[1]王睿轶,王秀青,刘万明,等.基于 FPGA 的移动机器人 SNNs 走廊场景分类器[J].计算机技术与发展,2023,33(12):32-40.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 005]
　WANG Rui-yi,WANG Xiu-qing,LIU Wan-ming,et al.Mobile Robots’ SNNs Corridor-scene-classifier Based on FPGA[J].,2023,33(12):32-40.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 005]

点击复制

基于 FPGA 的移动机器人 SNNs 走廊场景分类器()

分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

33

期数:

2023年12期

页码:

32-40

栏目:

嵌入式计算

出版日期:

2023-12-10

文章信息/Info

Title:

Mobile Robots’ SNNs Corridor-scene-classifier Based on FPGA

文章编号:

1673-629X(2023)12-0032-09

作者:

王睿轶¹; 2; 3 ; 王秀青¹; 2; 3 ; 刘万明⁴ ; 王永吉⁵ ; 叶晓雅¹; 2; 3

1. 河北师范大学 计算机与网络空间安全学院,河北 石家庄 050024;

2. 河北省网络与信息安全重点实验室,河北 石家庄 050024;

3. 河北省供应链大数据分析与数据安全工程研究中心,河北 石家庄 050024;

4. 河北师范大学 中燃工学院,河北 石家庄 050024;

5. 中国科学院 软件研究所,北京 100190

Author(s):

WANG Rui-yi1; 2; 3 ; WANG Xiu-qing1; 2; 3 ; LIU Wan-ming4 ; WANG Yong-ji5 ; YE Xiao-ya1; 2; 3

1. School of Computer and Cyber Security,Hebei Normal University,Shijiazhuang 050024,China;

2. Hebei Provincial Key Laboratory of Network & Information Security,Shijiazhuang 050024,China;

3. Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security,Shijiazhuang 050024,China;

4. China Institute of Gas Engineering,Hebei Normal University,Shijiazhuang 050024,China;

5. Institute of Software,Chinese Academy of Sciences,Beijing 100190,China

关键词:

脉冲神经网络; 积分点火神经元模型; 脉冲编码; 现场可编程门阵列; 移动机器人; 超声传感器

Keywords:

Spiking neural networks; integrated-and-fired neuron model; Spiking encoding; field programmable gate array; mobile robot; sonar sensor

分类号:

TP183

DOI:

10. 3969 / j. issn. 1673-629X. 2023. 12. 005

摘要:

神经形态芯片是类脑计算的重要研究内容之一,神经网络的硬件实现是神经形态芯片实现的基础。 具有生物似真性的脉冲神经网络( Spiking Neural Networks,SNNs),通过尖脉冲( Spikes)?

传递时空信息,更适于用硬件实现,是实现类脑计算的主要工具之一。 该文提出一种基于 FPGA 的移动机器人 SNNs 走廊场景分类器:将移动机器人超声传感器信息进行脉冲编码后输入到 SNNs 走廊场景分类器中,通过 FPGA 分类器的脉冲输出模式来判断机器人所处的走廊场景,从而提高机器人的环境感知能力和自主性。 详细讨论了脉冲积分点火神经元模型的 FPGA 实现原理,以及基于此神经元模型的SNNs 走廊场景分类器的硬件实现方案,仿真及实验结果证明了所提基于 FPGA 的移动机器人 SNNs 走廊场景分类器的有效性。 所提走廊场景分类器不受光

照条件的影响,需要的传感器测量信息少,FPGA 硬件资源占有率低( LE 的利用率仅10% ),分类速度快、准确率高,适于实际应用。 该研究不仅可以提高移动机器人的环境感知能力和自主性,而且为硬件实现 SNNs 提供了有益参考。

Abstract:

The neuromorphic-chip is one of the important research aspects of brain-inspired computing,and the hardware implementationof neural networks ( NNs) is the basis of neuromorphic - chip. Spiking neural networks ( SNNs) with biological plausibility, whichconvey temporal and spatial information by spikes,are suitable to be implemented with hardware,and are also?

one of the main tools forbrain-inspired computing. A novel SNNs based mobile robots‘ corridor - scene - classifier implemented by FPGA is proposed. Theultrasonic sensor information?

of the mobile robot is encoded and input into the SNNs corridor scene classifier,and the corridor scene of therobot is judged by the pulse output mode of the FPGA classifier,so as to improve the environment perception ability and autonomy of therobot. The principle of the Approximation - Spiking IAF neuron model and the implementation of the SNNs corridor -?

scene - classifier　based on Approximation-Spiking IAF by FPGA are discussed in detail. The simulation and experimental results validate the effectiveness of the proposed mobile robots’ corridor-scene-classifier based on FPGA and SNNs. Besides the fast processing speed,the classificationresults of the proposed method are accurate and not influenced by lighting conditions,the needed amount of sensor data is small,theFPGA resource-conquer-rate is low ( the utilization rate of LE is only 10% ) ,which is suitable for practical application. Moreover,theproposed corridor classifier can also improve mobile robots’ ability of environmental perception and autonomy,and provides a valuableinput for SNNs implemented by hardware.

常用功能