國立臺灣師範大學博碩士論文全文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	周毅安 Guilherme Christmann
論文名稱：	人形機器人於電動機車之平衡與轉向控制 Balance and Steering Control of a Humanoid Robot on an Electric Scooter
指導教授：	包傑奇 Jacky Baltes
學位類別：	碩士 Master
系所名稱：	電機工程學系 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：	58
英文關鍵詞：	Humanoid Robotics, Classical Control
DOI URL：	http://doi.org/10.6345/NTNU202100111
論文種類：	學術論文
相關次數：	點閱：149 下載：5
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

Autonomous vehicles and (humanoid) robotics are two fields that have greatly benefited from the rapid pace of development of deep learning systems. With intricate systems, it is possible to perform complex tasks and behaviors directly from raw sensor data. In light of recent developments in the aforementioned fields, it is necessary to start making efforts towards challenges that lie on their junction. From the perspective of humanoid robots, if we want to reach truly general-purpose robots it is of importance that they are capable of operating in any human environment. That includes the operation of vehicles, which we believe pose an interesting challenge for the state-of-the-art in both fields. This work focuses on the control and operation of a two-wheeled scooter using a large sized humanoid robot. A 3D model of the robot and scooter system was developed using CAD software, as well as physics based simulation environments. The subject of this study was the development of a steering-based control system. Two controllers were developed, analyzed and compared: a PID controller and a reinforcement learning control. Both controls were able to balance and track trajectories, and both performed better under different conditions. Advantages and limitations of applying these controllers to the real robot are also discussed.

Acknowledgements  i
Abstract  ii
Table of Contents  iii
List of Tables  v
List of Figures  vi
List of Symbols  x
Chapter 1 Introduction  1
1 Aims and Objectives  2
1.1 General Aim  3
1.2 Objectives  3
Chapter 2 Literature Review  4
1 Two-wheeled Vehicle Dynamics  4
2 Reinforcement Learning  7
2.1 PPO Proximal Policy Optimization  9
Chapter 3 Robot -Scooter System  12
1 The Two -Wheeled Vehicle Gogoro Scooter  12
2 The Robot THORMANG3  13
3 Robot-Scooter System  15
Chapter 4 Methodology  17
1 PID Controller  17
1.1 Balance Control  17
1.2 Direction Control – Path Tracking  18
2 RL Agent – PPO  20
2.1 Balance Control  21
2.2 Commanded Control – Path Tracking  22
Chapter 5 Results and Discussion  24
1 Balance Control – PID Controller  24
1.1 PID – Upright Balance (Tilt Reference = 0°)  24
1.2 PID – Balance while turning (Tilt Reference ≠ 0°)  26
1.3 PID – Upright Balance under Disturbances (Tilt Reference = 0)  27
2 Balance Control – RL Agent  29
2.1 RL – Upright Balance (Tilt Reference = 0°)  30
2.2 RL – Upright Balance under Disturbances (Tilt Reference = 0)  32
3 Path Tracking Control PID Controller  35
3.1 PID – Tracking Sinusoidal Path  36
3.2 PID – Tracking Straight Line Path  38
3.3 PID – Tracking Straight Line Path under Disturbances  40
4 Path Tracking – RL Agent  42
4.1 RL Agent – Tracking Sinusoidal Path  43
4.2 RL Agent – Tracking Straight Line Path  46
4.3 RL Agent – Tracking Straight Line under Disturbances  49
5 Comparing the PID controller and the RL agent  50
6 Real Robot Steering Velocity Test  52
Chapter 6 Conclusion and Future Work  54
References  56
                                

[1] K. J. Astrom, R. E. Klein, and A. Lennartsson, “Bicycle dynamics and control: adapted bicycles for education and research,” IEEE Control Systems Magazine, vol. 25, no. 4, pp. 26–47, 2005.

[2] M. Yamakita, A. Utano, and K. Sekiguchi, “Experimental study of automatic control of bicycle with balancer,” in 2006 IEEE/RSJInternational Conference on Intelligent Robots and Systems, pp. 5606–5611, IEEE, 2006.

[3] U. Franke, D. Gavrila, S. Gorzig, F. Lindner, F. Puetzold, and C. Wohler, “Autonomous driving goes downtown,” IEEE Intelligent Systems and their Applications, vol. 13, no. 6, pp. 40–48, 1998.

[4] C. Thorpe, M. Herbert, T. Kanade, and S. Shafer, “Toward autonomous driving: the cmu navlab. i.perception,” IEEE Expert, vol. 6, no. 4, pp. 31–42, 1991.

[5] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning”, Nature, vol. 521, no. 7553, pp. 436–444, 2015.

[6] F. Lambert, “Tesla to release new full selfdriving beta update w/ “fundamental improvements,” wider release could be coming soon,” Electrek, 2020.

[7] N. Sünderhauf, O. Brock, W. Scheirer, R. Hadsell, D. Fox, J. Leitner, B. Upcroft, P. Abbeel, W. Burgard, M. Milford,etal., “The limits and potentials of deep learning for robotics,” The International Journal of Robotics Research, vol. 37, no. 45, pp. 405–420, 2018.

[8] T. P. Lillicrap, J. J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra, “Continuous control with deep reinforcement learning,” arXiv preprint arXiv:1509.02971, 2015.

[9] S. Singhania, I. Kageyama, and V. M. Karanam, “Study on lowspeed stability of a motorcycle,” Applied Sciences, vol. 9, no. 11, p. 2278, 2019.

[10] N. K. Vu and H. Q. Nguyen, “Balancing control of twowheel bicycle problems,” Mathematical Problems inEngineering, vol. 2020, 2020.

[11] Y. Tanaka and T. Murakami, “Self sustaining bicycle robot with steering controller,” in The 8th IEEE International Workshop on Advanced Motion Control,2004.AMC’04., pp. 193–197, IEEE, 2004.

[12] L. X. Wang, J. M. Eklund, and V. Bhalla, “Simulation & road test results on balance and directional control of an autonomous bicycle,” in 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering(CCECE), pp. 1–5, IEEE, 2012.

[13] S. Lee and W. Ham, “Self stabilizing strategy in tracking control of unmanned electric bicycle with mass balance,” in IEEE/RSJ international conference on intelligent robots and systems, vol. 3,pp. 2200–2205, IEEE, 2002.

[14] Y. Kim, H. Kim, and J. Lee, “Stable control of the bicycle robot on a curved path by using a reaction wheel,” Journal of Mechanical Science and Technology, vol. 29, no. 5, pp. 2219–2226, 2015.

[15] A. Sikander and R. Prasad, “Reduced order modelling based control of two wheeled mobile robot,” Journal of Intelligent Manufacturing, vol. 30, no. 3, pp. 1057–1067, 2019.

[16] M. Yamakita and A. Utano, “Automatic control of bicycles with a balancer,” in Proceedings, 2005 IEEE/ASME International Conference on Advanced Intelligent Mechatronics., 2005.

[17] C.F. Huang, Y.C. Tung, and T.J. Yeh, “Balancing control of a robot bicycle with uncertain center of gravity,” in 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 5858–5863,IEEE, 2017.

[18] C.F. Huang, Y.C. Tung, H.T. Lu, and T.J. Yeh, “Balancing control of a bicycleriding humanoid robot with center of gravity estimation,” Advanced Robotics, vol. 32, no. 17, pp. 918–929, 2018.

[19] R. S. Sutton and A. G. Barto, "Reinforcement Learning: An Introduction." MIT press, 2018.

[20] V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, “Playing atari with deep reinforcement learning,” arXiv preprint arXiv:1312.5602, 2013.

[21] J. Peters and S. Schaal, “Policy gradient methods for robotics,” in 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2219–2225, IEEE, 2006.

[22] V. Mnih, A. P. Badia, M. Mirza, A. Graves, T. Lillicrap, T. Harley, D. Silver, and K. Kavukcuoglu, “Asynchronous methods for deep reinforcement learning,” in International Conference on Machine Learning, pp. 1928–1937, 2016.

[23] J. Schulman, S. Levine, P. Abbeel, M. Jordan, and P. Moritz, “Trust region policy optimization,” in International Conference on Machine Learning, pp. 1889–1897, 2015.63

[24] J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv preprint arXiv:1707.06347, 2017.

[25] S. Ruder, “An overview of gradient descent optimization algorithms,” arXiv preprint arXiv:1609.04747, 2016.

[26] G. Klambauer, T. Unterthiner, A. Mayr, and S. Hochreiter, “Selfnormalizing neural networks,” Advances in Neural Information Processing Systems, vol. 30, pp. 971–980, 2017.

簡易檢索 / 詳目顯示

相關論文