Mechatronic concepts in the design of new multisensory light-weight-robots
Markus Schedl, Bernd Gombert, J. Dietrich
- 发表年份
- 1993
- 引用次数
- 2
摘要
The paper outlines DLR's mechatronic development in the robotics area over the last five years. They aim at designing a new multisensory light weight robot generation in a unified and integral way. All sensors for the multisensory gripper concept are based on a fully modular hard- and software-concept. Sensors and actuators as well show up miniaturized integration of mechanics, electronics and of course microprocessor control. Joint torque based on inductive sensing is combined with different type of gearings: translational ones originally developed for grippers only as well as compact, highly reducing rotational ones. In combination with optimized carbon fibre grid structures and optical information transfer between the joints a new, extremely light-weight type of robot arises. The paper finally proposes a hybrid control concept adding neural net learning features to classical inverse dynamics control.
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