GeRT · Generalising Robot Manipulation Task

In order to work naturally in human environments robots of the future will need to be much more flexible and robust in the face of novelty than those of today. In GeRT we will develop new methods to cope with novelty in manipulation tasks. Humans cope seamlessly with novel objects: we do not think of grasping a new cup, or screwing the lid off a jar we haven't seen before as challenging. This kind of everyday novelty is hard for a robot. The most advanced robots can perform a task such as making a drink, which involves grasping, pouring and twisting off a cap from a jar. But the rules must be precisely programmed. The ability to manipulate fifty different objects means writing fifty different programs. When the robot encounters an object it hasn't seen before, it can't grasp the object. If one object in a task changes then the program for the whole task may need to be rewritten. If we substitute a mug for a glass in a task that involved pouring liquid from the mug or glass into another object, the pouring position changes, as changes the grasping position. Perhaps we would grasp the mug by the handle, and then tip it sideways to pour. All of this means that if robots are ever going to be useful in natural settings where manipulation is involved that they need ways of generalising on the fly to cope with novel objects, and perhaps novel tasks. Our approach is to take a small set of existing robot programs, for a certain robot manipulation task, such as serving a drink and to give the robot the ability to adapt them to a novel version of the task. These programs constitute a database of prototypes representing that class of task. When confronted with a novel instance of the same task the robot needs establishing correspondences between objects and actions in the prototypes and their counterparts in the novel scenario. To achieve that, GeRT will use a variety of techniques from machine perception, machine learning and Artificial Intelligence such as automated planning.