Intelligent Neurofuzzy Control of a Robotic Gripper

Abstract

One of the major challenges of robotics is the grasping and manipulating of objects in an unstructured environment, in particular where the physical properties of the object are not known a priori. The resultant uncertainty makes it difficult to control contact forces, and the relative position between the object and the gripper’s point of contact. As part of the grasping process, force control is required. This will avoid the risk of the object slipping out of the end effector as well as any possible damage to the object. The means of defining the required grasp force is crucial and can be posed as an optimisation problem, [1].