Robotic hand-eye coordination: from observation to manipulation

Author

Jafari, Shahram ; Jarvis, Ray

Author_Institution

Intelligent Robotics Res. Centre, Monash Univ., Clayton, Vic., Australia

fYear

2004

fDate

5-8 Dec. 2004

Firstpage

20

Lastpage

25

Abstract

In this paper, we present a new hybrid method of performing eye-to-hand coordination and manipulation to produce a working robot named COERSU. The method is an optimized combination of two neuro-fuzzy approaches developed by the authors: direct fuzzy servoing and fuzzy correction. The fuzzy methods are tuned by an adaptive neuro-fuzzy inference system (ANFIS). On the whole, a genetic tuner and two neuro-fuzzy networks contribute to find the final optimum position of the robotic tooltip in order to grasp the target. Experimental results from COERSU in a table-top scenario to manipulate some soft objects (e.g. fruit/egg) also validate the method.

Keywords

data mining; fuzzy neural nets; fuzzy reasoning; genetic algorithms; manipulators; robot vision; stereo image processing; K-nearest neighborhood; adaptive neuro-fuzzy inference system; direct fuzzy servoing; fuzzy correction; genetic algorithm; genetic tuner; robotic hand-eye coordination; visual servoing; Cameras; Fuzzy systems; Genetics; Image edge detection; Intelligent robots; Robot kinematics; Robot vision systems; Stereo vision; Tuners; Visual servoing; Adaptive neuro-fuzzy inference system (ANFIS); Eye-in-hand; Eye-to-hand; Genetic Algorithm; K-nearest neighborhood (K-NN); Visual servoing;

fLanguage

English

Publisher

ieee

Conference_Titel

Hybrid Intelligent Systems, 2004. HIS '04. Fourth International Conference on

Print_ISBN

0-7695-2291-2

Type

conf

DOI

10.1109/ICHIS.2004.82

Filename

1409975