Title :
Generation of moving task rules from human instructions
Author :
Ogata, Hiroyuki ; Arai, Tamio
Author_Institution :
Labs. of Cyber Solutions, NTT Co., Tokyo, Japan
Abstract :
We present a new approach to generating rules for a position-controlled manipulator to execute an assembly task in an uncertain environment. The rules are generated from a set of human instruction data. Unlike traditional methods of generating such execution rules, our approach does not require either a programmer with deep insight in the task or a large amount of trial-and-error learning by the manipulator. We have implemented our algorithm for a 7-DOF manipulator and verified the feasibility of our approach by computer simulation
Keywords :
assembling; manipulators; path planning; robot programming; 7-DOF manipulator; assembly task; computer simulation; human instruction data; human instructions; moving task rule generation; position-controlled manipulator; trial-and-error learning; uncertain environment; Computer simulation; Humans; Machine learning; Manipulators; Motion planning; Precision engineering; Robot sensing systems; Service robots; Telegraphy; Telephony;
Conference_Titel :
Assembly and Task Planning, 2001, Proceedings of the IEEE International Symposium on
Conference_Location :
Fukuoka
Print_ISBN :
0-7803-7004-X
DOI :
10.1109/ISATP.2001.928981
