Picking unsorted parts from crates and other containers is called reach-in-the-box or bin picking – the supreme discipline of robotics. One or more 3D cameras first generate a 3D point cloud of the crate contents. Complex algorithms are used to calculate the position and orientation of the workpieces in the box. In addition, there are also collision avoidance algorithms that determine the best possible robot path for gripping a workpiece. More recent solutions implement neural networks and deep learning to make the aforementioned algorithms more flexible and robust.
We have integrated various 3D image processing systems so that the user is free to choose which solution is best suited for the application. As an example, the video shows a bin-picking application with a KUKA robot, a Roboception 3D camera and a Robotiq gripper system.
Used drag&bot modules