| 引用本文: | 赵铭慧,张雪波,郭宪,欧勇盛.基于深度强化学习的双向装配序列规划[J].控制理论与应用,2021,38(12):1901~1910.[点击复制] |
| ZHAO Ming-hui,ZHANG Xue-bo,GUO Xian,OU Yong-sheng.Assembly sequence planning based on deep reinforcement learning[J].Control Theory and Technology,2021,38(12):1901~1910.[点击复制] |
|
| 基于深度强化学习的双向装配序列规划 |
| Assembly sequence planning based on deep reinforcement learning |
| 摘要点击 1941 全文点击 551 投稿时间：2020-08-08 修订日期：2021-04-01 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2021.00516 |
| 2021,38(12):1901-1910 |
| 中文关键词 智能装配 装配序列规划 深度强化学习 Gazebo |
| 英文关键词 intelligent assembly assembly sequence planning deep reinforcement learning Gazebo |
| 基金项目 国家自然科学基金项目(U1613210), 天津市杰出青年科学基金项目(19JCJQJC62100), 天津市自然科学基金项目(19JCYBJC18500), 中央高校基本 科研业务费项目, 广东省机器人与智能系统重点实验室开放基金项目资助. |
|
| 中文摘要 |
| 为了解决复杂装配模型的序列规划问题, 并使算法对任意初始状态具有较高的适应性, 本文提出了一种包
含正向装配以及逆向拆解的一体化双向装配序列规划方法BASPW–DQN. 针对复杂装配模型, 首先进行了一体化装
配序列规划的问题描述与形式化表示; 在此基础上, 引入了课程学习及迁移学习方法, 对包含前向装配和逆向错误
零件拆卸两部分过程的双向装配序列规划方法进行研究. 在所搭建的ROS-Gazebo与TensorFlow相结合的仿真平台
上进行了验证, 测试结果证明此双向网络对于任意初始状态(包括零装配、部分装配、误装配等初始状态)的装配任
务均可以在较少步数内完成, 验证了所提方法对于解决装配序列规划问题的有效性与适应性. |
| 英文摘要 |
| In order to solve the sequence planning problem of complex assembly models and improve the flexibility
of the algorithm to any initial state, this paper proposes an integrated bi-directional assembly sequence planning method
BASPW–DQN. Aiming at the complex assembly model, a bi-directional assembly sequence planning method including
forward assembly and wrong part disassembly process is proposed, on this basis, curriculum learning and transfer learning
methods are introduced to improve the training efficiency and assembly capabilities of the integrated assembly sequence
planning method. And a training platform is developed, which combines the physical simulator Gazebo and deep network
framework TensorFlow. The test results show that the bi-directional network can complete the assembly tasks of general
assembly in any initial state (such as none-assembly, partial assembly and misassembly) in a few steps demonstrating the
effectiveness and flexibility of the proposed method. |
|
|
|
|
|