Loading [MathJax]/extensions/TeX/cellcolor_ieee.js
Optimizing motion primitives to make symbolic models more predictive | IEEE Conference Publication | IEEE Xplore

Optimizing motion primitives to make symbolic models more predictive


Abstract:

Solving complex robot manipulation tasks requires to combine motion generation on the geometric level with planning on a symbolic level. On both levels robotics research ...Show More

Abstract:

Solving complex robot manipulation tasks requires to combine motion generation on the geometric level with planning on a symbolic level. On both levels robotics research has developed a variety of mature methodologies, including geometric motion planning and motion primitive learning on the motor level as well as logic reasoning and relational Reinforcement Learning methods on the symbolic level. However, their robust integration remains a great challenge. In this paper we approach one aspect of this integration by optimizing the motion primitives on the geometric level to be as consistent as possible with their symbolic predictions. The so optimized motion primitives increase the probability of a “successful” motion-meaning that the symbolic prediction was indeed achieved. Conversely, using these optimized motion primitives to collect new data about the effects of actions the learnt symbolic rules becomes more predictive and deterministic.
Date of Conference: 06-10 May 2013
Date Added to IEEE Xplore: 17 October 2013
ISBN Information:
Print ISSN: 1050-4729
Conference Location: Karlsruhe, Germany

References

References is not available for this document.