本研究根據微型無人機在室內環境中使用超寬頻(Ultra-wideband)定位系統時，因姿態角造成超寬頻系統測距誤差進行分析以及修正。超寬頻定位在動態目標追蹤有高精度與低延遲之優勢，卻會受到非視距、多路徑反射以及天線輻射方向性所干擾，導致定位性能下降。本研究中設計了一套無人機與錨點間的相對角度為輸入，結合經過獨熱編碼(one-hot encode)的錨點資訊的多層感知器（MLP）機器學習模型，透過收集大量不同角度配置下的數據訓練，並將模型嵌入無人機後進行飛行測試，實驗結果顯示模型能有效改善UWB測距誤差，提升定位品質。

This study analyzes and corrects the Ultra-Wideband (UWB) ranging errors induced by attitude angles when a micro Unmanned Aerial Vehicle (UAV) operates in indoor environments. Although UWB positioning offers high accuracy and low latency in dynamic target tracking, its performance can degrade due to non-line-of-sight (NLOS) conditions, multipath reflections, and the directional radiation pattern of antennas. In this research, a Multilayer Perceptron (MLP) machine learning model was designed, using the relative orientation between the UAV and the anchors as input features, combined with one-hot encoded anchor information. The model was trained using a large dataset collected under various angular configurations and deployed on the UAV for flight testing. Experimental results show that the model can effectively reduce UWB ranging errors and enhance positioning accuracy.

[1] Chi, G., Yang, Z., Xu, J., Wu, C., Zhang, J., Liang, J., & Liu, Y. (2022, June). Wi-Drone: Wi-Fi-based 6-DoF tracking for indoor drone flight control. In Proceedings of the 20th annual international conference on mobile systems, applications and services (pp. 56-68).
[2] Hashmi, A. (2021). A novel drone-based search and rescue system using bluetooth low energy technology. Engineering, Technology & Applied Science Research, 11(2), 7018-7022.
[3] Li, C., Tanghe, E., Suanet, P., Plets, D., Hoebeke, J., De Poorter, E., & Joseph, W. (2021). ReLoc 2.0: UHF-RFID relative localization for drone-based inventory management. IEEE Transactions on Instrumentation and Measurement, 70, 1-13.
[4] Niculescu, V., Palossi, D., Magno, M., & Benini, L. (2022). Energy-efficient, precise uwb-based 3-d localization of sensor nodes with a nano-uav. IEEE Internet of Things Journal, 10(7), 5760-5777.
[5] Fereidoony, F., Chamaani, S., & Mirtaheri, S. A. (2011). UWB monopole antenna with stable radiation pattern and low transient distortion. IEEE Antennas and Wireless Propagation Letters, 10, 302-305.
[6] Ahmed, Q. Z., & Yang, L. L. (2008, September). Normalised least mean-square aided decision-directed adaptive detection in hybrid direct-sequence time-hopping UWB systems. In 2008 IEEE 68th Vehicular Technology Conference (pp. 1-5). IEEE.
[7] Marano, S., Gifford, W. M., Wymeersch, H., & Win, M. Z. (2010). NLOS identification and mitigation for localization based on UWB experimental data. IEEE Journal on selected areas in communications, 28(7), 1026-1035.
[8] Foerster, J. R. (2001, May). The effects of multipath interference on the performance of UWB systems in an indoor wireless channel. In IEEE VTS 53rd Vehicular Technology Conference, Spring 2001. Proceedings (Cat. No. 01CH37202) (Vol. 2, pp. 1176-1180). IEEE.
[9] Yang, T., Davis, W. A., & Stutzman, W. L. (2009). Fundamental-limit perspectives on ultrawideband antennas. Radio Science, 44(01), 1-8.
[10] Zhao, W., Goudar, A., Panerati, J., & Schoellig, A. P. (2020). Learning-based bias correction for ultra-wideband localization of resource-constrained mobile robots. arXiv preprint arXiv:2003.09371.
[11] Ledergerber, A., & D’andrea, R. (2018). Calibrating away inaccuracies in ultra wideband range measurements: A maximum likelihood approach. IEEE Access, 6, 78719-78730.
[12] Niculescu, V., Palossi, D., Magno, M., & Benini, L. (2022). Energy-efficient, precise uwb-based 3-d localization of sensor nodes with a nano-uav. IEEE Internet of Things Journal, 10(7), 5760-5777.
[13] Okut, H. (2016). Bayesian Regularized Neural Networks for Small n Big. Artificial Neural Networks: Models and Applications, 27.
[14] W.-T. Koung, W.-L. Chan. (2024) “Enhancing Ultra-Wideband Positioning for Indoor UAVs Using Artificial Neural Network”
[15] Qian, M., Zhao, K., Li, B., & Seneviratne, A. (2022). An Overview of Ultra-Wideband Technology and Performance Analysis of UWB-TWR in Simulation and Real Environment. IPIN-WiP, 12, 1-16.
[16] Benouakta, A., Ferrero, F., Lizzi, L., & Staraj, R. (2024). Advancements in Industrial RTLSs: A Technical Review of UWB Localization Devices Emphasizing Antennas for Enhanced Accuracy and Range. Electronics, 13(4), 751. https://doi.org/10.3390/electronics13040751
[17] Hiraguri, T., Shimizu, H., Kimura, T., Matsuda, T., Maruta, K., Takemura, Y., ... & Takanashi, T. (2023). Autonomous drone-based pollination system using AI classifier to replace bees for greenhouse tomato cultivation. IEEE Access, 11, 99352-99364.