66141

Автор(ы): 

Автор(ов): 

2

Параметры публикации

Тип публикации: 

Доклад

Название: 

Optimal Estimation Using Deep Neural Networks Applied to Navigation and Motion Control

Электронная публикация: 

Да

ISBN/ISSN: 

17426588

DOI: 

10.1088/1742-6596/1864/1/012012

Наименование конференции: 

  • 13th Multiconference on Control Problems (MCCP 2020), Saint-Petersburg

Наименование источника: 

  • Journal of Physics: Conference Series

Обозначение и номер тома: 

Volume 1864, № 012012

Город: 

  • Saint Petersburg, Russia

Издательство: 

  • IOP Publishing Ltd

Год издания: 

2021

Страницы: 

https://iopscience.iop.org/article/10.1088/1742-6596/1864/1/012012
Аннотация
The critical analysis is given concerning the current state of using deep neural networks with convolutional and recurrent layers, a recurrent network of Long Short-Term Memory, Gated Recurrent Units for estimation tasks in relation to navigation and motion control. A comparison of neural network and traditional methods is given for understanding and explaining their functioning. The differences, advantages and disadvantages of deep neural networks in relation to solving estimation problems are revealed. The possibility of machine training with reinforcement is analyzed for estimation tasks in navigation and motion control in real time. The prospects of using neural networks in the processing of navigation data, as well as for the tasks of adaptive estimation and trajectory tracking, are formulated.

Библиографическая ссылка: 

Амосов О.С., Амосова С.Г. Optimal Estimation Using Deep Neural Networks Applied to Navigation and Motion Control / Journal of Physics: Conference Series. Saint Petersburg, Russia: IOP Publishing Ltd, 2021. Volume 1864, № 012012. С. https://iopscience.iop.org/article/10.1088/1742-6596/1864/1/012012.