Towards Learning Inverse Kinematics with a Neural Network Based Tracking Controller

被引：0

作者：

Waegeman, Tim ^{[1
]}

Schrauwen, Benjamin ^{[1
]}

机构：

[1] Univ Ghent, Dept Elect & Informat Syst, B-9000 Ghent, Belgium

来源：

NEURAL INFORMATION PROCESSING, PT III | 2011年 / 7064卷

关键词：

Adaptive control; Feedback control; Inverse kinematics; Neural network (NN); Reservoir computing (RC);

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Learning an inverse kinematic model of a robot is a well studied subject. However, achieving this without information about the geometric characteristics of the robot; is less investigated. In this work, a novel control approach is presented based on a recurrent neural network. Without any prior knowledge about the robot, this control strategy learns to control the iCub's robot arm online by solving the inverse kinematic problem in its control region. Because of its exploration strategy the robot starts to learn by generating and observing random motor behavior. The modulation and generalization capabilities of this approach are investigated as well.

引用

页码：441 / 448

页数：8

共 12 条

[1]

D'Souza A, 2001, IROS 2001: PROCEEDINGS OF THE 2001 IEEE/RJS INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, P298, DOI 10.1109/IROS.2001.973374

[2] Style-based inverse kinematics [J].

Grochow, K ;

Martin, SL ;

Hertzmann, A ;

Popovic, Z .

ACM TRANSACTIONS ON GRAPHICS, 2004, 23 (03) :522-531

[3]

Guez A., 1988, IEEE International Conference on Neural Networks (IEEE Cat. No.88CH2632-8), P617, DOI 10.1109/ICNN.1988.23979

[4]

Jaeger H., 2002, Patent Application, Patent No. [WO 2002/031764 A2, 2002031764]

[5] Optimization and applications of echo state networks with leaky-integrator neurons [J].

Jaegera, Herbert ;

Lukosevicius, Mantas ;

Popovici, Dan ;

Siewert, Udo .

NEURAL NETWORKS, 2007, 20 (03) :335-352

[6]

Metta G., 2008, P 8 WORKSHOP PERFORM, P50, DOI [10.1145/1774674.1774683, DOI 10.1145/1774674.1774683]

[7]

Neumann K, 2010, LECT NOTES ARTIF INT, V6226, P478, DOI 10.1007/978-3-642-15193-4_45

[8]

Peters J., 2006, P ROB SCI SYST RSS

[9]

Reinhart R., 2010, 9 IEEE RAS INT C HUM, P323

[10]

Schrauwen B., 2007, EUROPEAN S ARTIFICIA, P471

← 1 2 →