引用本文: | 崔朝臣,张翔,熊丹,韩伟,黄奕勇.空间软体机械臂的两阶段神经网络控制方法[J].控制理论与应用,2023,40(12):2257~2264.[点击复制] |
CUI Chao-chen,ZHANG Xiang,XIONG Dan,HAN Wei,HUANG Yi-yong.Two-stage neural network control method for space soft manipulato[J].Control Theory and Technology,2023,40(12):2257~2264.[点击复制] |
|
空间软体机械臂的两阶段神经网络控制方法 |
Two-stage neural network control method for space soft manipulato |
摘要点击 743 全文点击 349 投稿时间:2023-05-20 修订日期:2023-11-27 |
查看全文 查看/发表评论 下载PDF阅读器 |
DOI编号 10.7641/CTA.2023.30344 |
2023,40(12):2257-2264 |
中文关键词 在轨服务 软体机械臂建模和控制 两阶段神经网络 Transformer |
英文关键词 on-orbit service modeling and control of soft robotic arms two-stage neural network Transformer |
基金项目 |
|
中文摘要 |
软体机械臂凭借质量轻、价格低、操作灵活等特性在在轨服务任务中具有巨大应用前景. 然而, 针对软体
机械臂的逆运动学建模和控制仍是一个具有挑战性的问题. 作为一种替代方案, 采用数据驱动的方法对软体机械臂
数值模型进行学习取得了一定成果. 本文在前人研究的基础上, 提出一种端到端的两阶段神经网络软体机械臂控制
思想和异步Transformer执行策略. 文章通过与单阶段神经网络、传统的BP、LSTM等构建的两阶段方法进行对比,
结果表明: 本文方法具有更高的控制精度. 最后, 利用软体机械臂实物进行抓取实验, 验证了本文方法的可行性. |
英文摘要 |
Soft robotic arms, with their characteristics of lightweight, low cost, and flexible operation, hold tremendous
potential for on-orbit servicing tasks. However, the inverse kinematics modeling and control of soft robotic arms remain
challenging. As an alternative solution, the application of data-driven methods to learn numerical models of soft robotic
arms has shown some success. Building upon previous research, this paper proposes an end-to-end two-stage neural
network control approach and an asynchronous Transformer execution strategy for soft robotic arms. Comparative analysis
with single-stage neural networks, traditional backpropagation (BP), long short-term memory (LSTM), and other two-stage
methods from prior studies demonstrates that the approach presented in this paper achieves higher control precision. Finally,
practical grasping experiments with a physical soft robotic arm validate the feasibility of the proposed method. |
|
|
|
|
|