在電動車日益普及的時代，自動駕駛的性能隨著市場需求不斷進步。精確的車輛定位是推進車輛自動化技術超越第三級的關鍵基礎。然而，傳統的全球定位系統（global positioning system GPS）容易受到環境干擾而導致不準確性。現有的提高定位準確性的方法要麼需要基礎設施修改以替代 GPS，要麼需要利用環境信息的先前知識來減少干擾，這兩者在實務上都難以執行。為了提高基於 GPS 的車輛定位系統的準確性，提供更準確的座標估算，我們提出了一個自監督學習結構，由四種學習方法組成：分層基於密度的空間聚類（hierarchical density-based spatial clustering of applications with noise HDBSCAN）、圖卷積網絡（graph convolutional network GCN）、域對抗神經網絡（domain adversarial neural network DANN）和長短期記憶（long short-term memory LSTM）。所提出的框架利用了車輛定位中的空間和時間信息。模擬結果表明，在我們提出的綜合框架內，車輛座標估算的準確性得到了顯著提高。

Precise vehicle positioning is the key foundation for advancing vehicle automation technology beyond level three. However, the conventional global positioning system (GPS) is susceptible to inaccuracies due to environmental interference. Existing works for improving positioning accuracy either require fundamental infrastructure modification to replace GPS or utilize prior knowledge of environmental information to reduce interference, where both are impractical in the real world. To improve the GPS-based vehicle positioning system to provide more accurate coordinate estimates without prior knowledge of environmental information, we propose a self-supervised learning architecture composed of four learning methods: hierarchical density-based spatial clustering (HDBSCAN), graph convolution network (GCN), domain-adversarial neural network (DANN), and long short-term memory (LSTM). The proposed framework utilizes both spatial and temporal information in vehicle positioning. The simulation results indicate that within our proposed comprehensive framework, the accuracy of vehicle coordinate estimates receives significant improvement.

Abstract (Chinese) I
Abstract II
Acknowledgements (Chinese) III
Contents IV
List of Figures VI
List of Tables VII
1 Introduction 1
1.1 Background . . . . . . . . . . . 1
1.2 Motivation . . . . . . . . . . . 2
1.3 Main Contributions . . . . . . . 3
1.4 Organization . . . . . . . . . . 4
2 System Model 5
2.1 System Setup . . . . . . . . . . 5
2.2 Problem formulation . . . . . . 7
3 Architecture Design 9
3.1 System Overview . . . . . . . . 9
3.2 Architecture of the clustering vehicles . . . . . . . . 11
3.3 Architecture of the classifying clusters . . . . . . . 14
3.4 Architecture of generating initial estimations . . . . 16
3.5 Architecture of generating final estimations . . . . . 18
4 Results and Discussion 19
4.1 Data Generation . . . . . . . . . . . . . . . 19
4.2 Simulation setup . . . . . . . . . . . . . . . 22
4.3 Performance Comparison and Discussion . . . . .25
5 Conclusion 33
Bibliography 34

[1] P. Hang and X. Chen, “Towards autonomous driving: Review and perspectives on configuration and control of four-wheel independent drive/steering electric vehicles,” Actuators, vol. 10, no. 8, 2021.
[2] D. Phan, A. Bab-Hadiashar, M. Fayyazi, R. Hoseinnezhad, R. N. Jazar, and H. Khayyam, “Interval type 2 fuzzy logic control for energy management of hybrid electric autonomous vehicles,” IEEE Trans. Intell. Veh., vol. 6, no. 2, pp. 210–220,2021.
[3] Á. Takács, D. A. Drexler, P. Galambos, I. J. Rudas, and T. Haidegger, “Assessment and standardization of autonomous vehicles,” in Proc. IEEE 22nd Int. Conf. Intell. Eng. Syst. (INES), Jun. 2018, pp. 000 185–000 192.
[4] B. Goldfain, P. Drews, C. You, M. Barulic, O. Velev, P. Tsiotras, and J. M. Rehg, “Autorally: An open platform for aggressive autonomous driving,” IEEE Control Syst. Mag., vol. 39, no. 1, pp. 26–55, Feb. 2019.
[5] N. Joubert, T. G. R. Reid, and F. Noble, “Developments in modern gnss and its impact on autonomous vehicle architectures,” in 2020 IEEE Intelligent Vehicles Symposium (IV), 2020, pp. 2029–2036.
[6] M. Abolfazli Esfahani, H. Wang, K. Wu, and S. Yuan, “Aboldeepio: A novel deep inertial odometry network for autonomous vehicles,” IEEE Trans. Intell. Transp. Syst., vol. 21, no. 5, pp. 1941–1950, 2020.
[7] H. Jing, Y. Gao, S. Shahbeigi, and M. Dianati, “Integrity monitoring of gnss/ins based positioning systems for autonomous vehicles: State-of-the-art and open challenges,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 9, pp. 14 166–14 187, 2022.
[8] C. Barrios and Y. Motai, “Improving estimation of vehicle’s trajectory using the latest global positioning system with kalman filtering,” IEEE Trans. Instrum. Meas., vol. 60, no. 12, pp. 3747–3755, 2011.
[9] C. Zhang, D. Chu, S. Liu, Z. Deng, C. Wu, and X. Su, “Trajectory planning and tracking for autonomous vehicle based on state lattice and model predictive control,” IEEE Intell. Transp. Syst. Mag., vol. 11, no. 2, pp. 29–40, 2019.
[10] S.-W. Kim, W. Liu, M. H. Ang, E. Frazzoli, and D. Rus, “The impact of cooperative perception on decision making and planning of autonomous vehicles,” IEEE Intell. Transp. Syst. Mag., vol. 7, no. 3, pp. 39–50, 2015.
[11] H. Bagheri, M. Noor-A-Rahim, Z. Liu, H. Lee, D. Pesch, K. Moessner, and P. Xiao, “5g nr-v2x: Toward connected and cooperative autonomous driving,” IEEE Commun. Standards Mag., vol. 5, no. 1, pp. 48–54, 2021.
[12] Y. Fu, C. Li, F. R. Yu, T. H. Luan, and Y. Zhang, “A survey of driving safety with sensing, vehicular communications, and artificial intelligence-based collision avoidance,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 7, pp. 6142–6163, 2022.
[13] N. Piperigkos, A. S. Lalos, K. Berberidis, and C. Anagnostopoulos, “Cooperative multi-modal localization in connected and autonomous vehicles,” in Proc. IEEE 3rd Connected Automated Vehicles Symp. (CAVS), Nov. 2020, pp. 1–5.
[14] P. Yang, D. Duan, C. Chen, X. Cheng, and L. Yang, “Multi-sensor multi-vehicle (msmv) localization and mobility tracking for autonomous driving,” IEEE Trans. Veh. Technol., vol. 69, no. 12, pp. 14 355–14 364, 2020.
[15] K. Viana, A. Zubizarreta, and M. Díez, “Robust localization for autonomous vehicles in dense urban areas,” in 2021 25th International Conference on System Theory, Control and Computing (ICSTCC). IEEE, 2021, pp. 107–112.
[16] A. Foliadis, M. H. C. Garcia, R. A. Stirling-Gallacher, and R. S. Thoma, “Reliable deep learning based localization with csi fingerprints and multiple base stations,” in ICC 2022-IEEE International Conference on Communications. IEEE, 2022,
pp. 3214–3219.
[17] E. Zhang and N. Masoud, “Increasing gps localization accuracy with reinforcement learning,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 5, pp. 2615–2626, May. 2020.
[18] B. Yang, R. Chen, B. Li, and C. Li, “Multi-vehicle cooperative positioning based on edge-computed multidimensional scaling,” China Commun., vol. 18, no. 6, pp. 53–63, Jun. 2021.
[19] M. Yang, B. Ai, R. He, C. Shen, M. Wen, C. Huang, J. Li, Z. Ma, L. Chen, X. Li, and Z. Zhong, “Machine-learning-based scenario identification using channel characteristics in intelligent vehicular communications,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 7, pp. 3961–3974, Jul. 2021.
[20] I. H. Ghaith, A. Rawashdeh, and S. Al Zubi, “Transfer learning in data fusion at autonomous driving,” in 2021 International Conference on Information Technology (ICIT), 2021, pp. 714–718.
[21] S. Nam, D. Lee, J. Lee, and S. Park, “CNVPS: Cooperative neighboring vehicle positioning system based on vehicle-to-vehicle communication,” IEEE Access, vol. 7, pp. 16 847–16 857, 2019.
[22] R. J. Campello, D. Moulavi, and J. Sander, “Density-based clustering based on hierarchical density estimates,” in Pacific-Asia conference on knowledge discovery and data mining. Springer, 2013, pp. 160–172.
[23] C.-H. Lin, Y.-H. Fang, H.-Y. Chang, Y.-C. Lin, W.-H. Chung, S.-C. Lin, and T.-S. Lee, “GCN-CNVPS: Novel method for cooperative neighboring vehicle positioning system based on graph convolution network,” IEEE Access, vol. 9, pp. 153 429–153 441, Nov. 2021.
[24] W.-Y. Chen, H.-Y. Chang, C.-Y. Wang, and W.-H. Chung, “Cooperative neighboring vehicle positioning systems based on graph convolutional network: A multiscenario transfer learning approach,” in Proc. IEEE Int. Conf. Commun., 2022, pp. 3226–3231.
[25] K. Liu, H. B. Lim, E. Frazzoli, H. Ji, and V. C. S. Lee, “Improving positioning accuracy using gps pseudorange measurements for cooperative vehicular localization,” IEEE Trans. Veh. Technol., vol. 63, no. 6, pp. 2544–2556, 2014.
[26] S. B. Cruz, T. E. Abrudan, Z. Xiao, N. Trigoni, and J. Barros, “Neighbor-aided localization in vehicular networks,” IEEE Trans. Intell. Transp. Syst., vol. 18, no. 10, pp. 2693–2702, 2017.
[27] J. B. Kenney, “Dedicated short-range communications (dsrc) standards in the united states,” Proc. IEEE, vol. 99, no. 7, pp. 1162–1182, Jul. 2011.
[28] G. Dupont, C. Leite, D. R. dos Santos, E. Costante, J. den Hartog, and S. Etalle, “Similarity-based clustering for iot device classification,” in 2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS), 2021, pp. 1–7.
[29] Y. H. Dianhai Wang and Z. Cai, “A two-phase clustering approach for traffic accident black spots identification: integrated gis-based processing and hdbscan model,” Int. J. Inj. Control Saf. Promot., vol. 30, no. 2, pp. 270–281, 2023.
[30] S. Gare, S. Chel, P. D. Pantula, A. Saxena, K. Mitra, R. Sarkar, and L. Giri, “Analytics pipeline for visualization of single cell rna sequencing data from brochoaveolar fluid in covid-19 patients: Assessment of neuro fuzzy-c-means and hdbscan,” in 2022 44th Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC), 2022, pp. 1634–1637.
[31] S. Tahvili, L. Hatvani, M. Felderer, W. Afzal, and M. Bohlin, “Automated functional dependency detection between test cases using doc2vec and clustering,” in Proc. IEEE Int. Conf. Artif. Intell. Test. (AITest), 2019, pp. 19–26.
[32] R. Setiawan, B. Tjahjono, G. Firmansyah, and H. Akbar, “Fraud detection in credit card transactions using hdbscan, umap and smote methods,” International Journal of Science, Technology & Management, vol. 4, no. 5, pp. 1333–1339, 2023.
[33] S. Wankhade, A. Dixit, and S. Bag, “A fast and rigid copy move forgery detection technique using hdbscan,” in International Conference on Computer Vision and Image Processing. Springer, 2019, pp. 15–24.
[34] J. Korczak, M. Pondel, and W. Sroka, “An approach to customer community discovery,” in 2019 Federated Conference on Computer Science and Information Systems (FedCSIS), 2019, pp. 675–683.
[35] N. Mou, R. Yuan, T. Yang, H. Zhang, J. Tang, and T. Makkonen, “Exploring spatiotemporal changes of city inbound tourism flow: The case of shanghai, china,” Tourism Management, vol. 76, p. 103955, 2020.
[36] M. F. Rahman, W. Liu, S. B. Suhaim, S. Thirumuruganathan, N. Zhang, and G. Das, “Density based clustering over location based services,” in Proc. 33rd IEEE Int. Conf. Data Eng. (ICDE), 2017, pp. 461–472.
[37] W. Hamilton, Z. Ying, and J. Leskovec, “Inductive representation learning on large graphs,” in Proc. 31st Int. Conf. Neural Inf. Process. Syst, vol. 30, 2017, p. 1024–1034.
[38] H. Han, M. Zhang, M. Hou, F. Zhang, Z. Wang, E. Chen, H. Wang, J. Ma, and Q. Liu, “Stgcn: A spatial-temporal aware graph learning method for poi recommendation,” in Proc. IEEE Int. Conf. Data Mining, 2020, pp. 1052–1057.
[39] L. Hetzel, D. S. Fischer, S. Günnemann, and F. J. Theis, “Graph representation learning for single-cell biology,” Curr. Opin. Syst. Biol., vol. 28, p. 100347, 2021.
[40] Z. Li, K. Jiang, S. Qin, Y. Zhong, and A. Elofsson, “Gcsenet: A gcn, cnn and senet ensemble model for microrna-disease association prediction,” PLOS Comput. Biol., vol. 17, no. 6, p. e1009048, 2021.
[41] J. Shang and Y. Sun, “Predicting the hosts of prokaryotic viruses using gcn-based semi-supervised learning,” BMC Biol., vol. 19, pp. 1–15, 2021.
[42] K. Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” J.Big data, vol. 3, no. 1, pp. 1–40, 2016.
[43] P. M. Uplavikar, Z. Wu, and Z. Wang, “All-in-one underwater image enhancement using domain-adversarial learning.” in CVPR workshops, 2019, pp. 1–8.
[44] Y. Tu, M.-W. Mak, and J.-T. Chien, “Variational domain adversarial learning with mutual information maximization for speaker verification,” IEEE/ACM Trans. Audio, Speech, Language Process., vol. 28, pp. 2013–2024, 2020.
[45] M. Abdelwahab and C. Busso, “Domain adversarial for acoustic emotion recognition,” IEEE/ACM Trans. Audio, Speech, Language Process., vol. 26, no. 12, pp.2423–2435, 2018.
[46] D. Grießhaber, N. T. Vu, and J. Maucher, “Low-resource text classification using domain-adversarial learning,” Computer Speech Language, vol. 62, p. 101056, 2020.
[47] L. R. Medsker and L. Jain, “Recurrent neural networks,” Design and Applications, vol. 5, no. 64-67, p. 2, 2001.
[48] Y. Yu, X. Si, C. Hu, and J. Zhang, “A review of recurrent neural networks: Lstm cells and network architectures,” Neural Comput., vol. 31, no. 7, pp. 1235–1270, 2019.
[49] L. Yao and Y. Guan, “An improved lstm structure for natural language processing,” in Proc. IEEE Int. Conf. Saf. Produce Informatization (IICSPI), 2018, pp. 565–569.
[50] D. Wang, J. Su, and H. Yu, “Feature extraction and analysis of natural language processing for deep learning english language,” IEEE Access, vol. 8, pp. 46 335–46 345, 2020.
[51] R. Dhumal Deshmukh and A. Kiwelekar, “Deep learning techniques for part of speech tagging by natural language processing,” in 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), 2020, pp. 76–81.
[52] R. Valiente, M. Zaman, S. Ozer, and Y. P. Fallah, “Controlling steering angle for cooperative self-driving vehicles utilizing cnn and lstm-based deep networks,” in 2019 IEEE Intelligent Vehicles Symposium (IV), 2019, pp. 2423–2428.
[53] Y. Shi, Y. Li, J. Fan, T. Wang, and T. Yin, “A novel network architecture of decision-making for self-driving vehicles based on long short-term memory and grasshopper optimization algorithm,” IEEE Access, vol. 8, pp. 155 429–155 440, 2020.
[54] A. Kouris, S. I. Venieris, M. Rizakis, and C.-S. Bouganis, “Approximate lstms for time-constrained inference: Enabling fast reaction in self-driving cars,” IEEE Consum. Electron. Mag., vol. 9, no. 4, pp. 11–26, 2020.
[55] T. Hussain, K. Muhammad, A. Ullah, Z. Cao, S. W. Baik, and V. H. C. de Albuquerque, “Cloud-assisted multiview video summarization using cnn and bidirectional lstm,” IEEE Trans. Ind. Informat., vol. 16, no. 1, pp. 77–86, 2020.
[56] L. Yuan, F. E. H. Tay, P. Li, and J. Feng, “Unsupervised video summarization with cycle-consistent adversarial lstm networks,” IEEE Trans. Multimedia, vol. 22, no. 10, pp. 2711–2722, 2020.
[57] P. Saikia, D. Dholaria, P. Yadav, V. Patel, and M. Roy, “A hybrid cnn-lstm model for video deepfake detection by leveraging optical flow features,” in Proc. Int. Joint Conf. Neural Netw. (IJCNN), 2022, pp. 1–7.
[58] D. Krajzewicz, G. Hertkorn, C. Rössel, and P. Wagner, “Sumo (simulation of urban mobility)-an open-source traffic simulation,” in Proceedings of the 4th middle East Symposium on Simulation and Modelling (MESM20002), 2002, pp. 183–187.