Exploring tactile surface sensors as a gesture input device for intuitive robot programming
Arne Muxfeldt, Jan Niklas Haus, Jingyuan Cheng, Daniel Kubus
- Year
- 2016
- Citations
- 12
Abstract
The lack of efficient and intuitive programming paradigms for industrial manipulators stands in the way of increasing the degree of automation in various industrial manufacturing environments. We approach this lack by exploring tactile surface sensors (TSS) enclosing the links of a manipulator as a gesture input device for intuitive robot programming. First, our low-cost tactile surface sensor is briefly presented. Subsequently, a preliminary gesture set is introduced and feature-based approaches for gesture recognition are addressed. Furthermore, the extraction of relevant parameters from the gestures as well as the integration of gesture input into our skill-based robot control architecture are outlined. Quantitative performance results based on a user study with 12 subjects and a set of 7 gestures show that even with a comparatively low spatial resolution of the sensor (20mm) average accuracies of over 90% can be obtained.
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