Graspless manipulation with sensor feedback
Yasumichi AIYAMA, Tamio Arai
- Year
- 2002
- Citations
- 8
Abstract
In the robot manipulation field, a dexterous and easy manipulation method which uses the environment around an object is defined as graspless manipulation. In this paper, we first give a definition of "graspless manipulation with a concept of object stability, "gravity closure". There exist several graspless manipulation methods. Since they have different characteristics with the condition of an object, environment and frictional force, we can achieve low cost manipulation as a combination of these methods according to the states of the conditions. Next, we show a need of reactive planning of graspless manipulation with some sensor feedback. The robot senses a step, an angle of inclination, the changing of the coefficient of friction with the force sensor in practice, and the switch from pushing to tumbling. Moreover, to adopt to a down step which cannot be sensed by a force sensor, we introduce visual feedback control and perform an experiment.
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