Multi-Object Grasping -- Types and Taxonomy

TL;DR

This paper introduces a comprehensive taxonomy of 12 multi-object grasp types derived from human and robotic data, analyzing their characteristics and combinations to advance understanding of multi-object manipulation.

Contribution

It presents a novel taxonomy of multi-object grasp types based on extensive data collection, analysis, and comparison, including a stochastic grasping routine for robotic exploration.

Findings

12 MOG types categorized into shape-based and function-based groups

A stochastic grasping routine for robotic exploration of MOGs

Examples of 16 different multi-object grasp combinations

Abstract

This paper proposes 12 multi-object grasps (MOGs) types from a human and robot grasping data set. The grasp types are then analyzed and organized into a MOG taxonomy. This paper first presents three MOG data collection setups: a human finger tracking setup for multi-object grasping demonstrations, a real system with Barretthand, UR5e arm, and a MOG algorithm, a simulation system with the same settings as the real system. Then the paper describes a novel stochastic grasping routine designed based on a biased random walk to explore the robotic hand's configuration space for feasible MOGs. Based on observations in both the human demonstrations and robotic MOG solutions, this paper proposes 12 MOG types in two groups: shape-based types and function-based types. The new MOG types are compared using six characteristics and then compiled into a taxonomy. This paper then introduces the observed MOG type combinations and shows examples of 16 different combinations.