基于面结构光视觉引导的复杂型面机器人焊接系统研究

    Robot Welding System for Complex Surfaces Based on Surface Structure Light Vision Guidance

    • 摘要: 针对机器人视觉引导焊接过程中难以同时自动规划焊接路径和焊接姿态的问题,提出了一种基于面结构光视觉引导的机器人焊接轨迹规划方法。将面结构光视觉传感器固定在机器人末端,通过手眼标定将视觉传感器获得的点云转化到机器人坐标系下。利用微分思想将复杂焊件型面点云划分为单个模块,基于随机采样一致性算法对获得的点云进行分割和拟合,求出焊件不同平面的平面方程,利用焊缝处于平面间交线求解出焊接路径,通过焊枪向量与焊缝的两平面之间的向量重合解出焊接空间姿态。将所有模块的焊接轨迹连接作为焊件整体的机器人焊接轨迹。结果表明:对尺寸为800 mm×180 mm×180 mm的焊件进行测试,机器人焊接点的均方误差小于0.83 mm,满足实际焊接需求。

       

      Abstract: Aiming at the problem that it is difficult to automatically plan the welding path and welding attitude at the same time during the robot vision-guided welding process, a robot welding trajectory planning method based on the vision guidance of surface structured light was proposed. The surface structured light vision sensor was fixed at the end of the robot,and the point cloud obtained from the vision sensor was transformed into the robot coordinate system through hand-eye calibration. The point cloud of the complex weldment profile was divided into individual modules by using the differential idea, the obtained point cloud was segmented and fitted based on the random sampling consistency algorithm, the plane equations of different planes of the weldment were derived, the welding path was solved by using the weld seam being on the inter-planar intersecting line, and the welding spatial attitude was solved by the overlap of the vectors of the welding torch and the vectors between the two planes of the weld seam. The welding trajectory of all modules was connected as the robot welding trajectory of the weldment as a whole. The results show that for the welding of 800 mm×180 mm×180 mm weldment,the mean square error of the robot welding point is less than 0.83 mm, which can meet the actual welding requirements.

       

    /

    返回文章
    返回