Investigation into the Impact of Object intrinsic Features on Grasp Affordances
Robotic grasping systems often rely on visual observations to drive the grasping process, where the robot must be able to detect and localize an object, extract features relevant to the task, and then combine this information to plan a manipulation strategy. But what happens when some of the most impactful features are not observed by the robot? Without context on an object’s center of mass, for example, a robot may make assumptions such as uniform density that do not hold, and which may in turn guide the robot into perceiving a sub-optimal set of grasping conﬁgurations. In this work, we examine how having prior knowledge of an object’s intrinsic properties inﬂuences the task of dense grasp aﬀordance prediction. We investigate a simple, constrained grasping task where object properties heavily regulate the space of successful grasps, and further evaluate how learning is aﬀected when generalizing across unseen weight conﬁgurations and unseen object shapes.