, expensive and with arduous setup. Virtual environments can be used to expedite the testing, but also are very difficult due to a hard-work to configure each robot. The proposed platform is a tool set to easily configure the experimentation environment, aiming the swarm tasks, with most popular perception systems, absolute or relative localization reference, and position controllers. The user specifies in tool only the amount of robots required, sensor and function, without having to configure each robot individually for the simulation. This paper presents examples to multi-robot setup in industrial scenarios, through a simple parameterization script. The memory consumption is demystified to given to allow the estimation of computational resources necessary to perform the practical experimentation.

[1]  Tony J. Dodd,et al.  HyMod: A 3-DOF Hybrid Mobile and Self-Reconfigurable Modular Robot and its Extensions , 2018, DARS.

[2]  Prabhu Ramanathan,et al.  Smart controller for conical tank system using reinforcement learning algorithm , 2018 .

[3]  Ivana Budinská,et al.  A Self-adapting Method for 3D Environment Exploration Inspired by Swarm Behaviour , 2017, RAAD.

[4]  Michael R. M. Jenkin,et al.  A taxonomy for swarm robots , 1993, Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '93).

[5]  Elio Tuci,et al.  Cooperative object transport with a swarm of e-puck robots: robustness and scalability of evolved collective strategies , 2017, Swarm Intelligence.

[6]  Aditya Deshpande,et al.  Robot Swarm Based On Ant Foraging Hypothesis With Adaptive Levy Flights , 2017 .

[7]  Gerardo Beni,et al.  From Swarm Intelligence to Swarm Robotics , 2004, Swarm Robotics.

[8]  Amanda J. C. Sharkey,et al.  Robots, insects and swarm intelligence , 2006, Artificial Intelligence Review.

[9]  Huimin Lu,et al.  Task Allocation Without Communication Based on Incomplete Information Game Theory for Multi-robot Systems , 2019, J. Intell. Robotic Syst..

[10]  Spring Berman,et al.  A Probabilistic Approach to Automated Construction of Topological Maps Using a Stochastic Robotic Swarm , 2017, IEEE Robotics and Automation Letters.

[11]  L. E. Parker,et al.  Current research in multirobot systems , 2003, Artificial Life and Robotics.

[12]  S. G. Ponnambalam,et al.  Swarm Robotics: An Extensive Research Review , 2010 .

[13]  Noel E. Sharkey,et al.  The Application of Swarm Intelligence to Collective Robots , 2006 .

[14]  Richard Vaughan,et al.  Massively multi-robot simulation in stage , 2008, Swarm Intelligence.