Shaking eases Object Category Acquisition: Experiments with a Robot Arm
Shinya Takamuku, Koh Hosoda, Minoru Asada, Jst Erato
- Year
- 2007
- Citations
- 9
Abstract
This paper introduces a synthetic study which investigates the role of shaking behav-ior in object category acquisition. By shaking objects with several holding positions and ob-taining the amplitude spectrums of the audi-tory signal, a robot with poor control ability can acquire object categories such as rigid ob-jects, paper materials, and PET bottles with water. The result indicates the possiblity that dynamic touch is more e®ective for categoriza-tion than static touch such as grasping since they provide the agent with the information of the whole object enabling them to acquire object categories independent of size, shape, and contact condition. 1.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002