Physical Human Interactive Guidance: Identifying Grasping Principles From Human-Planned Grasps

Abstract

Abstract-We present a novel and simple experimental method called physical human interactive guidance to study humanplanned grasping. Instead of studying how the human uses his/her own biological hand or how a human teleoperates a robot hand in a grasping task, the method involves a human interacting physically with a robot arm and hand, carefully moving and guiding the robot into the grasping pose, while the robot's configuration is recorded. Analysis of the grasps from this simple method has produced two interesting results. First, the grasps produced by this method perform better than grasps generated through a state-of-the-art automated grasp planner. Second, this method when combined with a detailed statistical analysis using a variety of grasp measures (physics-based heuristics considered critical for a good grasp) offered insights into how the human grasping method is similar or different from automated grasping synthesis techniques. Specifically, data from the physical human interactive guidance method showed that the human-planned grasping method provides grasps that are similar to grasps from a state-of-the-art automated grasp planner, but differed in one key aspect. The robot wrists were aligned with the object's principal axes in the human-planned grasps (termed low skewness in this paper), while the automated grasps used arbitrary wrist orientation. Preliminary tests show that grasps with low skewness were significantly more robust than grasps with high skewness (77-93%). We conclude with a detailed discussion of how the physical human interactive guidance method relates to existing methods to extract the human principles for physical interaction.

Three-dimensional object reconstruction of symmetric objects by fusing visual and tactile sensing

“…Typically these are developed and evaluated mainly in simulation environments. More recent criteria relax the dependency on precise knowledge of contact and object shape but still partially or fully rely on global object properties such as the principal axes or center of mass (Hsiao et al, 2010;Balasubramanian et al, 2012). Once an object is grasped and has to be moved within the environment, constraints have to be respected for example for collision avoidance (Berenson et al, 2011).…”

Dex-Net 1.0: A cloud-based network of 3D objects for robust grasp planning using a Multi-Armed Bandit model with correlated rewards

“…Grasp planning considers the problem of finding grasps for a given object that achieve force closure or optimize a related quality metric, such as the epsilon quality [35], correlation with human labels [2], [18], or success in physical trials. Often it is assumed that the object is known exactly and that contacts are placed exactly, and mechanical wrench space analysis is applied.…”

Learning grasps with topographic features

“…However, even the developer of OpenRAVE claims (Diankov, 2010) that, in practice, grasps detected using this metric tend to be relatively fragile. In Balasubramanian et al (2012) a number of grasps were systematically tested in the real world that were stable according to classical grasp metrics. A similar study by Weisz and Allen (2012) focused on the e-metric.…”