It is an effective way to get more accurate results of UAV performance evaluation by fusing the data of infield test and outfield test. The common Bayes multi-source data fusion method can make comprehensive use of multiple information types while ensuring the decision risk as small as possible, but there are some risks, such as insufficient data utilization and small sample data being “submerged” by large sample data in the fusion. Due to the different scale and credibility of multi-source data, a non-uniform distribution probability sampling method is proposed based on evidence theory for the same sample space to avoid the risk of small sample data being “drowned” by large sample data; meanwhile, for the situation that the fusion weight mainly depends on the evaluation of experts is not objective enough, a comprehensive weight confirmation method of multi-source test data is proposed based on credibility measurement so as to realize the comprehensive evaluation of performance indicators based on multi-source data.
UAV Typical Index Evaluation Method Based on Improving Evidence Theory
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 311 ; 3171-3181
2022-03-18
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Evaluation of typical road telematics scenarios on a freeway
Kraftfahrwesen | 2004
|NTRS | 1965
|