The evolution of neural network controllers for the targeted swing of cockroach-like robot

Author

Fife, A. ; Laksanacharoen, S. ; Quinn, R.D. ; Beer, R.D. ; Ritzmann, R.E.

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., Case Western Reserve Univ., Cleveland, OH, USA

Volume

1

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

929

Lastpage

933

Abstract

In this work, agents are evolved to control the locomotion of legged robots. The work has been done on a 5-DOF simulated cockroach robot leg powered by artificial muscles known as braided pneumatic actuators. The problem was addressed in making a targeted swing movement from a number of possible initial leg configurations. The agents are evolved to successfully compensate for these differences and navigate obstacles in a robust swing

Keywords

actuators; collision avoidance; genetic algorithms; legged locomotion; motion control; neurocontrollers; pneumatic control equipment; recurrent neural nets; robot dynamics; software agents; artificial muscles; braided pneumatic actuators; continuous-time neural network; genetic algorithms; legged locomotion; mobile robots; neurocontrol; recurrent neural network; simulated cockroach robot; software agents; swing movement; Evolution (biology); Leg; Legged locomotion; Mechanical engineering; Mobile robots; Navigation; Neural networks; Robot control; Robust control; Weight control;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1005599

Filename

1005599