@inproceedings{Ramirez-Atencia2016a,
title = {A Weighted Penalty Fitness for a Hybrid MOGA-CSP to solve Mission Planning Problems},
author = {Cristian Ramirez-Atencia and Gema Bello-Orgaz and Maria D R-Moreno and David Camacho},
url = {http://aida.ii.uam.es/wp-content/uploads/2017/03/A-Weighted-Penalty-Fitness-for-a-Hybrid-MOGA-CSP-to-solve-Mission-Planning-Problems.pdf},
year = {2016},
date = {2016-01-01},
booktitle = {XI Congreso Español de Metaheurísticas, Algoritmos Evolutivos y Bioinspirados (MAEB 2016)},
pages = {305--314},
abstract = {Unmanned Aerial Vehicles (UAVs) are currently booming due to their high number of potential applications. In Mission Planning problems, several tasks must be performed by a team of UAVs, under the supervision of one or more Ground Control Stations (GCSs). In our approach, we have modelled the problem as a Constraint Satisfaction Problem (CSP), and solved it using a Multi-Objective Genetic Algorithm (MOGA). The algorithm has been designed to minimize several variables of the mission such as the fuel consumption or the makespan. In addition, the fitness function takes a new consideration when solutions are not valid. It uses the number of constraints fulfilled for each solution as a weighted penalty function. In this way, the number of constraints fulfilled is maximized in the elitism phase of the MOGA. Results show that the approach outperforms the convergence with respect to previous results.},
keywords = {Constraint Satisfaction Problems, Mission Planning, Muli-UAV, Multi-Objective Genetic Algorithm, Multi-objective Optimization, NSGA2, Unmanned Aerial Vehicles},
pubstate = {published},
tppubtype = {inproceedings}
}
Unmanned Aerial Vehicles (UAVs) are currently booming due to their high number of potential applications. In Mission Planning problems, several tasks must be performed by a team of UAVs, under the supervision of one or more Ground Control Stations (GCSs). In our approach, we have modelled the problem as a Constraint Satisfaction Problem (CSP), and solved it using a Multi-Objective Genetic Algorithm (MOGA). The algorithm has been designed to minimize several variables of the mission such as the fuel consumption or the makespan. In addition, the fitness function takes a new consideration when solutions are not valid. It uses the number of constraints fulfilled for each solution as a weighted penalty function. In this way, the number of constraints fulfilled is maximized in the elitism phase of the MOGA. Results show that the approach outperforms the convergence with respect to previous results.
@inproceedings{Ramirez-Atencia2016b,
title = {MOGAMR: A Multi-Objective Genetic Algorithm for Real-Time Mission Replanning},
author = {Cristian Ramirez-Atencia and Gema Bello-Orgaz and Maria D R-Moreno and David Camacho},
doi = {10.1109/SSCI.2016.7850235},
isbn = {978-1-5090-4240-1, 978-1-5090-4241-8},
year = {2016},
date = {2016-01-01},
booktitle = {2016 IEEE Symposium Series on Computational Intelligence (SSCI)},
abstract = {From the last few years the interest and repercussion on Unmanned Aerial Vehicle (UAV) technologies have been extended from pure military applications to industrial and societal applications. One of the basic tasks to any UAV problems is related to the Mission Planning. This problem is particularly complex when a set of UAVs is considered. In the field of MultiUAV Mission Planning, some approaches have been carried out in the last years. However, there are few works related to realtime Mission Replanning, which is the focus of this work. In Mission Replanning, some changes in the mission, such as the arrival of new tasks, require to update the preplanned solution as fast as possible. In this paper a Multi-Objective Genetic Algorithm for Mission Replanning (MOGAMR) is proposed to handle this problem. This approach uses a set of previous plans (or solutions), generated using an offlline planning process, in order to initialize the population of the algorithm, then acts as a complete regeneration method. In order to simulate a real-time system we have fixed a time limit of 2 minutes. This has been considered as an appropriate time for a human operator to take a decision. Using this time restriction, a set of experiments adding from 1 to 5 new tasks in the Replanning Problems has been carried out. The experiments show that the algorithm works well with this few number of new tasks during the replanning process generating a set of feasible solutions under the time restriction considered.},
keywords = {Constraint Satisfaction Problems, Metaheuristics, Mission Planning, Multi-objective Optimization, NSGA2, Replanning, Unmanned Aircraft Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
From the last few years the interest and repercussion on Unmanned Aerial Vehicle (UAV) technologies have been extended from pure military applications to industrial and societal applications. One of the basic tasks to any UAV problems is related to the Mission Planning. This problem is particularly complex when a set of UAVs is considered. In the field of MultiUAV Mission Planning, some approaches have been carried out in the last years. However, there are few works related to realtime Mission Replanning, which is the focus of this work. In Mission Replanning, some changes in the mission, such as the arrival of new tasks, require to update the preplanned solution as fast as possible. In this paper a Multi-Objective Genetic Algorithm for Mission Replanning (MOGAMR) is proposed to handle this problem. This approach uses a set of previous plans (or solutions), generated using an offlline planning process, in order to initialize the population of the algorithm, then acts as a complete regeneration method. In order to simulate a real-time system we have fixed a time limit of 2 minutes. This has been considered as an appropriate time for a human operator to take a decision. Using this time restriction, a set of experiments adding from 1 to 5 new tasks in the Replanning Problems has been carried out. The experiments show that the algorithm works well with this few number of new tasks during the replanning process generating a set of feasible solutions under the time restriction considered.
@article{Ramirez-Atencia2016c,
title = {Solving complex multi-UAV mission planning problems using multi-objective genetic algorithms},
author = {Cristian Ramirez-Atencia and Gema Bello-Orgaz and Maria D R-Moreno and David Camacho},
url = {http://aida.ii.uam.es/wp-content/uploads/2017/03/RamirezEtAl.pdf},
doi = {10.1007/s00500-016-2376-7},
issn = {1432-7643; 1433-7479},
year = {2016},
date = {2016-01-01},
journal = {Soft Computing},
volume = {In Press},
pages = {1--18},
publisher = {Springer Verlag},
abstract = {Due to recent booming of unmanned air vehicles (UAVs) technologies, these are being used in many fields involving complex tasks. Some of them involve a high risk to the vehicle driver, such as fire monitoring and rescue tasks, which make UAVs excellent for avoiding human risks. Mission planning for UAVs is the process of planning the locations and actions (loading/dropping a load, taking videos/pictures, acquiring information) for the vehicles, typically over a time period. These vehicles are controlled from ground control stations (GCSs) where human operators use rudimentary systems. This paper presents a new multi-objective genetic algorithm for solving complex mission planning problems involving a team of UAVs and a set of GCSs. A hybrid fitness function has been designed using a constraint satisfaction problem to check whether solutions are valid and Pareto-based measures to look for optimal solutions. The algorithm has been tested on several datasets, optimizing different variables of the mission, such as the makespan, the fuel consumption, and distance. Experimental results show that the new algorithm is able to obtain good solutions; however, as the problem becomes more complex, the optimal solutions also become harder to find.},
keywords = {Constraint Satisfaction Problems, Genetic Algorithms, Mission Planning, Multi-objective Optimization, NSGA2, Unmanned air vehicles},
pubstate = {published},
tppubtype = {article}
}
Due to recent booming of unmanned air vehicles (UAVs) technologies, these are being used in many fields involving complex tasks. Some of them involve a high risk to the vehicle driver, such as fire monitoring and rescue tasks, which make UAVs excellent for avoiding human risks. Mission planning for UAVs is the process of planning the locations and actions (loading/dropping a load, taking videos/pictures, acquiring information) for the vehicles, typically over a time period. These vehicles are controlled from ground control stations (GCSs) where human operators use rudimentary systems. This paper presents a new multi-objective genetic algorithm for solving complex mission planning problems involving a team of UAVs and a set of GCSs. A hybrid fitness function has been designed using a constraint satisfaction problem to check whether solutions are valid and Pareto-based measures to look for optimal solutions. The algorithm has been tested on several datasets, optimizing different variables of the mission, such as the makespan, the fuel consumption, and distance. Experimental results show that the new algorithm is able to obtain good solutions; however, as the problem becomes more complex, the optimal solutions also become harder to find.