一种基于触觉信息的脉冲图注意力残差卷积物体检测算法
DOI:
作者:
作者单位:

1.燕山大学信息科学与工程学院;2.北京信息科技大学自动化学院

作者简介:

通讯作者:

中图分类号:

TP273

基金项目:

国家重点研发计划(2018YFB1308300);国家自然科学基金区域联合基金(U20A20167);北京市自然科学基金(4202026);河北省自然科学基金(F202103079).


An object detection algorithm based on convolution of attention residuals of pulse graph based on tactile information
Author:
Affiliation:

1.School of Information Science and Engineering, Yanshan University;2.School of Automation, Beijing Information Science & Technology University, Beijing

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    触觉传感器(柔性电子皮肤)在机器人进行人机交互和工具操作时发挥重要作用,如何有效利用触觉信息进行物体检测是当前研究的主要瓶颈。本文提出一种脉冲图卷积神经网络SNN-Atten-ResGCN的物体检测算法。首先使用图残差网络ResGCN模型训练触觉时间序列的表征信息,其次通过引入深度学习模型中的注意力机制,拟合触觉数据图形结构的局部特征,然后对重构的触觉图形输入由三个LIF神经元和两个FC全连接层组成的SNN脉冲神经网络训练得到特征向量,最后投票层Vote解码网络特征并检测物体类别。在EvTouch-Objects和EvTouch-Containers两个家庭常见物体触觉数据集上进行对比实验,实验结果表明,本文方法在保证模型迭代效率的同时,对各种不同的家庭工具对象和容器对象的准确率、精度、召回率和F1-score均得到提升。

    Abstract:

    Tactile sensor (flexible electronic skin) plays an important role in robot human-computer interaction and tool operation. How to effectively use tactile information for object detection is the main bottleneck of current research. In this paper, a pulse graph convolution neural network SNN-Atten-ResGCN is proposed for object detection. Firstly, the graph residual network ResGCN model is used to train the representation of tactile time series. Secondly, the attention mechanism in the deep learning model is introduced to fit the local features of the graphic structure of tactile data, Then, the reconstructed tactile graphics are input, and the SNN pulse neural network composed of three LIF neurons and two FC full connection layers is trained to obtain the feature vector. Finally, vote is utilized to decode the network feature components and discriminate object category. Comparative experiments are carried out on the tactile datasets of EvTouch-Objects and EvTouch-Containers. The experimental results show that the proposed method ensures the model iteration efficiency, meanwhile the accuracy, precision, recall rate and F1-score of various household objects and container are improved.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-12-26
  • 最后修改日期:2022-04-27
  • 录用日期:2022-04-27
  • 在线发布日期:
  • 出版日期: