基于场景点云重建的移动焊接机器人作业轨迹提取方法

Operation trajectory extraction method of mobile welding robot based on point cloud reconstruction

为保证移动作业焊接机器人能够在建筑、石化、船舶等非结构化场景中精准高效的完成作业,提出一种基于点云重建的焊接轨迹提取方法。焊接机器人变换作业场景后,首先通过深度相机实时检测引导标志物,明确作业范围和起点并重建场景点云。然后基于点云分割和边界提取算法获取焊缝点云轨迹,并提出一种焊接机器人位姿调整策略。最后,针对点云精度不足的问题,采用激光视觉传感器对焊缝进行精度修正,提取精确焊接轨迹。通过曲线焊缝场景实验,表明机器人运动平滑,焊缝轨迹提取误差小于0.5 mm,精度满足生产要求。

To ensure mobile welding robots complete high precision and efficiency operation in unstructured environments such as construction,petrochemical or shipbuilding,a welding trajectory extraction strategy was proposed based on point cloud reconstruction.The RGB-D camera was employed to the target detection to initial point guidance and reconstruction point cloud after changing the work scene.Then the point cloud trajectory was extracted and the robotic pose adjustment method was proposed based on point cloud segment and boundary estimation algorithm.Aiming at the point cloud accuracy problem,the accurate welding seam position was generated using the laser vision sensor.The seam tracking experimental of curve shaped welding seam was conducted,and the results showed that the strategy realized continuous smoothly welding seam tracking and trajectory error was less than 0.05mm,which met the production requirements of automation working.