• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Second ICSC Symposium on Engineering of Intelligent Systems, Jun 27-30, 2000, Scotland, U.K. >A SELF-ORGANIZING NEURAL NETWORK FOR LEARNING AND RECALL OF COMPLEX ROBOT TRAJECTORIES
【24h】

A SELF-ORGANIZING NEURAL NETWORK FOR LEARNING AND RECALL OF COMPLEX ROBOT TRAJECTORIES

机译：用于学习和回忆复杂机器人轨迹的自组织神经网络

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

We propose an unsupervised neural network model to learn and recall complex robot trajectories. Two cases are considered: (1) A single trajectory in which a particular arm configuration may occur more than once, and (2) trajectories sharing states with other ones ― they are said to contain a shared state. Hence, ambiguities occur in both cases during recall of such trajectories. The proposed model consists of two groups of synaptic weights trained by competitive and Hebbian learning laws. They are responsible for encoding spatial and temporal features of the input sequences, respectively. Three mechanisms allow the network to deal with repeated or shared states: local and global context units, neurons disabled to learn, and redundancy. The network produces the current and the next state of the learned sequences and is able to solve ambiguities. The model is simulated over various sets of robot trajectories in order to evaluate learning and recall, trajectory sampling effects and robustness.
机译：我们提出了一种无监督的神经网络模型来学习和回忆复杂的机器人轨迹。考虑了两种情况：（1）一条特定的手臂配置可能发生多次的单一轨迹，以及（2）与其他轨迹共享状态的轨迹-据说它们包含共享状态。因此，在回忆这种轨迹的两种情况下都存在歧义。所提出的模型包括两组通过竞争和赫本学习法训练的突触权重。它们分别负责编码输入序列的空间和时间特征。网络可以通过三种机制来处理重复或共享的状态：局部和全局上下文单元，无法学习的神经元以及冗余。网络产生学习序列的当前状态和下一状态，并且能够解决歧义。该模型在各种机器人轨迹集上进行仿真，以评估学习和记忆，轨迹采样效果和鲁棒性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号