Reinforcement Learning Control for a Robotic Manipulator with Unknown Deadzone

被引：0

作者：

Li, Yanan ^{[1
]}

Xiao, Shengtao ^{[2
]}

Ge, Shuzhi Sam ^{[2
]}

机构：

[1] Agcy Sci Technol & Res, Inst Infocomm Res, Singapore, Singapore

[2] Natl Univ Singapore, Dept Elect & Comp Engn, Singapore, Singapore

来源：

2014 11TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA) | 2014年

关键词：

Reinforcement learning; robot control; neural networks; deadzone; ADAPTIVE NEURAL-CONTROL; NONLINEAR-SYSTEMS; CONTINUOUS-TIME; COMPENSATION; NETWORKS;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, an actor critic neural network control is developed for a robotic manipulator. Both system uncertainties and unknown deadzone are considered in the tracking control design. Stability of the closed-loop system is analyzed via the Lyapunov's direct method. The critic neural network is used to estimate the cost-to-go and the actor neural network is used to make the cost-to-go converge. Simulation studies are conducted to examine the effectiveness of the proposed actor critic neural network control.

引用

页码：593 / 598

页数：6

共 17 条

[1] Reinforcement learning in continuous time and space [J].

Doya, K .

NEURAL COMPUTATION, 2000, 12 (01) :219-245

[2]

Ge S. S., 2013, P CHIN CONTR C CCC C, P2997

[3]

Ge S. S., 1998, Adaptive Neural Network Control of Robotic Manipulators, V19

[4] Adaptive neural control of uncertain MIMO nonlinear systems [J].

Ge, SS ;

Wang, C .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2004, 15 (03) :674-692

[5] Adaptive NN control of uncertain nonlinear pure-feedback systems [J].

Ge, SS ;

Wang, C .

AUTOMATICA, 2002, 38 (04) :671-682

[6] Reinforcement Learning and Adaptive Dynamic Programming for Feedback Control [J].

Lewis, Frank L. ;

Vrabie, Draguna .

IEEE CIRCUITS AND SYSTEMS MAGAZINE, 2009, 9 (03) :32-50

[7] Impedance Learning for Robots Interacting With Unknown Environments [J].

Li, Yanan ;

Ge, Shuzhi Sam .

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2014, 22 (04) :1422-1432

[8] GAUSSIAN NETWORKS FOR DIRECT ADAPTIVE-CONTROL [J].

SANNER, RM ;

SLOTINE, JJE .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (06) :837-863

[9] Deadzone compensation in motion control systems using neural networks [J].

Selmic, RR ;

Lewis, FL .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2000, 45 (04) :602-613

[10]

Selmic RR, 2003, 42ND IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-6, PROCEEDINGS, P4327

← 1 2 →