An Inexpensive Yet “Intelligent” Prototype System Using Vision-Guided Robotics for Depalletizing and Emptying Polyethylene Sacks

I n the production line of many industries there exists the procedure of palletizing/depalletizing sacks of raw or finished materials. The plastics industry, for example, uses polyethylene for the production of a series of products, including polyethylene pipes for irrigation, plastic sheets for greenhouse coverings, and other agricultural uses. The usual production procedure is as follows. Pallets are kept in storage areas and are transported by forklifts to depalletization stations when depalletizing is needed. Depalletizing is a labor-intensive job for workers. There are some purely mechanical systems in the market that assist the process in one way or another, but they tend to be expensive and they do not provide a complete solution to the problem. In the majority of palletizing or depalletizing jobs, the environment is either completely structured or may be structured in such a way that the procedure is automated with dedicated machines. This probably explains the low degree of penetration of robots in this area—at least until lately. Changes in this area should be expected once the costs of the required robotic systems decrease further [1]. A requirement for a class of palletization-depalletizion problems is that the automated system should have the ability to recognize the shape and the position in space of the pallet or of the pallet elements. The use of a robotic system with vision capabilities seems to be the most appropriate way to tackle this problem. The Mitsubishi Company presented in 1997 a prototype depalletizing robotic system equipped with stereo vision [2]. The vision system was implemented with the aid of a PC and uses structured lighting techniques to detect the exact three-dimensional (3-D) position of the cargo in the pallet. If the height of the objects in the pallet and the number of the pallet layers are known, then the vision problem is essentially a two-dimensional (2-D) recognition problem. Such a problem—a carton depalletizing problem—has also been solved with a robotic system equipped with a single camera [3]. An ultrasound sensor attached in the gripper provides depth information, and the system is reported to be able to handle cartons randomly placed in the pallet layers. A robotic material transport system designed for the automated supply of packaging machines with paper bobbins has also been reported in [4]. A single camera is used to identify the locations of the bobbins, which come in pallets. The manipulator grasps it in turn and moves it to the requesting machine. In this article a novel structure is presented that is designed and built to minimize costs and increase reliability of the whole system, while at the same time fully automating the depalletizing and emptying of polyethelene sacks. The system is built around a conventional PC that carries out the tasks of control, vision, gripping, and fault monitoring. Simple PID loops are used for the control of all the robot axes, while an inexpensive vision system is used for the determination of the orientation of the pallets. A pneumatic gripper is used for the lifting of the sacks. The most probable faults are monitored for and appropriate actions are taken in the event of fault occurrence. In this way, a form of “intelligence” is built into the system. The system in its present form is ready for use in an appropriate industrial environment.