DocumentCode :
2415001
Title :
A scripting-based approach to robot behavior engineering using hierarchical generators
Author :
De Haas, Thijs Jeffry ; Laue, Tim ; Röfer, Thomas
Author_Institution :
Dept. of Math. & Comput. Sci., Univ. Bremen, Bremen, Germany
fYear :
2012
fDate :
14-18 May 2012
Firstpage :
4736
Lastpage :
4741
Abstract :
When developing software for autonomous robots, the aspect of behavior engineering is, among tasks such as sensing, state estimation, and motion control, of major importance. Current solutions range from basic behavior-based approaches to sophisticated reasoning systems, in each case depending on the complexity of the robot´s task as well as the available amount of computing time. In this paper, we present a behavior specification language, which is called b-script, to describe hierarchical agent behaviors using the programming concept of generators. We show that this is a convenient approach to realize complex robot behaviors in an intuitive and clean way that can be used in large-scale. Furthermore, the actual implementation of this language is in particular suited to be used on resource-restricted embedded systems. This is shown in different examples of a Nao robot in a robot soccer scenario.
Keywords :
authoring systems; computational complexity; embedded systems; inference mechanisms; motion control; robots; state estimation; Nao robot; autonomous robots; b-script; behavior-based approaches; complex robot behaviors; hierarchical generators; motion control; reasoning systems; resource-restricted embedded systems; robot behavior engineering; robot soccer; robot task complexity; scripting-based approach; state estimation; Context; Generators; Programming; Robot sensing systems; Runtime; Software;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation (ICRA), 2012 IEEE International Conference on
Conference_Location :
Saint Paul, MN
ISSN :
1050-4729
Print_ISBN :
978-1-4673-1403-9
Electronic_ISBN :
1050-4729
Type :
conf
DOI :
10.1109/ICRA.2012.6225038
Filename :
6225038
Link To Document :
بازگشت