Adding diagnostics to intelligent robot systems

Author

Chandrababu, Sneha ; Christensen, Henrik I.

Author_Institution

Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA

fYear

2009

fDate

10-15 Oct. 2009

Firstpage

3961

Lastpage

3967

Abstract

Robot systems are increasing in complexity. Trying to diagnose a robot that is non-functional or exhibiting suboptimal performance can be a major challenge. A framework for plug-n-play addition of diagnostics to modules in an object oriented software framework is presented. The methods for modeling of system modules, their transition to a Bayesian model and final implementation are described. The methodology is exemplified for a mobile manipulation system and experimental results are presented.

Keywords

belief networks; control engineering computing; industrial robots; intelligent robots; object-oriented programming; Bayesian network; industrial robot; intelligent robot; mobile manipulation; nonfunctional robot; object oriented software; plug-n-play; robot diagnosis; robot system; suboptimal performance; system module; Bayesian methods; Decision trees; Diagnostic expert systems; Expert systems; Intelligent networks; Intelligent robots; Knowledge based systems; Object oriented modeling; Printers; USA Councils; Bayesian network; Diagnostics; Intelligent Robotics; Quantitative Modeling; Troubleshooting;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on

Conference_Location

St. Louis, MO

Print_ISBN

978-1-4244-3803-7

Electronic_ISBN

978-1-4244-3804-4

Type

conf

DOI

10.1109/IROS.2009.5354626

Filename

5354626