PDF
Full
Outline
To address the issue of existing neural network models in inertial navigation overlooking the temporal characteristics, interdependencies, and periodicity of inertial measurement unit (IMU) sequences, which leads to degraded positioning accuracy, a IMU positioning neural network model is proposed that deeply integrates Xception and Transformer architectures. The proposed model employs an initial feature extraction layer, a deep feature extraction layer, and a velocity regression layer, which are tailored for learning velocity vectors, in order to capture the complex spatiotemporal characteristics of IMU sequences. To validate the effectiveness of the proposed model, experiments are conducted on four publicly available IMU datasets (RONIN, RIDI, IDOL and IMUNET). Experimental results demonstrate that, the proposed model achieves improved localization performance on most seen and unseen test sets compared with five state-of-the-art models. Specifically, on the largest RONIN dataset, the absolute trajectory error is reduced by 17.16% and 13.15% relative to the weakest baseline model. On the smallest IDOL dataset, the reductions reach 28.29% and 22.96%, respectively. These results indicate that the proposed model provides more accurate and robust velocity predictions, thereby significantly enhancing IMU-based localization accuracy.
PDF
186
90
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
