A Decision Method for Placement of Tactile Elements on a Sensor Glove for the Recognition of Grasp Types
Authors:
- Kouji MurakamiKMKouji Murakami
- Kazuya MatsuoKMKazuya Matsuo
- Tsutomu HasegawaTHTsutomu Hasegawa
- Ryo KurazumeRKRyo Kurazume
- 19 June 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 15 (1) , 157-162
Abstract
We describe a decision method for effective placement of tactile elements for grasp-type recognition. Not only does the placement decided by our method require a small number of tactile elements, it also achieves recognition performance as high as placements consisting of many elements. The placement decided by the method is evaluated through experiments involving the recognition of grasp type from the two types of grasp taxonomy defined by Cutkosky and Kamakura. The proposed method is extended by applying a decision tree pruning. The pruning is useful for reducing the number of selected tactile elements without badly dropping the recognition rate.Keywords
This publication has 28 references indexed in Scilit:
- Robust trajectory learning and approximation for robot programming by demonstrationRobotics and Autonomous Systems, 2006
- Dexterous anthropomorphic robot hand with distributed tactile sensor: Gifu hand IIIEEE/ASME Transactions on Mechatronics, 2002
- Hands for dexterous manipulation and robust grasping: a difficult road toward simplicityIEEE Transactions on Robotics and Automation, 2000
- Slip detection and control using tactile and force sensorsIEEE/ASME Transactions on Mechatronics, 2000
- 1-ms sensory-motor fusion systemIEEE/ASME Transactions on Mechatronics, 2000
- Toward automatic robot instruction from perception-mapping human grasps to manipulator graspsIEEE Transactions on Robotics and Automation, 1997
- Toward an assembly plan from observation. I. Task recognition with polyhedral objectsIEEE Transactions on Robotics and Automation, 1994
- Learning by watching: extracting reusable task knowledge from visual observation of human performanceIEEE Transactions on Robotics and Automation, 1994
- On grasp choice, grasp models, and the design of hands for manufacturing tasksIEEE Transactions on Robotics and Automation, 1989
- Spatial properties of the population of mechanoreceptive units in the glabrous skin of the human handBrain Research, 1980