Precision grasp planning based on Fast Marching Square
David A Lvarez, Alejandro Lumbier, Javier V. Gómez, Santiago Garrido, Luís Moreno
- 发表年份
- 2013
- 引用次数
- 2
摘要
This paper presents a novel methodology for planning the movements of a robotic hand when a precision grasp wants to be performed. This approach is based on the standard Fast Marching Square (FM2) path planning method recently introduced for robot formations. A three-finger kinematic chain is consider as a robot formation to perform simulations. In order to achieve a precision grasp, the task is divided into two phases. In the first one, the hand has to move towards the object to be grasped and stops at a position from which the grasping points can be reached by the fingers of the hand. In the second one, given the contact points for a precision grasp, the movements of the fingers must be planned so that those points are reached by the corresponding fingertips. In both cases, the path planning method used is FM2, so smooth and fast paths are ensured due to the characteristics of FM2. In each phase, different control strategies for robot formations are used. The changes in the geometry of the formations are based on the velocities map calculated in FM2, ensuring collision avoidance and speeding up the grasping phase. Simulation results show the usefulness of this novel application of the method thanks to a good performance of the chosen planning strategy.
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