Study of dexterous robotic grasping for deformable objects manipulation
D. Mira, Á.V. Delgado, Carlos M. Mateo, Francisco A. Candelas-Herías, Fernando Torres
- 发表年份
- 2015
- 引用次数
- 11
摘要
Most works in dexterous manipulation consider Force Closure Grasp (FCG), not only for rigid object but also, for flexible ones, though in the second case a force readjustment is also necessary. However, there are situations in which FCG is nonviable. This paper deals with the situation of a flexible object that must be necessarily grasped from one of its sides, taking advantage of its flexibility. This situation is common in packaging processes, or other everyday situations carried out by people. The paper presents first a new solution based on a planner that reproduces the actions of a human hand, aided by a database with knowledge about previous tasks. The paper is focused on describing the first tests done to evaluate the effectiveness of the planner for grasping different basic flexible objects, compared to a human hand.
关键词
相关论文
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