SIMULATING RUBBER ACTUATOR IN PICTURE ANALYSIS WITH NEURAL NETWORK
|
Accession number;04A0171213
|
| Title;SIMULATING RUBBER ACTUATOR IN PICTURE ANALYSIS WITH NEURAL NETWORK |
| Author;
OHNUMA M
(Yokohama National Univ., Yokohama, Jpn)
HONDA H
(Yokohama National Univ., Yokohama, Jpn)
NAGAO T
(Yokohama National Univ., Yokohama, Jpn)
|
Journal Title;IEIC Technical Report (Institute of Electronics, Information and Communication Engineers)
|
Journal Code:S0532B
|
ISSN:0913-5685
|
|
VOL.103;NO.539(IE2003 148-162);PAGE.25-28(2004)
|
| Figure&Table&Reference;FIG.8, REF.2 |
| Pub. Country;Japan |
| Language;English |
| Abstract;Rubber Actuators are structural actuators which operates the mechanism by inflating a rubber tube and a fiber bag with compressed air. This feature is soft like the muscles of a living thing. Robots that operate in close proximity to human beings such as care or pet robots have been studied recently. We believe rubber actuators are the sources of power with optimal features for these robots. The advantages are lightness, softness and suppleness. Power to generate is 2000 times larger than its own weight. Because it is made of rubber and the fiber, it is soft. Even if someone collides with the robot, the actuator will absorb the shock because it is soft and full of air. We intend to achieve a high degree of accuracy by using picture analysis on the simulation, inputting the data from a real rubber actuator and predicting the next operation. (author abst.) |
|
|
|
Related Articles;
|
|
