Title :
Machine recognition of human task for man-machine cooperative work
Author :
Tateno, Toshitake ; Ito, Takeshi ; Igoshi, Masanori
Author_Institution :
Graduate Sch. of Mech. Eng., Tokyo Metropolitan Univ., Japan
Abstract :
Because recent products are becoming too complex to operate or maintain by only one worker without special education, an associate system, which advises the worker on what to do, is required. In order to construct the associate system, a recognition method for human task and motion monitoring by using a HMM and an AND/OR graph is proposed. An experimental system is developed, in which a vision device and a force sensing device are used for detecting human motions. As the results of the recognition tests for assembly and disassembly show, we found the system can identify the task about 90% correctly. We confirmed the system can contribute to man-machine cooperative work
Keywords :
assembling; computer vision; force sensors; graph theory; hidden Markov models; image motion analysis; AND/OR graph; assembly; computer vision; disassembly; experimental system; force sensing device; hidden Markov model; human motion detection; human task monitoring; human task recognition; man-machine cooperative work; Assembly systems; Character recognition; Collaborative work; Educational products; Hidden Markov models; Humans; Indium tin oxide; Man machine systems; Mechanical engineering; Systems engineering education;
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-5731-0
DOI :
10.1109/ICSMC.1999.812366
