Automated and robotic handling systems get a grip

For this reason, Festo's Bionic Learning Network developed the MultiChoiceGripper, which offers a combination of different grip types with flexible, adaptive gripping fingers. Its fingers can therefore be switched over so that they can either grip in a parallel or centric direction, without requiring any conversion. This is enabled by two rotatable finger slots on the base body of the gripper, which are arranged either around a central point or opposite the third finger. Naturally enough, this is inspired by the human hand with its opposable thumb, which can be rotated by 130o in relation to the other fingers. Depending on requirements, between two and six finger elements can be fitted to the MultiChoiceGripper. Besides the Fin Ray fingers, two other types of fingers can be attached. Due to the adaptive fingers with a Fin Ray structure, the MultiChoiceGripper is not only variable in terms of the direction of grip as the fingers themselves can adapt to a wide variety of shapes. It can therefore grip differently shaped and also very sensitive objects without additional sensor or control technology. The adaptive Fin Ray-Fingers were designed in 2009 for the bionic FinGripper and have been continually developed ever since. For instance, since 2014 they have been made of food-compliant polyurethane, which means they can be used for the food industry. The MultiChoiceGripper can grip nearly every kind of object – apart from those that are very flat. In order to demonstrate this when exhibited, it first picks up the top part of a blue ball using the centric grip and puts it to one side. At the same time, there is a dark-blue cuboid in the ball and the gripper lifts this up and then places it next to the ball. At this point, a silver-plated cylinder appears; this is also gripped and put to one side. An illuminated blue diamond made of glass is the only thing left. The gripper takes the diamond out of the small holder using its centric-gripping capability and holds it up for show. It then puts the diamond back, covers it with the cylinder and then places the cuboid over the cylinder. The ball is closed once again as the gripper replaces the top part of it. Nature usually focuses on several operating principles with regard to its gripping systems. A combination of force fitting and form fitting is employed most often. Force-fit gripping involves grasping and holding objects using forces acting on a particular point or area – such as frictional forces, vacuums, negative pressures, or magnetic and electrostatic forces. In the case of the form-fitting principle, the gripper adapts to the object and exerts less force. When it comes to technology, most grip systems also apply both operating principles. The aim of these systems is to be able to handle objects with different shapes, sizes, surfaces and textures – preferably without converting the gripper. A simple redirection is used as a kinematic technique for changing the direction of grip. A pull-push bar transfers the force to the holders located on the two finger elements, which in turn can be rotated. These holders change the finger position accordingly: either all the fingers are directed towards a central point, or alternatively two of the fingers are arranged next to each other, while the third finger takes on the function of the opposable thumb to enable a parallel grip. By means of a mechanical locking system, which is pneumatically operated, the finger elements are fixed in their respective final positions. Meanwhile, in the UK, A way of 'teaching' robots to pick up unfamiliar objects without dropping or breaking them has been developed by researchers at the University of Birmingham. The research paves the way for robots to be used in more flexible ways and in more complex environments. These could include manufacturing and packaging industries where a wide variety of different tasks have to be undertaken, and especially where humans and robots need to be able to work together. It is already fairly commonplace to programme robots to pick up particular objects and move them around – factory production lines are a good example of this. But, as already explained, when those objects vary in size or shape, robots tend to get clumsy. In the University's School of Computer Science, researchers have produced a solution to this problem. They have designed a way of programming a robotic hand to be able to pick up an object and then use information learned in that first grip to grasp and move a whole range of similar objects. The researchers taught the robot a specific grasp type, for example, a power grip, using the whole hand to curve around an object, or a pinch grip, which uses two or three fingers. The robot was then able to generalise the grip and adapt it to other objects. Alta Innovations, the University of Birmingham's technology commercialisation office, is currently looking for partners interested in licensing the technology. The University is already working with several companies keen to incorporate the technology into their processes. "Current robot manipulation relies on the robot knowing the exact shape of the object," explains Jeremy Wyatt, professor of robotics and artificial intelligence at the University of Birmingham. "If you put that robot into an unstructured environment, for example if it is trying to pick up an object amongst clutter, or an object for which it doesn't already have an exact model, it will struggle. "The programming we have developed allows the robot to assess the object and generate around 1,000 different grasp options in about five seconds. That means the robot is able to make choices in real time about the best grasp for the object it has been told to pick up and it doesn't need to be continually retrained each time the object changes." The robotic hands used by the team look very similar to human hands, with five jointed fingers, however, the programming would also work with robots that had other types of hand, such as pincer grips. Professor Wyatt's research was presented at the International Conference of Robotics and Automation, organised by the Institute of Electronics and Electrical Engineers,in May 2014. It was carried out within the PaCMan (Probabilistic and Compositional Representations for Object Manipulation) Consortium, funded by the European Union. The consortium is led by Birmingham and also includes the Università di Pisa, in Italy, and Austria's Universität Innsbruck.