Inverse ACO Applied for Exploration and Surveillance in Unknown Environments

This paper focuses on a distributed strategy proposed to coordinate a multiple robot system applied to exploration and surveillance tasks. The strategy is based on the artificial ant system theory. According to it robots are guided to unexplored or not recently explored regions. The main features of the strategy are, among others: low computation cost; and independence of the number of robots. Results from preceding investigations confirm the strategy is able to emerge a cooperative robot behavior, that is, the exploration and surveillance tasks are synergistically executed. This paper concerns specifically the robustness of the coordination strategy regarding to the environment structure. Two metrics are adopted for evaluation: needed time to conclude the exploration task, and time between two consecutive senses on a same region. Simulation results show that the coordination strategy is able to establish effective trajectories, that is, robots are guided to explore the environment and to sense repeatedly and completely the environment. Keywords-multiple robot systems; surveillance task; ant colony systems; environment exploration; swarm systems; mobile robots

[1]  Futoshi Kobayashi,et al.  Re-formation of mobile robots using genetic algorithm and reinforcement learning , 2003, SICE 2003 Annual Conference (IEEE Cat. No.03TH8734).

[2]  Steven Dubowsky,et al.  Tactile Robotic Mapping of Unknown Surfaces, With Application to Oil Wells , 2011, IEEE Transactions on Instrumentation and Measurement.

[3]  Marco Dorigo,et al.  Optimization, Learning and Natural Algorithms , 1992 .

[4]  Antonio Franchi,et al.  On optimal cooperative patrolling , 2010, 49th IEEE Conference on Decision and Control (CDC).

[5]  Wu Qing-hong.  Review of Ant Colony Optimization , 2011 .

[6]  Mahmoud Tarokh,et al.  Fuzzy logic decision making for multi-robot security systems , 2010, Artificial Intelligence Review.

[7]  Luca Maria Gambardella,et al.  Ant Algorithms for Discrete Optimization , 1999, Artificial Life.

[8]  Brian Yamauchi,et al.  A frontier-based approach for autonomous exploration , 1997, Proceedings 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA'97. 'Towards New Computational Principles for Robotics and Automation'.

[9]  Qiang Jiang.  An improved algorithm for coordination control of multi-agent system based on r-limited voronoi partitions , 2006, 2006 IEEE International Conference on Automation Science and Engineering.

[10]  Renato Zaccaria,et al.  Surveillance robotics: analyzing scenes by colors analysis and clustering , 2003, Proceedings 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation. Computational Intelligence in Robotics and Automation for the New Millennium (Cat. No.03EX694).

[11]  Roseli A. Francelin Romero,et al.  A distributed, bio-inspired coordination strategy for multiple agent systems applied to surveillance tasks in unknown environments , 2011, The 2011 International Joint Conference on Neural Networks.

[12]  Peng Yang,et al.  Distributed estimation and control of swarm formation statistics , 2006, 2006 American Control Conference.