A biologically inspired learning to grasp system

Abstract

Abstract-We propose and implement a learning to grasp system inspired from the development of reaching and grasping in infants, and the neurophysiology of the monkey premotor cortex. The system is composed of a virtual 19 DOF kinematics arm/hand and a learning mechanism that enables it to perform a successful grasp. The learning is based on "motor babbling".The model performs open hand reaches to the vicinity of the targets, which human infants younger than 4 moths of age appear to do. The contact of the hand with the object triggers an enclosure of the hand simulating the palmer reflex, characteristic to infants that are younger than 6 months of age. The varying degree of enclosure of each finger and the randomness in the reaching phase enables the system to explore the grasp configuration space. The learning scheme employed is a Hebbian one. Keywords -reaching, grasping, infant, Hebbian learning I. INTRODUCTIONWe can perform a reach and grasp action for many objects in our daily lives effortlessly. However, the task is not trivial at all. The reach and grasp should be planned in ahead for the anticipation of the grasp configuration suitable for the object [1]. As humans have very dexterous hands the possible grasps that can be applied to an object is many. Iberall and Arbib [2] introduced the theory of virtual fingers and opposition space. The term virtual finger is used to describe the physical entity (one or more fingers, the palm of the hand, etc.) that is used in applying force and thus includes specification of the region to be brought in contact with the object (what we might call the "virtual fingertip"). Figure 1 shows three types of opposition: those for the precision grip, power grasp, and side opposition. Each of the grasp types is defined by specifying two virtual fingers, VF1 and VF2, and the regions on VF1 and VF2 which are to be brought into contact with the object to grasp it. Note that the "virtual fingertip" for VF1 in palm opposition is the surface of the palm, while that for VF2 in side opposition is the side of the index finger. The grasp defines two "opposition axes": the opposition axis in the hand joining the virtual finger regions to be opposed to each other, and the opposition axis in the object joining the regions where the virtual fingers contact the object. Visual perception provides affordances (different ways to grasp the object); once an affordance is selected, an appropriate opposition axis in the object can be determined. The task of motor control is to preshape the hand to form an opposition axis appropriate to the chosen affordance, and to so move the arm as to transport the hand to bring the hand and object axes into alignment. During the last stage of transport, the virtual fingers move down the opposition axis (the "enclose" phase) to grasp the object just as the hand reaches the appropriate position. Figure 1. Each of the 3 grasp types here is defined by specifying two "virtual fingers", VF1 and VF2, which are groups of fingers or a part of the hand such as the palm whic...

Object Grasping using the Minimum Variance Model

“…A more realistic model of the hand, such as that used by Meulenbroek et al (2001), could certainly be introduced to our system without changing its fundamental characteristics. However, different types of grip have been modelled using two "virtual" fingers (Oztop and Arbib 2001) that are similar to our arrangement for the hand. A further extension of our model would be to move away from planar grasping and model full three-dimensional grasping movements, with all the challenges involved in the potential link configurations.…”

An SVM learning approach to robotic grasping

“…Several authors have used learning for visually guided grasping [5], [6], [7]. Wheeler et al have developed a learning system for high level grasping [8], and Oztop and Arbib used Hebbian learning to grasp unknown objects [9]. Rezzoug and Groce [10] use multistage neural networks to learn grasping postures.…”