帳號:guest(3.15.206.172)          離開系統
字體大小: 字級放大   字級縮小   預設字形  

詳目顯示

以作者查詢圖書館館藏以作者查詢臺灣博碩士論文系統以作者查詢全國書目
作者(中文):高振晏
作者(外文):Kao, Chen-Yen
論文名稱(中文):基於深度學習之H無窮大規模雙足機器人分散式編隊控制考量外來干擾與耦合效應之影響
論文名稱(外文):Decentralized H∞ Team Formation DNN-based Tracking Control for Large-Scale Biped Robots with External Disturbance and Coupling Effects
指導教授(中文):陳博現
指導教授(外文):Chen, Bor-Sen
口試委員(中文):翁慶昌
李征衛
黃志良
口試委員(外文):WENG, CHING-CHANG
LI, CHENG-WEI
HUANG, CHIH-LIANG
學位類別:碩士
校院名稱:國立清華大學
系所名稱:電機工程學系
學號:108061578
出版年(民國):110
畢業學年度:110
語文別:英文
論文頁數:29
中文關鍵詞:強健性控制分散式編隊控制雙足機器人深度學習HJIE
外文關鍵詞:robust controldecentralized team formation controlbiped robotsdeep learningHJIE
相關次數:
  • 推薦推薦:0
  • 點閱點閱:339
  • 評分評分:*****
  • 下載下載:0
  • 收藏收藏:0
在這項研究中,針對外部干擾和通信耦合下的大型雙足機器人,提出了一種分散的 H∞ 時變隊形跟踪控制。為避免求解大型雙足機器人分佈式H∞團隊編隊跟踪控制的一組非線性偏微分Hamiton Jacobi Issac方程(HJIE),通過Adam學習算法訓練深度神經網絡對每個雙足機器人求解HJIE在團隊中實現分散的H∞團隊編隊跟踪控制設計。在離線訓練階段,利用來自其​​他雙足機器人的最壞情況外部擾動和最壞情況耦合代替真實的外部擾動和耦合,生成雙足機器人下一步訓練的系統狀態,不影響分散的H ∞ 隊形跟踪表現。由於HJIE和雙足機器人系統模型已被用於HJIE嵌入式DNN的訓練,與傳統的圖像大數據驅動設計相比,我們節省了大量的訓練數據和時間來實現分散的H∞團隊編隊跟踪控制設計。分類和語音識別。我們可以證明,所提出的基於 HJIE 嵌入式 DNN 的隊形控制方案在 Adam 學習算法收斂後可以接近理論上的大型雙足機器人分佈式 H∞ 隊形跟踪控制策略。最後,給出了 24 個雙足機器人時變組隊的仿真實例,以驗證所提出的基於分佈式 H∞ DNN 的大型雙足機器人組隊在外部干擾和通信耦合下的組隊跟踪性能。
In this study, a decentralized H∞ time-varying team formation tracking control is proposed to large-scale biped robots under external disturbance and communication coupling. In order to avoid solving a set of nonlinear partial differential Hamiton Jacobi Issac equations (HJIEs) of decentralized H∞ team formation tracking control of large-scale biped robots, a deep neural network is trained by Adam learning algorithm to solve HJIE for each biped robot in team to achieve the decentralized H∞ team formation tracking control design. In the off-line training phase the worst-case external disturbance and worst-case coupling from other biped robots are used to replace real external disturbance and coupling to generate the system state of biped robot for the next training step without influence on the decentralized H∞ team formation tracking performance. Since the HJIE and system model of biped robot have been employed for the training of HJIE-embedded DNN, we save much amount of training data and time to achieve decentralized H∞ team formation tracking control design than the conventional big-data driven designs in image classification and speech recognition. We could prove that the proposed HJIE-embedded DNN-based team formation control scheme can approach the theoretical decentralized H∞ team formation tracking control strategy of large-scale biped robots after the convergence of Adam learning algorithm. Finally, a simulation example of time-varying team formation of 24 biped robots is given to validate the team formation tracking performance of the proposed decentralized H∞ DNN-based team formation of large-scale biped robots under external disturbance and communication couplings.
Introduction (p.1)
PRELIMINARIES AND WALKING BIPED ROBOT MODEL (p.4)
DECENTRALIZED H ∞ TEAM FORMATION TRACKING CONTROL OF LARGE-SCALE BIPED
ROBOTS (p.8)
DECENTRALIZED ROBUST H ∞ LARGE-SCALE WALKING BIPED ROBOT TEAM FORMATION
TRACKING CONTROL DESIGN BASED ON HJIE-EMBEDDED DNN (p.14)
SIMULATION (p.19)
CONCLUSION (p.25)
APPENDIX (p.26)
REFERENCES (p.28)
[1] R. Brooks, “A robust layered control system for a mobile robot,” in IEEE Journal on Robotics and Automation, vol. 2, no. 1, pp.
14-23, March 1986.
[2] T. C. S. Hsia, T. A. Lasky and Z. Guo, “Robust independent joint controller design for industrial robot manipulators,” in IEEE Trans.
on Industrial Electronics, vol. 38, pp. 21-25, Feb. 1991.
[3] Lum, H.K. & Zribi, Mohamed & Soh, Y.C.. “Planning and control of a biped robot,” International Journal of Engineering Science.
37. 1319-1349, 1999
[4] H. F.N. Al-Shuka, B. Corves, W. Zhu, and B. Vanderborght, B. (2016). “Multi-level control of zero-moment point-based humanoid
biped robots: A review.” Robotica, 34(11), 2440-2466.
[5] A. Yongga, “Dynamic humanoid locomotion: Hybrid zero dynamics based gait optimization via direct collocation methods.”, Georgia
Tech Library (http://hdl.handle.net/1853/56249 ), Aug, 2016.
[6] A.S. Hayder & C. Burkhard & V. Bram and W.H. Zhu. “Zero-Moment Point-Based Biped Robot with Different Walking Patterns.”
INT. J. Intelligent Systems and Applications(IJISA). 07. 31-41, Jan, 2015
[7] E. R. Westervelt, J. W. Grizzle and D. E. Koditschek, “Hybrid zero dynamics of planar biped walkers,” in IEEE Trans. on Automatic
Control, vol. 48, no. 1, pp. 42-56, Jan. 2003.
[8] A. D. Ames, K. Galloway, K. Sreenath and J. W. Grizzle, “Rapidly exponentially stabilizing control Lyapunov functions and hybrid
zero dynamics,” in IEEE Trans. on Automatic Control, vol. 59, no. 4, pp. 876-891, April 2014.
[9] J.W. Grizzle, C. Chevallereau, R.W. Sinnet, A.D. Ames, “Models, feedback control, and open problems of 3D bipedal robotic walking”,
Automatica, vol. 50, pp. 1955-1988, Aug. 2014
[10] R. C. Luo and C. C. Chen, “Biped walking trajectory generator based on three-mass with angular momentum model using model
predictive control,” IEEE Trans. Ind. Electron., vol. 63, no. 1, pp. 268–276, Jan. 2016
[11] S. Shimmyo, T. Sato and K. Ohnishi, “Biped walking pattern generation by using preview control based on three-mass model,” IEEE
Trans. Ind. Electron., vol. 60, no. 11, pp. 5137–5147, Nov. 2013.
[12] B.S. Chen, C.-P. Wang, and M.-Y. Lee, “Stochastic robust team tracking control of multi-UAV networked system under Wiener and
Poisson random fl uctuations,” IEEE Trans. Cybern., (to be published : 10.1109/TCYB.2019.2960104) Jan. 2020.
[13] P. Ogren, M. Egerstedt, and X. Hu, “A control Lyapunov function approach to multiagent coordination,” IEEE Trans. Robot. Autom.,
vol. 18, no. 5, pp. 847–851, Oct. 2002.
[14] W. Yu, G. Chen, W. Ren, J. Kurths, and W. X. Zheng, “Distributed higher order consensus protocols in multiagent dynamical systems,”
IEEE Trans. Circuits Syst., vol. 58, no. 8, pp. 1924–1932, Aug. 2011.
[15] B. S. Chen, Y. Y. Tsai and M. Y. Lee, “Robust Decentralized Formation Tracking Control for Stochastic Large-Scale Biped Robot
Team System under External Disturbance and Communication Requirements,” IEEE Trans. on Control of Network Systems, vol. 8, no.
2, pp. 654-666, June 2021.
[16] Wei Ren, “Consensus based formation control strategies for multi-vehicle systems,” 2006 American Control Conference, pp. 6, 2006.
[17] M. F. Santos Rabelo, A. Santos Brand˜ao and M. Sarcinelli-Filho, “Centralized control for an heterogeneous line formation using virtual
structure approach,” 2018 Latin American Robotic Symposium, 2018 Brazilian Symposium on Robotics (SBR) and 2018 Workshop on
Robotics in Education (WRE), pp. 135-140, 2018.
[18] A. S. Brand˜ao, J. P. A. Barbosa, V. Mendoza, M. Sarcinelli-Filho and R. Carelli, “A Multi-Layer Control Scheme for a centralized
UAV formation,” 2014 International Conference on Unmanned Aircraft Systems (ICUAS), pp. 1181-1187, 2014.
[19] M. Y. Lee, B. S. Chen, C. Y. Tsai and C. L. Hwang, “Stochastic H ∞ Robust Decentralized Tracking Control of Large-Scale
Team Formation UAV Network System With Time-Varying Delay and Packet Dropout Under Interconnected Couplings and Wiener
Fluctuations,” IEEE Access, vol. 9, pp. 41976-41997, 2021.
[20] D. Lee, S. P. Viswanathan, L. Holguin, A. K. Sanyal and E. A. Butcher, “Decentralized guidance and control for spacecraft formation
fl ying using virtual leader confi guration,” 2013 American Control Conference, pp. 4826-4831, 2013.30
[21] Y. Watanabe, A. Amiez and P. Chavent, “Fully-autonomous coordinated fl ight of multiple UAVs using decentralized virtual leader
approach,” 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5736-5741, 2013.
[22] A. A. Khuwaja, G. Zheng, Y. Chen, and W. Feng, “Optimum deployment of multiple UAVs for coverage area maximization in the
presence of co-channel interference,” IEEE Access, vol. 7, pp. 85203–85212, 2019.
[23] C. Shen, T.-H. Chang, J. Gong, Y. Zeng, and R. Zhang, “Multi-UAV interference coordination via joint trajectory and power control,”
IEEE Trans. Signal Process., vol. 68, pp. 843–858, Jan. 2020.
[24] B.S. Chen, C.S. Tseng, H.J. Uang, “Mixed H 2 /H ∞ Fuzzy Output Feedback Control Design for Nonlinear Dynamic Systems: An LMI
Approach.” IEEE Trans. Fuzzy Systems, vol. 8. pp. 249 - 265 July, 2000.
[25] W. Zhang & B.S. Chen, “State Feedback H ∞ Control for a Class of Nonlinear Stochastic Systems.” Siam Journal on Control and
Optimization - SIAM. vol. 44. pp. 1973-1991, 2006.
[26] B.S. Chen, C.L. Tsai and D.S. Chen, “Robust H ∞ and mixed H 2 /H ∞ fi lters for equalization designs of nonlinear communication
systems: fuzzy interpolation approach,” in IEEE Trans. on Fuzzy Systems, vol. 11, no. 3, pp. 384-398, June 2003.
[27] B.S. Chen, S. -Y. Hsu and M. -Y. Lee, “Robust Stochastic Observer-Based Attack-Tolerant Missile Guidance Control Design Under
Malicious Actuator and Sensor Attacks,” in IEEE Access, vol. 9, pp. 109652-109670, 2021.
[28] B. S Chen, W. Y. Chen, C. T. Young and Z. Yan,“Noncooperative game strategy in cyber-fi nancial systems with wiener and poisson
random fl uctuations: LMIs-constrained MOEA approach,” IEEE Trans. on Cybern., vol. 48, no. 12, pp. 3323–3336, Dec. 2018.
[29] H. Gao, J. Lam, L. Xie and C. Wang, “New approach to mixed H 2 /H ∞ fi ltering for polytopic discrete-time systems,” in IEEE Trans.
on Signal Processing, vol. 53, no. 8, pp. 3183-3192, Aug. 2005.
[30] B.S. Chen, C.S. Tseng and H.J. Uang, “Robustness design of nonlinear dynamic systems via fuzzy linear control,” in IEEE Trans. on
Fuzzy Systems, vol. 7, no. 5, pp. 571-585, Oct. 1999.
[31] K. Hornik, M. Stinchcombe, H. White, “Multilayer feedforward networks are universal approximators,” Neural Networks, vol 2, pp.
359-366, May 1989.
[32] A. Krizhevsky, I. Sutskever, G.E. Hinton, “Imagenet classifi cation with deep convolutional neural networks.” 2012 Advances in neural
information processing systems, vol. 25, pp. 1097-1105, 2012.
[33] Ronneberger, O., Fischer, P., & Brox, T. “U-net: Convolutional networks for biomedical image segmentation.” In International
Conference on Medical image computing and computer-assisted intervention, pp. 234-241. Springer, Cham, Oct, 2015.
[34] Devlin, J., Ming-Wei Chang, Kenton Lee and Kristina Toutanova. “BERT: Pre-training of Deep Bidirectional Transformers for Language
Understanding.” NAACL (2019).
[35] K. M. Lynch and F. C. Park, “Modern Robotics: Mechanics, Planning,and Control.” Cambridge, U. K.: Cambridge Univ. Press, 2017
[36] S. Boyd and L. Vandenberghe, “Convex Optimization.” Cambridge, U. K.:Cambridge Univ. Press, 2004.
[37] K. Jouili and H. Jerbi, “A Computationally Lyapunov Nonlinear Gain Scheduling Control of Nonlinear Systems with Stability
Guarantees,” 2009 11th International Conference on Computer Modelling and Simulation, pp. 374-379, 2009.
[38] B. Xu, N. Wang, T. Chen, M. Li, “Empirical evaluation of rectifi ed activations in convolutional network,” pp. 1-5, arXiv preprint
arXiv:1505.00853, Nov. 2015.
[39] Ioffe, S., & Szegedy, C. ”Batch normalization: Accelerating deep network training by reducing internal covariate shift.” International
conference on machine learning, pp. 448-456, Jun, 2015.
[40] D. P. Kingma, J. Ba, “Adam: A method for stochastic optimization,” ICLR,San Diego, pp. 1-15, arXiv preprint arXiv: 1412.6980, 2014.
 
 
 
 
第一頁 上一頁 下一頁 最後一頁 top
* *