Route Planning for Unmanned Aerial Vehicle (UAV) on the Sea Using Hybrid Differential Evolution and Quantum-Behaved Particle Swarm Optimization

Fu, Yangguang; Ding, Mingyue; Zhou, Chen; Hu, Hanping

doi:10.1109/tsmc.2013.2248146

Cited by 204 publications

(92 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One approach to developing hybrid metaheuristic consists of mixing parts of two established algorithms to form a new and improved solution. This is what the authors of Fu et al (2013) did by adding selection, crossover and mutation operators to a quantum particle swarm optimisation (QPSO). A second approach to hybridisation consists of executing different metaheuristics in parallel and allowing cooperation by migrating solutions between the algorithms.…”

Section: Metaheuristicsmentioning

confidence: 82%

gpuMF: a framework for parallel hybrid metaheuristics on GPU with application to the minimisation of harmonics in multilevel inverters

Roberge

Tarbouchi

Okou

2015

IJPSE

View full text Add to dashboard Cite

Metaheuristics are non-deterministic optimisation algorithms used to solve complex problems for which classic approaches are unsuitable or unable to generate satisfying solutions in a reasonable time. Despite their effectiveness, metaheuristics require considerable computational power. Multiple efforts have been made on the development of parallel metaheuristics on graphics processing units (GPUs). Based on a massively parallel architecture, the GPU offers remarkable computing power and can provide significant speedup. However, there currently exists no software project that unites these research initiatives into a comprehensive and reusable tool. To address this shortcoming, we developed gpuMF, a framework for parallel hybrid metaheuristics on GPUs. GPU metaheuristic framework (gpuMF) exploits the intrinsic parallelism found in metaheuristics and fully utilises the massively parallel architecture of GPUs. To demonstrate the effectiveness of our framework, we use gpuMF to minimise the harmonics of multilevel inverters while providing a speedup of 276x.

show abstract

Section: Metaheuristicsmentioning

confidence: 82%

gpuMF: a framework for parallel hybrid metaheuristics on GPU with application to the minimisation of harmonics in multilevel inverters

Roberge

Tarbouchi

Okou

2015

IJPSE

View full text Add to dashboard Cite

show abstract

“…In DCMA-EA, the mutation, crossover and selection strategy of DE are embedded into the structure of a CMA-ES algorithm. A hybrid of DE and quantum PSO (QPSO), called DEQPSO, is presented for route planning of unmanned aerial vehicle in [30]. In DEQPSO, QPSO and DE are hybridized in sequential order at a population level i.e., at every iteration, the population undergoes evolution first using QPSO and then using DE.…”

Section: Hybridization Instances Of De With Other Easmentioning

confidence: 99%

Hybridizing genetic algorithm with differential evolution for solving the unit commitment scheduling problem

Trivedi¹,

Srinivasan²,

Biswas

et al. 2015

Swarm and Evolutionary Computation

View full text Add to dashboard Cite

“…Scholars tend to optimize the selected algorithm according to their own simulation scenarios but the results of the experiments seem to not be very objective. For example, the results obtained by PSO were much better than GA in [13], whereas the results of PSO were inferior to GA in [18].…”

Section: Introductionmentioning

confidence: 96%

“…The evolutionary algorithm (EA) is used for multi-constraint route planning in a simulation scenario [10][11][12]. The particle swarm optimizer (PSO) is used to solve the path planning problem of UAVs on the sea [13]. Improved ACO [14,15], A* and Theta* [16] algorithms are used for route planning in three-dimensional environments.…”

Section: Introductionmentioning

confidence: 99%

Unmanned Aerial Vehicle Route Planning in the Presence of a Threat Environment Based on a Virtual Globe Platform

Zhang

Liu

et al. 2016

IJGI

View full text Add to dashboard Cite

Route planning is a key technology for an unmanned aerial vehicle (UAV) to fly reliably and safely in the presence of a threat environment. Existing route planning methods are mainly based on the simulation scene, whereas approaches based on the virtual globe platform have rarely been reported. In this paper, a new planning space for the virtual globe and the planner is proposed and a common threat model is constructed for threats including a no-fly zone, hazardous weather, radar coverage area, missile killing zone and dynamic threats. Additionally, an improved ant colony optimization (ACO) algorithm is developed to enhance route planning efficiency and terrain masking ability. Our route planning methods are optimized on the virtual globe platform for practicability. A route planning system and six types of planners were developed and implemented on the virtual globe platform. Finally, our evaluation results demonstrate that our optimum planner has better performance in terms of fuel consumption, terrain masking, and risk avoidance. Experiments also demonstrate that the method and system described in this paper can be used to perform global route planning and mission operations.

show abstract

Route Planning for Unmanned Aerial Vehicle (UAV) on the Sea Using Hybrid Differential Evolution and Quantum-Behaved Particle Swarm Optimization

Cited by 204 publications

References 37 publications

gpuMF: a framework for parallel hybrid metaheuristics on GPU with application to the minimisation of harmonics in multilevel inverters

gpuMF: a framework for parallel hybrid metaheuristics on GPU with application to the minimisation of harmonics in multilevel inverters

Hybridizing genetic algorithm with differential evolution for solving the unit commitment scheduling problem

Unmanned Aerial Vehicle Route Planning in the Presence of a Threat Environment Based on a Virtual Globe Platform

Contact Info

Product

Resources

About