Learning to generate articulated behavior through the bottom-up and the top-down interaction processes
Learning to generate articulated behavior through the bottom-up and the top-down interaction processes
复制标题
学习通过自下而上和自上而下的交互过程生成明确的行为
DOI：
10.1016/s0893-6080(02)00214-9
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
J. Tani
中科院分区：
文献类型：
--
作者：
J. Tani
提出了一种新的用于感觉-运动学习和行为生成的层次神经网络结构。两层正演神经网络在不同的时间尺度上运行，两层网络之间在自底向上和自顶向下方向上允许参数交互。最后，利用装备视觉系统的真实机械臂进行了行为学习和生成实验，验证了模型的正确性。学习实验结果表明，行为模式的学习是由低级行为原语的自组织和高级行为原语的顺序组合来完成的。结果与Pawelzik等人的先前工作形成对比。[神经计算，8 (1996)340]，Tani和Nolfi[从动物到动物，1998]，以及Wolpert和Kawato[神经网络11(1998)1317]，在本方案中，原语以分布式方式在网络中表示，而在先前的工作中，原语被定位在网络中的特定模块中。进一步的在线规划实验表明，该行为可以在真实环境噪声的背景下鲁棒地生成，并且可以根据环境的变化灵活地修改行为计划。结论是，自下而上的回忆过去过程和自上而下的预测未来过程之间的相互作用使情境行为既稳健又灵活。
A novel hierarchical neural network architecture for sensory-motor learning and behavior generation is proposed. Two levels of forward model neural networks are operated on different time scales while parametric interactions are allowed between the two network levels in the bottom-up and top-down directions. The models are examined through experiments of behavior learning and generation using a real robot arm equipped with a vision system. The results of the learning experiments showed that the behavioral patterns are learned by self-organizing the behavioral primitives in the lower level and combining the primitives sequentially in the higher level. The results contrast with prior work by Pawelzik et al. [Neural Comput. 8 (1996) 340], Tani and Nolfi [From animals to animats, 1998], and Wolpert and Kawato [Neural Networks 11 (1998) 1317] in that the primitives are represented in a distributed manner in the network in the present scheme whereas, in the prior work, the primitives were localized in specific modules in the network. Further experiments of on-line planning showed that the behavior could be generated robustly against a background of real world noise while the behavior plans could be modified flexibly in response to changes in the environment. It is concluded that the interaction between the bottom-up process of recalling the past and the top-down process of predicting the future enables both robust and flexible situated behavior.