Data Driven Adaptive Predictive Control for Holonomic Constrained Under-Actuated Biped Robots

被引：60

作者：

Ge, Shuzhi Sam ^{[1
,2
]}

Li, Zhijun ^{[3
]}

Yang, Huayong ^{[4
]}

机构：

[1] Univ Elect Sci & Technol China, Inst Robot, Chengdu 610054, Peoples R China

[2] Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 610054, Peoples R China

[3] Minist Educ China, Key Lab Syst Control & Informat Proc, Shanghai 200240, Peoples R China

[4] Zhejiang Univ, State Key Lab Fluid Power Transmiss & Control, Hangzhou 310027, Zhejiang, Peoples R China

来源：

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY | 2012年 / 20卷 / 03期

基金：

对外科技合作项目（国际科技项目）;

关键词：

Biped robot; support vector regression (SVR); under-actuated mechanical system; UNIVERSAL APPROXIMATION; STABLE WALKING; SUPPORT; SYSTEMS;

D O I：

10.1109/TCST.2011.2145378

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Fundamentally, control system designs are concerned with the flow of signals in the closed loop. In this paper, we are to present the control technique at the next level of abstraction in control system design. We construct a control using implicit function with support vector regression-based data-driven model for the biped, in the presence of parametric and functional dynamics uncertainties. Based on Lyapunov synthesis, we develop decoupled adaptive control based on the model predictive and the data-driven techniques and construct the control directly from online or offline data. The adaptive predictive control mechanisms use the advantage of data-driven technique combined with online parameters estimation strategy in order to achieve an efficient approximation. Simulation results are presented to verify the effectiveness of the proposed control.

引用

页码：787 / 795

页数：9

共 22 条

[1] A Control Approach for Actuated Dynamic Walking in Biped Robots [J].

Braun, David J. ;

Goldfarb, Michael .

IEEE TRANSACTIONS ON ROBOTICS, 2009, 25 (06) :1292-1303

[2] Control of a Biped Robot With Support Vector Regression in Sagittal Plane [J].

Ferreira, Joao P. ;

Crisostomo, Manuel M. ;

Coimbra, A. Paulo ;

Ribeiro, Bernardete .

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2009, 58 (09) :3167-3176

[3] SENSOR-BASED CONTROL OF A 9-LINK BIPED [J].

FURUSHO, J ;

SANO, A .

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 1990, 9 (02) :83-98

[4]

Ge S. S., 2002, STABLE ADAPTIVE NEUR

[5] Neural-network control of nonaffine nonlinear system with zero dynamics by state output feedback [J].

Ge, SS ;

Zhang, J .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (04) :900-918

[6] Asymptotically stable walking for biped robots: Analysis via systems with impulse effects [J].

Grizzle, JW ;

Abba, G ;

Plestan, F .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2001, 46 (01) :51-64

[7] A note on the universal approximation capability of support vector machines [J].

Hammer, B ;

Gersmann, K .

NEURAL PROCESSING LETTERS, 2003, 17 (01) :43-53

[8] Fuzzy neural network approaches for robotic gait synthesis [J].

Juang, JG .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2000, 30 (04) :594-601

[9]

Lee T. H., 1998, Adaptive Neural Network Control of RoboticManipulators, V19

[10] Fuzzy neural networks quadratic stabilization output feedback control for biped robots via H∞ approach [J].

Liu, Z ;

Li, CW .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2003, 33 (01) :67-84

← 1 2 3 →