CPG Driven RBF Network Control with Reinforcement Learning for Gait Optimization of a Dung Beetle-Like Robot

被引：19

作者：

Pitchai, Matheshwaran ^{[1
]}

Xiong, Xiaofeng ^{[1
]}

Thor, Mathias ^{[1
]}

Billeschou, Peter ^{[1
]}

Mailander, Peter Lukas ^{[2
]}

Leung, Binggwong ^{[3
]}

Kulvicius, Tomas ^{[2
]}

Manoonpong, Poramate ^{[1
,3
]}

机构：

[1] Univ Southern Denmark, Embodied AI & Neurorobot Lab, Ctr BioRobot, Maersk McKinney Moller Inst, Odense M, Denmark

[2] Univ Goettingen, Dept Computat Neurosci, Gottingen, Germany

[3] Vidyasirimedhi Inst Sci & Technol, Bioinspired Robot & Neural Engn Lab, Sch Informat Sci & Technol, Rayong, Thailand

来源：

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: THEORETICAL NEURAL COMPUTATION, PT I | 2019年 / 11727卷

基金：

欧盟地平线“2020”;

关键词：

Brain inspired computing; Reinforcement learning; Artificial neural networks; CENTRAL PATTERN GENERATORS; LOCOMOTION;

D O I：

10.1007/978-3-030-30487-4_53

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we employ a central pattern generator (CPG) driven radial basis function network (RBFN) based controller to learn optimized locomotion for a complex dung beetle-like robot using reinforcement learning approach called "Policy Improvement with Path Integrals (PI2)". Our CPG driven RBFN controller is inspired by rhythmic dynamic movement primitives (DMPs). The controller can be also seen as an extension to a traditional CPG controller, which usually controls only the frequency of the motor patterns but not the shape. Our controller uses the CPG to control the frequency while the RBFN takes care of the shape of the motor patterns. In this paper, we only focus on the shape of the motor patterns and optimize those with respect to walking speed and energy efficiency. As a result, the robot can travel faster and consume less power than using only the CPG controller.

引用

页码：698 / 710

页数：13

共 15 条

[11]

Pasemann F, 2003, LECT NOTES COMPUT SC, V2686, P144

[12] Programmable central pattern generators: an application to biped locomotion control [J].

Righetti, Ludovic ;

Ijspeert, Auke Jan .

2006 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-10, 2006, :1585-+

[13]

Stulp Freek, 2011, 2011 11th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2011), P231, DOI 10.1109/Humanoids.2011.6100841

[14]

Stulp Freek, 2013, Paladyn, Journal of Behavioral Robotics, V4, P49

[15] Reinforcement Learning of Motor Skills in High Dimensions: A Path Integral Approach [J].

Theodorou, Evangelos ;

Buchli, Jonas ;

Schaal, Stefan .

2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2010, :2397-2403

← 1 2 →