An Integration of Deep Neural Network-Based Extended Kalman Filter (DNN-EKF) Method in Ultra-Wideband (UWB) Localization for Distance Loss Optimization
Chanthol Eang, Seungjae Lee · 2024
Read An Integration of Deep Neural Network-Based Extended Kalman Filter (DNN-EKF) Method in Ultra-Wideband (UWB) Localization for Distance Loss Optimization by Chanthol Eang, Seungjae Lee (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11645068.txt.
Description
Chanthol Eang and Seungjae Lee work on a practical problem: helping indoor robots know exactly where they are. In tight spaces such as homes and warehouses, satellite signals do not reach, so their system uses ultra-wideband radio instead. The authors blend a deep neural network with a classic tracking filter, the extended Kalman filter.
Their combined method, called DNN-EKF, learns patterns in the radio signals and then smooths the position estimates with the filter. The goal is to cut distance errors for robots moving in noisy indoor settings. In the authors' tests, the combined method beat rival pairings of learning models and filters. It also beat older standard approaches. They report the lowest distance loss of all methods tried, and they present the method as a good fit for real-time robot use.
Catalog record
| CREATOR | Chanthol Eang, Seungjae Lee |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 107 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |