Autonomous multi-robot tracking system for oil spills on sea surface based on hybrid fuzzy distribution and potential field approach

Abstract Oil spill, may happen as a result of the offshore well vessel failures. The precise information about the location and real-time situation of the oil spill is essential to perform an efficient treatment of these environmental catastrophes. A novel approach of multi robot's system which can navigate autonomously and track oil spill on the sea surfaces. This system is able to self-adapt and path plan amidst environmental changes, including the temporospatial variation of the oil concentration. The method consists of two main parts, which are the modelling of the oil spill, the tracking system and autonomous control of the robots. The simulated model depicts the morphological complexities of the spatiotemporal changes in the oil spills. The fuzzy controller is designed to control the robots to control nonlinear and non-crisply distributed water surfaces where oil pollution occurs. Meanwhile, the multi-robot path planning system hybridised with artificial potential field approach to avoid the collision. Several numerical simulations with different scenarios are done to show the robustness of the methods, based on the accuracy and precision of tracking. The evaluation with the simulated ground truth demonstrates that accuracy and precision of the tracking system are more than 70 and 80 percent respectively.

[1]  Farzaneh Abdollahi,et al.  A Decentralized Cooperative Control Scheme With Obstacle Avoidance for a Team of Mobile Robots , 2014, IEEE Transactions on Industrial Electronics.

[2]  Mar Pujol,et al.  Modelling Oil-Spill Detection with Swarm Drones , 2014 .

[3]  Hyo-Sung Ahn,et al.  Formation Control of Mobile Agents Based on Distributed Position Estimation , 2013, IEEE Transactions on Automatic Control.

[4]  E. Mamdani.  A fuzzy rule-based method of controlling dynamic processes , 1981, 1981 20th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes.

[5]  Subhasri Duttagupta,et al.  A survey of sensory data boundary estimation, covering and tracking techniques using collaborating sensors , 2012, Pervasive Mob. Comput..

[6]  Myung Jin Chung,et al.  Robustness of fuzzy logic control for an uncertain dynamic system , 1998, IEEE Trans. Fuzzy Syst..

[7]  Loukas Petrou,et al.  Multi-objective optimization for dynamic task allocation in a multi-robot system , 2013, Eng. Appl. Artif. Intell..

[8]  Robert Bogue,et al.  Robots for monitoring the environment , 2011, Ind. Robot.

[9]  Andreas Krause,et al.  Efficient Planning of Informative Paths for Multiple Robots , 2006, IJCAI.

[10]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[11]  Kimon P. Valavanis,et al.  Swarm Formation Control Utilizing Elliptical Surfaces and Limiting Functions , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[12]  Wesley M. DeBusk.  Unmanned Aerial Vehicle Systems for Disaster Relief: Tornado Alley , 2010 .

[13]  Lino Marques,et al.  Robots for Environmental Monitoring: Significant Advancements and Applications , 2012, IEEE Robotics & Automation Magazine.

[14]  Ramón Rizo,et al.  A swarm behaviour for jellyfish bloom detection , 2017 .

[15]  Toru Namerikawa,et al.  Cooperative target-capturing strategy for multi-vehicle systems with dynamic network topology , 2009, 2009 American Control Conference.

[16]  Hyo-Sung Ahn,et al.  A survey of multi-agent formation control , 2015, Autom..

[17]  Siddhartha S. Srinivasa,et al.  Decentralized estimation and control of graph connectivity in mobile sensor networks , 2008, 2008 American Control Conference.

[18]  Y. Ahmet Sekercioglu,et al.  Distributed formation control of networked mobile robots in environments with obstacles , 2016, Robotica.

[19]  Ryan Luna,et al.  Efficient Multi-Robot Path Planning in Discrete Spaces , 2011 .

[20]  Bernhard Hofmann-Wellenhof,et al.  GNSS - Global Navigation Satellite Systems , 2008 .

[21]  J. Fay.  Physical Processes in the Spread of Oil on a Water Surface , 1971 .

[22]  Eliseo Ferrante,et al.  Swarm robotics: a review from the swarm engineering perspective , 2013, Swarm Intelligence.

[23]  Levent Bayındır,et al.  A review of swarm robotics tasks , 2016, Neurocomputing.

[24]  Mo M. Jamshidi,et al.  Underwater swarm robotics consensus control , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[25]  Wenwu Yu,et al.  An Overview of Recent Progress in the Study of Distributed Multi-Agent Coordination , 2012, IEEE Transactions on Industrial Informatics.

[26]  Gaurav S. Sukhatme,et al.  Data‐driven learning and planning for environmental sampling , 2017, J. Field Robotics.

[27]  Rubiyah Yusof,et al.  Oil Spill trajectory tracking using swarm intelligence and hybrid fuzzy system , 2014, 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[28]  E.M. Atkins,et al.  A survey of consensus problems in multi-agent coordination , 2005, Proceedings of the 2005, American Control Conference, 2005..

[29]  Roman Fedorenko,et al.  Research of Autonomous Surface Vehicle Control System , 2016, ICCMA '16.

[30]  W. J. Guo,et al.  A numerical oil spill model based on a hybrid method. , 2009, Marine pollution bulletin.

[31]  Yu Wang,et al.  Aquatic environment monitoring using robotic sensor networks , 2015 .

[32]  Reza Olfati-Saber,et al.  Consensus and Cooperation in Networked Multi-Agent Systems , 2007, Proceedings of the IEEE.

[33]  M. Reed,et al.  Oil Spill Modeling towards the Close of the 20th Century: Overview of the State of the Art , 1999 .

[34]  A. Fick.  On liquid diffusion , 1995 .