A minimum invasive strategy to guarantee safety under unexpected unintentional human-robot contact
Yiannis Koveos, George A. Rovithakis, Ioannis Agriomallos, Stefanos Doltsinis
- 发表年份
- 2017
- 引用次数
- 2
摘要
The problem of designing an active robot reaction scheme to increase safety against unexpected, unintentional robot contacts with a human or its environment, is considered in this work. Its main functionalities are a) the regulation of the interaction force profile within acceptable/safe boundaries and b) the prevention of undesirable after-contact collisions. The developed methodology is model-free and operates at the high level of reference trajectory determination, producing bounded and sufficiently smooth modifications of the nominal reference, leaving intact the embedded low-level, robot position controller. It is underlined that the proposed minimal invasive solution, is evaluated via experiments performed on a KUKA LWR4+ robotic manipulator equipped with a Shadow Hand-Lite having optoforce sensors attached at its fingertips.
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