Spiking Neurons Ensemble for Movement Generation in Dynamically Changing Environments

Spiking Neurons Ensemble for Movement Generation in Dynamically Changing Environments
复制标题

用于在动态变化的环境中生成运动的尖峰神经元集合

DOI:
10.1109/iros45743.2020.9340721
复制
发表时间:
2020
期刊:
Conference: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
影响因子:
--
通讯作者:
Kuniyoshi Yasuo
Kuniyoshi Yasuo
中科院分区:
--
文献类型:
--
作者:
Favier Kaname;Yonekura Shogo;Kuniyoshi Yasuo

文献摘要

参考文献

相似文献

尖峰神经元可能发挥更大的作用,而不仅仅是作为一个有效的信号传递器。几项研究已经证明了如何使用尖峰神经元网络产生运动。然而,尖峰神经网络的复杂性使得它们的实现变得困难,并且在机器人技术中使用尖峰神经元在很大程度上仍然不切实际。在本文中,我们表明,增加一个单一的尖峰神经元层,可以帮助提高性能的稳定任务,在动态变化的环境。在一维倒立摆稳定控制任务中,脉冲神经元似乎扩展了控制器的可用参数空间。在3-D空间中使用机器人手臂,额外的尖峰神经元层足以提高倒立摆稳定任务的性能高达30%。我们希望这种技术可以提高大多数稳定任务的性能,但也可以提高基本相似的任务,如达到任务和姿态控制。我们还期望当控制参数的最佳调整很困难时,例如当环境不可预测和动态时,这一层的效果最大。
Spiking neurons might play a larger role than simply as an efficient signal transmitter. Several studies have demonstrated how movements can be generated using networks of spiking neurons. However, the complexity of spiking neural networks makes their implementation difficult, and the use of spiking neurons in robotics has remained largely impractical. In this paper, we show that the addition of a single layer of spiking neurons can help improve performance on stabilization tasks in dynamically changing environments. In a one-dimensional inverted pendulum stabilization task, the spiking neurons seem to expand the space of usable parameters of the controller. Using a robot arm in 3-D space, the additional layer of spiking neurons suffices to improve performance up to 30% on an inverted pendulum stabilization task. We expect this technique to enhance performance in most stabilization tasks but also tasks that are essentially similar such as reaching tasks and posture control. We also expect the effects of this layer to be greatest when the optimal tuning of control parameters is difficult, such as when the environment is unpredictable and dynamic.
DOI: --
发表时间: 2007-11
期刊: Bulletin of the Society for Science on Form
影响因子: --
作者:
山田 祐;平田 隆幸
通讯作者: 山田 祐;平田 隆幸
尖峰诱导排序:随机神经尖峰为感觉运动系统提供即时适应性
DOI: 10.1073/pnas.1819707117
发表时间: 2020
期刊: Proceedings of the National Academy of Sciences
影响因子: --
作者:
Yonekura Shogo;Kuniyoshi Yasuo
通讯作者: Kuniyoshi Yasuo
DOI: 10.1371/journal.pcbi.1005507
发表时间: 2017-04
影响因子: 4.3
作者:
Schwalger T;Deger M;Gerstner W
通讯作者: Gerstner W
DOI: 10.1080/14786440809463763
发表时间: 1908
期刊: Philosophical Magazine Series 1
影响因子: --
作者:
A. Stephenson
通讯作者: A. Stephenson