自主無人車定位與軌跡追蹤控制器設計｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	楊瑞安 Jui-An Yang
論文名稱：	自主無人車定位與軌跡追蹤控制器設計 Design of Positioning and Trajectory Tracking Controller for an Autonomous Vehicle
指導教授：	郭重顯 Chung-Hsien Kuo
口試委員:	黃漢邦 Han-Pang Huang 顏炳郎 Bing-Lang Yan 蔣欣翰 Hsin-Han Jiang 蘇順豐 Shun-Feng Su 郭重顯 Chung-Hsien Kuo
學位類別：	碩士 Master
系所名稱：	電資學院 - 電機工程系 Department of Electrical Engineering
論文出版年：	2021
畢業學年度：	109
語文別：	英文
論文頁數：	90
中文關鍵詞：	車輛定位、軌跡追蹤、無損型卡爾曼濾波器、模型預測控制、強化式學習
外文關鍵詞：	Vehicle Positioning, Path Tracking, Unscented Kalman Filter, Model Predictive Control, Reinforcement Learning
相關次數：	點閱：282 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

上一筆

定位以及軌跡追蹤是衡量自主無人車效能的重要指標。縱使RTK-GPS能夠提供良好的戶外車輛定位能力。然而，低更新率、訊號遮蔽、訊號飄移及通訊穩定性，都是一般GPS乃至於高精度RTK-GPS存在的問題。本研究應用無損型卡爾曼濾波器(UKF)之多感測器融合，結合RTK-GPS、慣性量測單元(IMU)以及輪里程計來提升自主車輛定位能力。模型預測控制(MPC)能應用並解決車輛之軌跡追蹤問題。然而，模型預測控制器中的參數調整，對於整體控制表現有著顯著地影響。一般參數調整皆是根據使用者長期累積的經驗進行手動調整，此舉容易造成時間的浪費以及錯誤的調校。因此，本論文應用強化式學習(RL)來預先訓練控制器參數之基準值，從而讓使用者能夠更快速的應用其訓練結果於實際車輛控制，並提升整體效率。利用Matlab以及iVAM實驗室自主開發之無人電動車來驗證本研究之可靠性。於199.27公尺的行進路線中，本論文提出之UKF座標估測系統有著0.82%之低誤差率。應用RL訓練參數之MPC控制器在軌跡追蹤任務中，比起手動調整之控制器也有著0.227公尺的低均方根誤差。從模擬以及實驗中能夠驗證本研究具有高準確性以及優良的軌跡追蹤能力。

Positioning and path tracking are important measures to evaluate the performance of autonomous vehicles. Although the real-time kinematic GPS (RTK-GPS) provides a good accuracy of outdoor positioning, low update rate, signal obstruction, signal drift and network instability result in robust positioning concerns. To solve this problem, a multi-sensory fusion approach using an unscented Kalman filter (UKF) is proposed to improve the vehicle positioning performance, and hence the RTK-GPS combing with inertial measurement unit (IMU) and wheel odometry is utilized for robust vehicle positioning. In addition to vehicle positioning, a model predictive control (MPC) method is usually used to solve the path tracking problem. However, the determination of MPC parameters is a challenge of applying the MPC to achieve high performance. Therefore, reinforcement learning (RL) is utilized in this paper to generalize the pre-trained datum value for the determination of MPC parameters in practice. Such an RL process is to significantly reduce the time of blind tuning of MPC parameters. In order to evaluate the performance of vehicle positioning and path tracking, the software simulation using Matlab and a laboratory-made full-scale electric vehicle was arranged for experiments and validation. In a 199.27m loop path, the estimated travel distance error was 0.82% in terms of UKF. The MPC parameters generated by RL also achieved better tracking performance with 0.227m of RMSE in path tracking experiments, and it also achieved better tracking performance when compared to human-tuned MPC parameters.

指導教授推薦書    i
口試委員會審定書    ii
誌謝    iii
摘要    iv
Abstract    v
List of Tables    ix
List of Figures    x
Nomenclature    xii
Chapter 1    Introduction    1
1    Motivation and Purpose    1
2    Literature Review    3
2.1    Related Research of RTK-GPS and Multi-sensory Fusion    3
2.2    Related Research of MPC and RL    6
3    Organization of the Thesis    8
Chapter 2    System Architecture and Operation    9
1    System Hardware Architecture    9
2    Software Design and Operation Flowchart    10
2.1    Robot Operating System (ROS)    10
2.2    Operation Flowchart    11
3    Data Communication Architecture    16
3.1    Real-Time Kinematic GPS (RTK-GPS)    16
3.2    Inertial Measurement Unit (IMU)    18
3.3    Wheel Encoder    18
3.4    2D-LiDAR    19
Chapter 3    Position Estimator with Multi-Sensory Fusion    20
1    Data Filtering and Elimination    20
1.1    Mahalanobis Distance    20
1.2    Threshold Definition and Switch Cases    22
2    Position Estimator Design    24
2.1    Unscented Kalman Filter    24
2.2    Sensor Fusion with RTK-GPS and IMU/Odometry    27
Chapter 4    RL Based MPC Controller Design    30
1    Vehicle Modeling    30
1.1    Kinematic Model of Vehicle Motion    30
1.2    Dynamic Model of Vehicle Motion    32
2    MPC Problem Formulation    34
2.1    Prediction Model    34
2.2    Prediction Formulation Sparseness    36
2.3    Quadratic Programming Problem    39
2.4    Quadratic Objective Function    40
3    Reinforcement Learning Pre-trained Procedure    41
3.1    Overview of Reinforcement Learning Framework    41
3.2    Exploration and Exploitation of RL    43
3.3    Reinforcement Learning Based MPC    44
4    Constraint Handling    45
4.1    Constraint Types    45
4.2    Constraint Design    46
5    Solution and Optimization of Constrained MPC    47
5.1    Convex Optimization    47
5.2    Barrier Interior Point Method    48
Chapter 5    Experiments and Results    52
1    Experiment Setup and Coordinate Transformation    52
1.1    Experiment Setup    52
1.2    Coordinates Transformation    55
2    Simulation of RLMPC Based Path Tracking    55
3    Validation of Estimated Distance with Position Estimator    57
4    Integrated Experiment with EV by Applying RLMPC    62
Chapter 6    Conclusions and Future Works    66
References    67
Appendix A Simulation of DLC Maneuver with Constrained MPC    71

                                

[1] E.A. Wan, and R.V.D. Merwe, “The Unscented Kalman Filter for Nonlinear Estimation,” IEEE Adaptive Systems for Signal Processing, Communications, and Control Symposium, pp. 2153-2158, 2000.
[2] C. Rose, J. Britt, J. Allen and D. Bevly, “An Integrated Vehicle Navigation System Utilizing Lane-Detection and Lateral Position Estimation Systems in Difficult Environments for GPS,” IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 6, pp. 2615-2629, 2014.
[3] I. Um, S. Park, S. Oh and H. Kim, “Analyzing Location Accuracy of Unmanned Vehicle According to RTCM Message Frequency of RTK-GPS,” 2019 25th Asia-Pacific Conference on Communications (APCC), Ho Chi Minh City, Vietnam, pp. 326-330, 2019.
[4] J. W. Kim, D. K. Lee, S. B. Cao and S. S. Lee, “Availability evaluation and development of network-RTK for vehicle in downtown,” 2014 International Conference on Information and Communication Technology Convergence (ICTC), Busan, Korea, pp. 557-558, 2014.
[5] T. Liu and B. Li, “Single-frequency BDS/GPS RTK with low-cost U-blox receivers,” 2017 Forum on Cooperative Positioning and Service (CPGPS）, Harbin, China, pp. 232-238, 2017.
[6] K. M. Ng, J. Johari, S. A. C. Abdullah, A. Ahmad and B. N. Laja, “Performance Evaluation of the RTK-GNSS Navigating under Different Landscape,” 2018 18th International Conference on Control, Automation and Systems (ICCAS), Daegwallyeong, Korea, pp. 1424-1428, 2018.
[7] I. Um, S. Park, H. T. Kim and H. Kim, “Configuring RTK-GPS Architecture for System Redundancy in Multi-Drone Operations,” IEEE Access, vol. 8, pp. 76228-76242, 2020.
[8] D. Maier and A. Kleiner, “Improved GPS sensor model for mobile robots in urban terrain,” 2010 IEEE International Conference on Robotics and Automation, Anchorage, Alaska, pp. 4385-4390, 2010.
[9] S. Yi, S. Worrall and E. Nebot, “Geographical Map Registration and Fusion of Lidar-Aerial Orthoimagery in GIS,” 2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand, pp. 128-134, 2019.
[10] L. Wei, C. Cappelle, Y. Ruichek and F. Zann, “Intelligent Vehicle Localization in Urban Environments Using EKF-based Visual Odometry and GPS Fusion,” IFAC Proceedings Volumes, vol.44, issue 1, pp. 13776-13781, 2011.
[11] M. Aftatah, A. Lahrech and A. Abounada, “Fusion of GPS/INS/Odometer measurements for land vehicle navigation with GPS outage,” 2016 2nd International Conference on Cloud Computing Technologies and Applications (CloudTech), Marrakech, Morocco, pp. 48-55, 2016.
[12] P. Henkel, A. Sperl, U. Mittmann, R. Bensch and P. Färber, “Precise Positioning of Robots with Fusion of GNSS, INS, Odometry, LPS and Vision,” 2019 IEEE Aerospace Conference, Big Sky, MT, USA, pp. 1-6, 2019.
[13] S. A. S. Mohamed, M. Haghbayan, T. Westerlund, J. Heikkonen, H. Tenhunen and J. Plosila, “A Survey on Odometry for Autonomous Navigation Systems,” IEEE Access, vol. 7, pp. 97466-97486, 2019.
[14] A. Mikov, A. Panyov, V. Kosyanchuk and I. Prikhodko, “Sensor Fusion for Land Vehicle Localization Using Inertial MEMS and Odometry,” 2019 IEEE International Symposium on Inertial Sensors and Systems (INERTIAL), Naples, FL, USA, pp. 1-2, 2019.
[15] S. Zhao, Y. Chen and J. A. Farrell, “High-Precision Vehicle Navigation in Urban Environments Using an MEM's IMU and Single-Frequency GPS Receiver,” IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 10, pp. 2854-2867, 2016.
[16] M. Chen and Y. Ren, “MPC based path tracking control for autonomous vehicle with multi-constraints,” 2017 International Conference on Advanced Mechatronic Systems (ICAMechS), Xiamen, China, pp. 477-482, 2017.
[17] B. Paden, M. Čáp, S. Z. Yong, D. Yershov and E. Frazzoli, “A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles,” IEEE Transactions on Intelligent Vehicles, vol. 1, no. 1, pp. 33-55, 2016.
[18] J. -H. Jhang and F. -L. Lian, “An Autonomous Parking System of Optimally Integrating Bidirectional Rapidly-Exploring Random Trees* and Parking-Oriented Model Predictive Control,” IEEE Access, vol. 8, pp. 163502-163523, 2020.
[19] C. Shen, H. Guo, F. Liu and H. Chen, “MPC-based path tracking controller design for autonomous ground vehicles,” 2017 36th Chinese Control Conference (CCC), Dalian, China, pp. 9584-9589, 2017.
[20] W. Tang, M. Yang, C. Wang, B. Wang, L. Zhang and F. Le, “MPC-Based Path Planning for Lane Changing in Highway Environment,” 2018 Chinese Automation Congress (CAC), Xi'an, China, pp. 1003-1008, 2018.
[21] Y. Chen and J. Wang, “Trajectory Tracking Control for Autonomous Vehicles in Different Cut-in Scenarios,” 2019 American Control Conference (ACC), Philadelphia, PA, USA, pp. 4878-4883, 2019.
[22] S. Dixit et al., “Trajectory Planning for Autonomous High-Speed Overtaking in Structured Environments Using Robust MPC,” IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 6, pp. 2310-2323, 2020.
[23] A. Liniger, A. Domahidi and M. Morari, “Optimization-Based Autonomous Racing of 1:43 Scale RC Cars,” Optimal Control Applications and Methods, vol. 36, no. 5, pp.628-647, 2015.
[24] U. Rosolia, A. Carvalho and F. Borrelli, “Autonomous racing using learning Model Predictive Control,” 2017 American Control Conference (ACC), Seattle, WA, USA, pp. 5115-5120, 2017.
[25] F. Lin, Y. Chen, Y. Zhao and S. Wang, “Path tracking of autonomous vehicle based on adaptive model predictive control,” International Journal of Advanced Robotic Systems, pp.1-12, 2019.
[26] D. Görges, “Relations between Model Predictive Control and Reinforcement Learning,” IFAC-PapersOnLine, vol. 50, no. 1, pp. 4920-4928, 2017.
[27] H. Xie, X. Xu, Y. Li, W. Hong and J. Shi, “Model Predictive Control Guided Reinforcement Learning Control Scheme,” 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, United Kingdom, pp. 1-8, 2020.
[28] Y. Guan, Y. Ren, S.E. Li, Q. Sun, L. Luo, and K. Li, “Centralized Cooperation for Connected and Automated Vehicles at Intersections by Proximal Policy Optimization,” IEEE Transactions. On Transportation and Vehicular Technology, vol. 69, no. 11, pp. 12597- 12608, 2020.
[29] Y. Tange, S. Kiryu and T. Matsui, “Model Predictive Control Based on Deep Reinforcement Learning Method with Discrete-Valued Input,” 2019 IEEE Conference on Control Technology and Applications (CCTA), Hong Kong, China, 2019.
[30] H. K. Modalavalasa and M. L. Makkena, “Intelligent Parameter Tuning Using Segmented Adaptive Reinforcement Learning Algorithm,” 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, 2020, pp. 252-256.
[31] S. Lee, Mechatronic Design and Implementation of an Autonomous Electric Vehicle Prototype, Master Thesis, Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2018.
[32] M. Gao, Applying 3D Lidar Odometry and Mapping Technique for Campus Autonomous Vehicle Navigation System Development, Master Thesis, Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2019.
[33] A. Chang, Applying Sensor Fusion Technique for Indoor Mobile Robot SLAM System Development, Master Thesis, Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2019.

全文公開日期 2026/02/05 (校內網路)
全文公開日期本全文未授權公開 (校外網路)
全文公開日期本全文未授權公開 (國家圖書館：臺灣博碩士論文系統)

簡易檢索 / 詳目顯示

相關論文