電動載具在貨物和乘客運輸的重要性與應用性日益提高，而在室內場域越來越大以及載具數量越來越多的情況下，車隊管理對於確保載具的調度與運行控管的議題日益凸顯，因此我們在本研究中的目標是在機場、購物中心、博物館此類的大型室內場域中，建構一套適用車隊管理的軟硬體架構，在此架構中有兩大重點，分別為載具的室內定位與資通訊能力，在室內定位方面，由於沒有統一的技術標準，且不同的室內定位技術有不同特性，因此我們運用了一種混合室內定位框架以結合多種定位技術的特點，並採用無跡卡爾曼濾波器演算法進行位置融合與校正，藉此達到穩定且準確的定位成效，從而可支援路徑規劃與導航功能；在資通訊能力方面，我們在載具上安裝了物聯網閘道器，並針對其軟體架構進行設計，除了讓載具在場域內移動時，能夠與伺服器之間具有可靠的訊息傳輸，還可以藉由邊緣運算方式讓車輛能夠迅速應對環境的改變。藉由本研究所提出之架構能夠支援車隊管理系統，管理人員可以透過載具傳送至伺服器的即時位置，有效提升場域中載具的維運與調度效率。

The importance and applicability of electric vehicles, such as electric scooter, automated guided vehicles (AGV), and autonomous mobile robot (AMR), are growing in terms of transporting goods and passengers. As indoor spaces expand and the number of vehicles grows, fleet management's role in ensuring proper vehicle scheduling and operational control becomes more pronounced. Therefore, the goal of our study is to construct a hardware and software architecture suitable for fleet management in large indoor areas such as airports, shopping malls, and museums. Within this architecture, there are two main focuses: indoor positioning of vehicles and their communication capabilities. In terms of indoor positioning, due to the lack of a unified technical standard and different indoor positioning technologies having distinct characteristics, we employ a hybrid indoor positioning framework that combines the features of multiple positioning techniques. We use the unscented Kalman filter algorithm for position fusion and calibration, achieving stable and accurate positioning results, which can further support route planning and navigation functions. Regarding communication capabilities, we install Internet of Things (IoT) gateway on the vehicle and design the software architecture. This not only ensures reliable message transmission between the vehicle and the server as the vehicle moves within the venue but also allows the vehicle to quickly adapt to environmental changes through edge computing. With the framework proposed in this study, fleet management systems can be supported. Managers can efficiently enhance the maintenance and dispatching efficiency of vehicles in the venue by accessing their real-time locations sent to the server.

[1] F. Rubio, F. Valero, and C. Llopis-Albert. “A review of mobile robots: Concepts, methods, theoretical framework, and applications.” International Journal of Advanced Robotic Systems, 2019.
[2] An AIoT-based Inventory Auditing and Surveillance Autonomous Mobile Robot (AMR), https://www.polyu.edu.hk/kteo/knowledge-transfer/innovations-and-technologies/technology-search/4-smart-cities-and-information-technology/4_ise_20_0220/
[3] K. Raphael, et al. “Techno-economic evaluation of 5g technology for automated guided vehicles in production.” Electronics 11.2 (2022): 192.
[4] M. Bielli, A. Bielli, and R. Rossi. “Trends in models and algorithms for fleet management.” Procedia-Social and Behavioral Sciences, 2011.
[5] Security platform now runs on in-vehicle network processors, https://www.microcontrollertips.com/security-platform-now-runs-on-in-vehicle-network-processors/
[6] J. Guth, et al. “Comparison of IoT Platform Architectures: A Field Study Based on a Reference Architecture,” In 2016 Cloudification of the Internet of Things (CIoT), pages 1-6, Paris, France, November 23-25, 2016
[7] What is ThingsBoard Edge, https://thingsboard.io/docs/pe/edge/getting-started-guides/what-is-edge/
[8] Z. Deng, et al. “Situation and development tendency of indoor positioning.” China Communications 10.3 (2013): 42-55.
[9] F. Gu, et al. “Indoor localization improved by spatial context—A survey.” ACM Computing Surveys (CSUR) 52.3 (2019): 1-35.
[10] L. Li, et al. “Experiencing and handling the diversity in data density and environmental locality in an indoor positioning service.” Proceedings of the 20th annual international conference on Mobile computing and networking. 2014.
[11] A. Baniukevic, S. J. Christian, and H. Lu. “Hybrid indoor positioning with wi-fi and bluetooth: Architecture and performance.” 2013 IEEE 14Th international conference on mobile data management. Vol. 1. IEEE, 2013.
[12] A. Nessa, et al. “A survey of machine learning for indoor positioning.” IEEE access 8 (2020): 214945-214965.
[13] W. Shao, et al. “Location fingerprint extraction for magnetic field magnitude based indoor positioning.” Journal of Sensors 2016 (2016).
[14] J. Zhu, and H. Xu. “Review of RFID-based indoor positioning technology.” Innovative Mobile and Internet Services in Ubiquitous Computing: Proceedings of the 12th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS-2018). Springer International Publishing, 2019.
[15] A. Poulose, O. S. Eyobu, and D. S. Han. “An indoor position-estimation algorithm using smartphone IMU sensor data.” Ieee Access 7 (2019): 11165-11177.
[16] F. Alhomayani, and H. M. Mohammad. “OutFin, a multi-device and multi-modal dataset for outdoor localization based on the fingerprinting approach.” Scientific Data 8.1 (2021): 66.
[17] S. Xia, et al. “Indoor fingerprint positioning based on Wi-Fi: An overview.” ISPRS International Journal of Geo-Information 6.5 (2017): 135.
[18] A. Loeffler. “Localizing passive UHF RFID tags with wideband signals.” 2011 IEEE International Conference on Microwaves, Communications, Antennas and Electronic Systems (COMCAS 2011). IEEE, 2011.
[19] X. Teng, et al. “ARPDR: An accurate and robust pedestrian dead reckoning system for indoor localization on handheld smartphones.” 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2020.
[20] M. Wang, et al. “Indoor PDR positioning assisted by acoustic source localization, and pedestrian movement behavior recognition, using a dual-microphone smartphone.” Wireless Communications and Mobile Computing 2021 (2021): 1-16.
[21] Object Tracking: Kalman Filter with Ease, https://www.kalmanfilter.net/kalman1d.html
[22] R. Woo, E. J. Yang, and D. W. Seo. “A fuzzy-innovation-based adaptive Kalman filter for enhanced vehicle positioning in dense urban environments.” Sensors 19.5 (2019): 1142.
[23] C. Jian, S. Song, and H. Yu. “An indoor multi-source fusion positioning approach based on PDR/MM/WiFi.” AEU-International Journal of Electronics and Communications 135 (2021): 153733.
[24] F. Bakhshande, and S. Dirk. “Adaptive Step Size Control of Extended/Unscented Kalman Filter Using Event Handling Concept.” Frontiers in Mechanical Engineering 5 (2020): 74.
[25] K. C. Chien, D. Z. Zhuang, and W. G. Teng. “Assisting Order Picking and Inventory Tracking in Warehouses with an IoT Gateway.” 2022 12th International Conference on Software Technology and Engineering (ICSTE). IEEE, 2022.
[26] H. X. Li, et al. “Research on multi-sensor pedestrian dead reckoning method with UKF algorithm.” Measurement 169 (2021): 108524.
[27] Y. Zhu, et al. “Indoor positioning method based on WiFi/Bluetooth and PDR fusion positioning.” 2021 13th International Conference on Advanced Computational Intelligence (ICACI). IEEE, 2021.