| 基于关键点预测的装配机器人工件视觉定位技术 |
| |
| 引用本文： | 倪涛,张泮虹,李文航,赵亚辉,张红彦,翟海阳.基于关键点预测的装配机器人工件视觉定位技术[J].农业机械学报,2022,53(6):443-450. |
| |
| 作者姓名： | 倪涛 张泮虹 李文航 赵亚辉 张红彦 翟海阳 |
| |
| 作者单位： | 1. 燕山大学车辆与能源学院;2. 吉林大学机械与航空航天学院 |
| |
| 基金项目： | 吉林省重点研发计划项目（20200101130GX） |
| |
| 摘 要： | 针对目前装配机器人基于手工的特征检测易受光照条件、背景和遮挡等干扰因素的影响，而基于点云特征检测又依赖模型构建精度，本文采用深度学习的方式，对基于关键点预测的工件视觉定位技术展开研究。首先，采集工件各个角度的深度图像，计算得到工件的位姿信息，选取工件表面的关键点作为数据集。然后，构造工件表面关键点的向量场，与数据集一同进行深度训练，以实现前景点指向关键点的向量场预测。之后，将向量场中各像素指向同一关键点的方向向量每两个划分为一组，取其向量交点生成关键点的假设，并基于RANSAC的投票对所有假设进行评价。使用EPnP求解器计算工件位姿，并生成工件的有向包围盒显示位姿估计结果。最后，通过实验验证了系统估计结果的准确性和鲁棒性。
|
| 关 键 词： | 装配机器人 关键点 预测 工作位姿 深度学习 |
| 收稿时间： | 2021/6/23 0:00:00 |
Visual Positioning Technology of Assembly Robot Workpiece Based on Prediction of Key Points |
| |
| NI Tao,ZHANG Panhong,LI Wenhang,ZHAO Yahui,ZHANG Hongyan,ZHAI Haiyang.Visual Positioning Technology of Assembly Robot Workpiece Based on Prediction of Key Points[J].Transactions of the Chinese Society of Agricultural Machinery,2022,53(6):443-450. |
| |
| Authors: | NI Tao ZHANG Panhong LI Wenhang ZHAO Yahui ZHANG Hongyan ZHAI Haiyang |
| |
| Institution: | Yanshan University;Jilin University |
| |
| Abstract: | Aiming at the problem that the current manual feature detection of assembly robots was susceptible to interference factors such as illumination conditions, background and occlusion, and the feature detection based on point cloud depends on the accuracy of model construction, the method of deep learning was proposed to carry out research on the visual positioning technology of the workpiece based on key point prediction. Firstly, the ArUco pose detection marker and ICP point cloud registration technology were used to construct a set of data for training the pose estimation network model. The depth images from various angles of the workpiece were collected, and the pose information of the workpiece was calculated. The key points on the workpiece surface were selected as the data set. Then the vector field of the key points on the workpiece surface was constructed, and the depth training was carried out to gather with the data set to realize the vector field prediction of the foreground points pointing to the key points. And the direction vectors of each pixel in the vector field pointing to the same key point were divided into two groups, the intersection points of their vectors were taken to generate the hypothesis of the key point, and all the hypotheses were evaluated based on RANSAC voting. The EPnP solver was used to calculate the pose of the workpiece, and the orientation bounding box of the workpiece was generated to display the pose estimation results. Finally, the accuracy and robustness of the estimation results were verified by experiments. |
| |
| Keywords: | assembly robot key points prediction pose of workpiece deep learning |
|
| 点击此处可从《农业机械学报》浏览原始摘要信息 |
| 点击此处可从《农业机械学报》下载免费的PDF全文 |
|
