A centralized multi-robot task allocation for industrial plant inspection by using a* and genetic algorithms

Authors:
Chun Liu;Andreas Kroll
Affiliations:
Measurement and Control Department, Mechanical Engineering, University of Kassel, Kassel, Germany;Measurement and Control Department, Mechanical Engineering, University of Kassel, Kassel, Germany
Venue:
ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part II
Year:
2012

Citing 5
Cited 1

AllelesLociand the Traveling Salesman Problem

Proceedings of the 1st International Conference on Genetic Algorithms
Cooperative Observation of Multiple Moving Targets: an algorithm and its formalization

International Journal of Robotics Research
A Multi-Objective Pareto-Optimal Solution to the Box-Pushing Problem by Mobile Robots

EMS '08 Proceedings of the 2008 Second UKSIM European Symposium on Computer Modeling and Simulation
On autonomous detection of pressured air and gas leaks using passive IR-thermography for mobile robot application

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Mobile robots with active IR-optical sensing for remote gas detection and source localization

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation

On designing genetic algorithms for solving small- and medium-scale traveling salesman problems

SIDE'12 Proceedings of the 2012 international conference on Swarm and Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multi-robot systems are widely employed in various applications including industrial plant inspection. However, current research work mainly focuses on the methods of object detection, and rarely addresses task allocation and path-planning of multi-robot systems for industrial plant inspection. Therefore, a centralized method for multi-robot task allocation (MRTA) and path-planning to solve inspection problems is proposed in this paper. For the first time, the problem statement of the task allocation for inspection problems is formulated. This paper introduces the implementation of the algorithm based on A* and a novel Genetic Algorithm including the environment representation. The task allocation and path-planning are performed based on the assumption that the robots work in known environments. The proposed algorithm is tested in a simulation study derived from a large industrial site.