Self-repairing mobile robotic car using astrocyte-neuron networks
Self-repairing mobile robotic car using astrocyte-neuron networks
复制标题
DOI：
10.1109/ijcnn.2016.7727359
复制
发表时间：
2016-03
期刊：
影响因子：
--
通讯作者：
Junxiu Liu;J. Harkin;L. McDaid;D. Halliday;A. Tyrrell;J. Timmis
中科院分区：
文献类型：
--
作者：
Junxiu Liu;J. Harkin;L. McDaid;D. Halliday;A. Tyrrell;J. Timmis
提出了一种利用星形胶质细胞-神经元网络的自修复机器人。它利用神经元的输出尖峰频率来控制运动速度和机器人的激活。星形胶质细胞-神经元网络的软件模型之前展示了故障的自我检测和自我修复能力。本文利用移动机器人应用演示器来评估星形细胞-神经元网络在基于硬件的机器人小车系统中的容错能力。结果表明，当与神经元相关的突触出现20%或更少的故障时，机器人小车可以维持系统性能，并正确完成向前运动任务。如果80%的突触有故障，系统性能会出现边际退化，但这种退化比相同故障水平下的传统容错技术要小得多。这是第一次星形胶质细胞合并在尖峰神经元内展示了硬件系统的自我修复能力，用于实际应用。
A self-repairing robot utilising a spiking astrocyte-neuron network is presented in this paper. It uses the output spike frequency of neurons to control the motor speed and robot activation. A software model of the astrocyte-neuron network previously demonstrated self-detection of faults and its self-repairing capability. In this paper the application demonstrator of mobile robotics is employed to evaluate the fault-tolerant capabilities of the astrocyte-neuron network when implemented in a hardware-based robotic car system. Results demonstrated that when 20% or less synapses associated with a neuron are faulty, the robot car can maintain system performance and complete the task of forward motion correctly. If 80% synapses are faulty, the system performance shows a marginal degradation, however this degradation is much smaller than that of conventional fault-tolerant techniques under the same levels of faults. This is the first time that astrocyte cells merged within spiking neurons demonstrates a self-repairing capabilities in the hardware system for a real application.