An Efficient Sampling-Based Algorithms Using Active Learning and Manifold Learning for Multiple Unmanned Aerial Vehicle Task Allocation under Uncertainty
This paper presents a sampling-based approximation for multiple unmanned aerial vehicle (UAV) task allocation under uncertainty. Our goal is to reduce the amount of calculations and improve the accuracy of the algorithm. For this purpose, Gaussian process regression models are constructed from an un...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/8/2645 |
| id |
doaj-60408005d22948c98163a04504f58498 |
|---|---|
| record_format |
Article |
| spelling |
doaj-60408005d22948c98163a04504f584982020-11-25T00:01:20ZengMDPI AGSensors1424-82202018-08-01188264510.3390/s18082645s18082645An Efficient Sampling-Based Algorithms Using Active Learning and Manifold Learning for Multiple Unmanned Aerial Vehicle Task Allocation under UncertaintyXiaowei Fu0Hui Wang1Bin Li2Xiaoguang Gao3School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710129, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, Xi’an 710129, ChinaShaanxi Key Laboratory of Integrated and Intelligent Navigation, Xi’an 710068, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, Xi’an 710129, ChinaThis paper presents a sampling-based approximation for multiple unmanned aerial vehicle (UAV) task allocation under uncertainty. Our goal is to reduce the amount of calculations and improve the accuracy of the algorithm. For this purpose, Gaussian process regression models are constructed from an uncertainty parameter and task reward sample set, and this training set is iteratively refined by active learning and manifold learning. Firstly, a manifold learning method is used to screen samples, and a sparse graph is constructed to represent the distribution of all samples through a small number of samples. Then, multi-points sampling is introduced into the active learning method to obtain the training set from the sparse graph quickly and efficiently. This proposed hybrid sampling strategy could select a limited number of representative samples to construct the training set. Simulation analyses demonstrate that our sampling-based algorithm can effectively get a high-precision evaluation model of the impact of uncertain parameters on task reward.http://www.mdpi.com/1424-8220/18/8/2645uncertaintymulti-UAVstask allocationactive learningmanifold learning |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Xiaowei Fu Hui Wang Bin Li Xiaoguang Gao |
| spellingShingle |
Xiaowei Fu Hui Wang Bin Li Xiaoguang Gao An Efficient Sampling-Based Algorithms Using Active Learning and Manifold Learning for Multiple Unmanned Aerial Vehicle Task Allocation under Uncertainty Sensors uncertainty multi-UAVs task allocation active learning manifold learning |
| author_facet |
Xiaowei Fu Hui Wang Bin Li Xiaoguang Gao |
| author_sort |
Xiaowei Fu |
| title |
An Efficient Sampling-Based Algorithms Using Active Learning and Manifold Learning for Multiple Unmanned Aerial Vehicle Task Allocation under Uncertainty |
| title_short |
An Efficient Sampling-Based Algorithms Using Active Learning and Manifold Learning for Multiple Unmanned Aerial Vehicle Task Allocation under Uncertainty |
| title_full |
An Efficient Sampling-Based Algorithms Using Active Learning and Manifold Learning for Multiple Unmanned Aerial Vehicle Task Allocation under Uncertainty |
| title_fullStr |
An Efficient Sampling-Based Algorithms Using Active Learning and Manifold Learning for Multiple Unmanned Aerial Vehicle Task Allocation under Uncertainty |
| title_full_unstemmed |
An Efficient Sampling-Based Algorithms Using Active Learning and Manifold Learning for Multiple Unmanned Aerial Vehicle Task Allocation under Uncertainty |
| title_sort |
efficient sampling-based algorithms using active learning and manifold learning for multiple unmanned aerial vehicle task allocation under uncertainty |
| publisher |
MDPI AG |
| series |
Sensors |
| issn |
1424-8220 |
| publishDate |
2018-08-01 |
| description |
This paper presents a sampling-based approximation for multiple unmanned aerial vehicle (UAV) task allocation under uncertainty. Our goal is to reduce the amount of calculations and improve the accuracy of the algorithm. For this purpose, Gaussian process regression models are constructed from an uncertainty parameter and task reward sample set, and this training set is iteratively refined by active learning and manifold learning. Firstly, a manifold learning method is used to screen samples, and a sparse graph is constructed to represent the distribution of all samples through a small number of samples. Then, multi-points sampling is introduced into the active learning method to obtain the training set from the sparse graph quickly and efficiently. This proposed hybrid sampling strategy could select a limited number of representative samples to construct the training set. Simulation analyses demonstrate that our sampling-based algorithm can effectively get a high-precision evaluation model of the impact of uncertain parameters on task reward. |
| topic |
uncertainty multi-UAVs task allocation active learning manifold learning |
| url |
http://www.mdpi.com/1424-8220/18/8/2645 |
| work_keys_str_mv |
AT xiaoweifu anefficientsamplingbasedalgorithmsusingactivelearningandmanifoldlearningformultipleunmannedaerialvehicletaskallocationunderuncertainty AT huiwang anefficientsamplingbasedalgorithmsusingactivelearningandmanifoldlearningformultipleunmannedaerialvehicletaskallocationunderuncertainty AT binli anefficientsamplingbasedalgorithmsusingactivelearningandmanifoldlearningformultipleunmannedaerialvehicletaskallocationunderuncertainty AT xiaoguanggao anefficientsamplingbasedalgorithmsusingactivelearningandmanifoldlearningformultipleunmannedaerialvehicletaskallocationunderuncertainty AT xiaoweifu efficientsamplingbasedalgorithmsusingactivelearningandmanifoldlearningformultipleunmannedaerialvehicletaskallocationunderuncertainty AT huiwang efficientsamplingbasedalgorithmsusingactivelearningandmanifoldlearningformultipleunmannedaerialvehicletaskallocationunderuncertainty AT binli efficientsamplingbasedalgorithmsusingactivelearningandmanifoldlearningformultipleunmannedaerialvehicletaskallocationunderuncertainty AT xiaoguanggao efficientsamplingbasedalgorithmsusingactivelearningandmanifoldlearningformultipleunmannedaerialvehicletaskallocationunderuncertainty |
| _version_ |
1725442546251857920 |