One of the biggest challenges in robotic manufacturing is bin picking. Automating the bin picking task would produce a lot of savings for manufacturers. The numbers of human workers could be reduced, freeing them from monotonous and repetitious jobs. But, is a robot able to locate and pick individual pieces in a bin of random parts? We might not talk about completely random pieces yet, but “semi-random” bin picking is closer to a solution with all the new vision system technologies available.
Vision System
In order to develop new applications for robotic technology, vision has become a must. Giving eyes to a robot enables it to be deployed in new areas and dramatically improves its performance. Different systems have been developed such as: iRvision from Fanuc, SHAPEscan from ISRA Vision and IPI’s 3D vision-guided robot technology, to name a few. Although they all have the same methodology, bin picking can use vision for two tasks: object recognition and path planning.
The Object Recognition
Object recognition uses the local geometric features of the part to be able to accurately calculate the position and orientation of the object. Moreover, objects that contain a lot of unique features can be detected from a partial view. The vision system, usually a 2D or 3D camera, takes pictures of the bin, then processes the images in order to make a match between its pre-programmed models and a part in the bin. Object recognition not only gives information on the detected object, but also on the undetected ones. This is called environmental information. By using this information, collisions can be avoided while calculating the path.
The Path Planning
This leads us to the path planning role of the vision system. When an object’s position and orientation is determined, the path of the robot for reaching this object is calculated. As stated before, collisions have to be avoided, so the vision system helps by providing information on the other parts in the bin, as well as for the localization of the bin’s walls. This is a safety feature that all bin picking systems should be using.
End effectors
When all the calculations are done, the robot arm can move and pick the piece detected. However, to grab this object, the right end effector has to be chosen. And here again there are some challenges to consider:
-
A specific robot gripper can be designed for the kind of object in the bin. But, since the parts are randomly located in the bin with different orientations, designing the right gripper can be a hard and expensive task.
-
Also designing a specific device brings flexibility problems, because often different grippers need to be used for different pieces. Furthermore, what if the bin contains various different types of objects?
-
General grippers can be used such as suction cups or magnets, but bin picking is often the first part of a task and later in the manufacturing process the robot arm might need to position the part accurately on an assembly or in a machine. Those devices cannot complete these tasks. Moreover, magnets and suction cups can not be used for all materials. Read more about the top 5 problems with suction cups.
Providing gripping flexibility for bin picking
Industrial bin picking applications represents a good fit with our flexible electric grippers. Our robot grippers can adapt to any piece, no matter what their orientations are. Since they have mechanically intelligent fingers, they can automatically adapt themselves to different part shapes, sizes and orientations. Our electric end effectors can also reach tight areas through partial opening and closing. Some of our partners/integrators have already used our robotic grippers for bin picking applications. See the following video on bin picking and robotic assembly from Robomotive.
Leave a comment