With the improvement of industrial automation and technological progress, the number of robots continues to increase, application scenarios are becoming more and more complex, and the requirements for automation and intelligence of robots are also increasing. Due to the development of computer technology and artificial intelligence based on machine vision technical robots has received great attention inthe field of research and production. With the growth of demand, rapid and accurate identification and positioning of objects in any posture in complex spatial environments have become a research hotspot. Based on the image feature processing technology, this paper studies the autonomous target recognition and grasping of industrial robots, establishes the coordinate system of the vision system, derives the projection matrix, and builds a parallel binocular stereo vision system. The method adopted in this paper is that the claw at the end of the robot grips the object to move to different poses, which is used as the theoretical pose of the object, and the grasping result of the visual system is used as the actual pose. The two are compared to solve the grasping errors, a total of 8 comparison experiments were made, and these experimental data were collected and decomposed to draw conclusions. Experiments show that the attitude errors in the X, Y, and Z directions are 1.08°, 1.01°, and 0.92°, respectively. Compared with the previous image positioning errors, it can be found that the errors in the actual robot positioning process are too large, which is mainly caused by the uncalibrated robot; the method used can accurately, quickly, and stably realize the recognition and positioning of the target and meet the needs of the robot for real-time grasping.

随着工业自动化程度的提高和技术进步，机器人数量不断增加，应用场景越来越复杂，对机器人自动化、智能化的要求也越来越高。由于计算机技术和人工智能的发展，基于机器视觉技术的机器人在研究和生产领域受到了极大的关注。随着需求的增长，对复杂空间环境中任意姿态的物体进行快速准确的识别和定位已成为研究热点。本文基于图像特征处理技术，研究工业机器人自主目标识别与抓取，建立视觉系统坐标系，推导投影矩阵，并构建了平行双目立体视觉系统。本文采用的方法是机器人末端的爪子抓取物体移动到不同的位姿，作为物体的理论位姿，视觉系统的抓取结果作为实际位姿. 将两者进行对比，解决抓取误差，共进行了8次对比实验，对这些实验数据进行收集和分解，得出结论。实验表明，X、Y和Z方向的姿态误差分别为1.08°、1.01°和0.92°。对比之前的图像定位误差，可以发现实际机器人定位过程中的误差过大，主要是机器人未标定造成的；使用的方法可以准确、快速、