arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1407.1460cs.RO
收藏

双向运动检测:认知机器人感知的神经智能模型

Bi-directioal Motion Detection: A Neural Intelligent Model For Perception of Cognitive Robots

K. N. Toosi University of Technology(卡托斯理工大学)

Matin Macktoobian

摘要:

本文提出了一种基于脉冲神经网络模型的新的神经元电路,用于检测认知机器人周围漫游的动态物体的运动方向。我们的新方法在双向运动检测中的能力归功于所提出的电路的对称配置。随着对神经元网络(如癫痫)中阻滞问题处理的重视,兴奋性和抑制性刺激的安装也被考虑在内。在PIONEER认知机器人上应用上述策略的研究表明,该策略导致感觉网络中的潜在水平的缓解。此外,对电路的固有延迟的研究表明,不仅可以获得显着的开关速率,但与其他高速电路的高效耦合。

英文摘要:

In this paper, a new neuronal circuit, based on the spiking neuronal network model, is proposed in order to detect the movement direction of dynamic objects wandering around cognitive robots. Capability of our new approach in bi-directional movement detection is beholden to its symmetric configuration of the proposed circuit. With due attention to magnificence of handling of blocking problems in neuronal networks such as epilepsy, mounting both excitatory and inhibitory stimuli has been taken into account. Investigations upon applied implementation of aforementioned strategy on PIONEER cognitive robot reveals that the strategy leads to alleviation of potential level in the sensory networks. Furthermore, investigation on intrinsic delay of the circuit reveals not only the noticeable switching rate which could be acquired but the high-efficient coupling of the circuit with the other high-speed ones.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑