2A1-E02 Autonomous 3D Object Modeling by a Humanoid Using Optimization Algorithms to Generate Whole-Body Postures Related to the Best Viewpoints
スポンサーリンク
概要
- 論文の詳細を見る
We present our original algorithm to find successive viewpoints around an unknown object in order to build its visual representation. A derivative-free optimization method, NEWUOA, and a gradient-based method, FSQP, are used to generate whole-body postures by taking into account visual features as well as constraints related to the use of a humanoid. We also incorporate a basic sampling of the configuration space to be able to cope with problems of local minima. This method has been tested on simulation with a HRP-2 humanoid robot on different objects varying in size and complexity.
- 一般社団法人日本機械学会の論文
- 2009-05-25
著者
-
Stasse Olivier
Cnrs-lirmm
-
FOISSOTTE Torea
CNRS-LIRMM
-
KHEDDAR Abderrahmane
CNRS-LIRMM
-
Kheddar Abderrahmane
Cnrs-lirmm:cnrs-aist Jrl
-
Foissotte Torea
Cnrs-lirmm:cnrs-aist Jrl
関連論文
- 2A1-E02 Autonomous 3D Object Modeling by a Humanoid Using Optimization Algorithms to Generate Whole-Body Postures Related to the Best Viewpoints
- 2A1-D30 ヒューマノイドの全身運動を利用した物体持ち上げ動作 : 運動量変化を利用する手法の提案