| 引用本文: | 邹双全,吕跃勇,管清华,刘立武,马广富.采用SOM算法的软体机械臂三维形状实时感知[J].哈尔滨工业大学学报,2023,55(4):8.DOI:10.11918/202112044 |
| ZOU Shuangquan,LYU Yueyong,GUAN Qinghua,LIU Liwu,MA Guangfu.Real-time 3D shape recognition for soft manipulator based on SOM algorithm[J].Journal of Harbin Institute of Technology,2023,55(4):8.DOI:10.11918/202112044 |
|
| 摘要: |
| 为实现软体机械臂精确的三维形状实时估计,奠定变形控制与应用的基础性工作,针对三段式软体机械臂,提出了一种基于自组织映射（Self-organizing map,SOM）算法的三维空间形状实时感知方法。首先,对ZED双目相机捕捉到的左、右图像帧进行图像预处理,得到左、右二值图像,并实时提取软体机械臂的二维轮廓数据。然后,采用SOM算法对轮廓数据进行聚类,有序得到软体机械臂二维中心线的多个骨干点,并与K均值,高斯混合模型以及细化3种中心线提取算法进行了对比研究,进一步表明SOM算法更适用于解决软体机械臂复杂形状的中心线辨识。最后,通过基于双目视差的三角测距模型完成软体机械臂的三维形状重构。该算法还采用数据降采样、SOM参数优化等方法,提高算法框架的实时性能。针对软体机械臂连续形变过程,进行了实时形状传感实验和对比验证实验。实验结果表明,该算法具有较高的形状感知精度和较好的实时跟踪效果。不仅如此,与其他文献中提出的形状检测算法相比,该算法也具有较好的性能。 |
| 关键词: 软体机械臂 形状感知 自组织映射（SOM）算法 三角测距 双目视觉 |
| DOI：10.11918/202112044 |
| 分类号:TP242.6 |
| 文献标识码:A |
| 基金项目:国家重点研发计划(2020YFB1506702)；空间智能控制技术实验室开放基金(HTKJ2020KL502014) |
|
| Real-time 3D shape recognition for soft manipulator based on SOM algorithm |
|
ZOU Shuangquan1,LYU Yueyong1,GUAN Qinghua2,LIU Liwu2,MA Guangfu1
|
|
(1.School of Astronautics, Harbin Institute of Technology, Harbin 150001, China; 2.Institute of Composite Materials and Structures, Harbin Institute of Technology, Harbin 150001, China）
|
| Abstract: |
| To realize the accurate 3D shape real-time estimation of soft manipulator and lay the foundation for deformation control and application, a real-time 3D shape recognition method based on the SOM algorithm is proposed for three-section soft manipulator. Firstly, the left and right frame data captured by ZED binocular camera are preprocessed to obtain the left and right binary images, with the 2D contour data of the soft manipulator extracted in real time. Then, the self-organizing map (SOM) algorithm is run to cluster the contour data to obtain the 2D centerline of the soft manipulator in order, and compared with K-means, Gaussian mixture model and thinning of three centerline extraction algorithms, revealing that SOM algorithm is more suitable for solving the centerline identification of complex shape of the soft manipulator. Finally, the 3D shape reconstruction of the soft manipulator is completed by using the triangulation model based on the disparity. Furthermore, the algorithm framework adapts data downsampling, SOM parameter optimization and other methods to improve real-time performance. The real-time shape sensing and comparative verification are carried out during the continuous deformation of the soft manipulator. Experimental results show that the algorithm presents a high shape sensing accuracy and a superior real-time tracking effect. Compared with other shape detection algorithms locally and globally, the proposed algorithm displays a better performance. |
| Key words: soft manipulator shape recognition self-organizing map (SOM) algorithm triangulation binocular vision |
