Presentation | 2021-06-24 A Study on Recurrent Neural Network Aided GNSS Positioning Kohei Nishioka, Shinsuke Ibi, Takumi Takahashi, Hisato Iwai, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | One method of positioning schemes with the aid of the global navigation satellite system (GNSS) is to approximately solve nonlinear simultaneous equations. However, these nonlinear simultaneous equations include external factors such as clock errors and multipath, which induce position estimation errors. To address the errors, this study focuses on the fact that the data obtained from the distance measurement signals broadcasted by positioning satellites is time-series data. Based on the focus point, two types of recurrent neural network (RNN) for time-series data are designed. The first one inputs pseudo-range and position coordinates of satellites. The other inputs solutions of successive approximation methods as pre-processing. The former relies on raw data, which makes the learning unstable depending on the availability of satellite observations. In contrast, the latter exploits on a model called the successive approximation method, resulting in stable learning at the sacrifice of computational complexity. In order to evaluate the usefulness of the RNN, a neural network consisting of fully connected layers is implemented for comparison. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | GNSS / pseudo-range / neural network / positioning / generalization performance |
Paper # | RCS2021-53 |
Date of Issue | 2021-06-16 (RCS) |
Conference Information | |
Committee | RCS |
---|---|
Conference Date | 2021/6/23(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | First Presentation in IEICE Technical Committee, Resource Control, Scheduling, Wireless Communications, etc. |
Chair | Eiji Okamoto(Nagoya Inst. of Tech.) |
Vice Chair | Fumihide Kojima(NICT) / Toshihiko Nishimura(Hokkaido Univ.) / Tomoya Tandai(Toshiba) |
Secretary | Fumihide Kojima(Panasonic) / Toshihiko Nishimura(NEC) / Tomoya Tandai |
Assistant | Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Tatsuki Okuyama(NTT DOCOMO) |
Paper Information | |
Registration To | Technical Committee on Radio Communication Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Study on Recurrent Neural Network Aided GNSS Positioning |
Sub Title (in English) | |
Keyword(1) | GNSS |
Keyword(2) | pseudo-range |
Keyword(3) | neural network |
Keyword(4) | positioning |
Keyword(5) | generalization performance |
1st Author's Name | Kohei Nishioka |
1st Author's Affiliation | Doshisha University(Doshisha Univ.) |
2nd Author's Name | Shinsuke Ibi |
2nd Author's Affiliation | Doshisha University(Doshisha Univ.) |
3rd Author's Name | Takumi Takahashi |
3rd Author's Affiliation | Osaka University(Osaka Univ.) |
4th Author's Name | Hisato Iwai |
4th Author's Affiliation | Doshisha University(Doshisha Univ.) |
Date | 2021-06-24 |
Paper # | RCS2021-53 |
Volume (vol) | vol.121 |
Number (no) | RCS-72 |
Page | pp.pp.145-150(RCS), |
#Pages | 6 |
Date of Issue | 2021-06-16 (RCS) |