Action-Driven Perception for a Humanoid
Action-Driven Perception for a Humanoid
复制标题
人形机器人的行动驱动感知
DOI：
10.1007/978-3-642-36907-0_6
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Wermter
中科院分区：
文献类型：
--
作者：
Kleesiek;Wermter
We present active object categorization experiments with a real humanoid robot. For this purpose, the training algorithm of a recurrent neural network with parametric bias has been extended with adaptive learning rates. This modification leads to an increase in training speed. Using this new training algorithm we conducted three experiments aiming at object categorization. While holding different objects in its hand, the robot executes a motor sequence that induces multi-modal sensory changes. During learning, these high-dimensional perceptions are ‘engraved’ in the network. Simultaneously, low-dimensional PB values emerge unsupervised. The geometrical relation of these PB vectors can then be exploited to infer relations between the original high dimensional time series characterizing different objects. Even sensations belonging to unknown objects can be discriminated from known (learned) ones and kept apart from each other reliably. Additionally, we show that the network tolerates noisy sensory signals very well.
登录
查看更多内容
动态循环网络
DOI：
--
发表时间：
2001
期刊：
影响因子：
--
作者：
J. Kolen;S. C. Kremer
通讯作者：
S. C. Kremer
DOI：
10.1016/j.neunet.2004.05.007
发表时间：
2004-10
期刊：
Neural networks : the official journal of the International Neural Network Society
影响因子：
--
作者：
J. Tani;Masato Ito;Y. Sugita
通讯作者：
J. Tani;Masato Ito;Y. Sugita
影响因子：
64.8
作者：
DILL, M;WOLF, R;HEISENBERG, M
通讯作者：
HEISENBERG, M
具有镜像特性的 RNPB 网络中动作序列的泛化
DOI：
--
发表时间：
2009
期刊：
The European Symposium on Artificial Neural Networks
影响因子：
--
作者：
R. Cuijpers;Floran Stuijt;I. Sprinkhuizen
通讯作者：
I. Sprinkhuizen
DOI：
--
发表时间：
2012
期刊：
International Conference on Agents and Artificial Intelligence
影响因子：
--
作者：
Jens Kleesiek;S. Badde;S. Wermter;A. Engel
通讯作者：
A. Engel