Human-Planned Robotic Grasp Ranges: Capture and Validation

TL;DR

This paper introduces a new data capture protocol for human-robot grasping that defines valid grasp ranges, verified through surveys and robot experiments, improving data efficiency and generalization.

Contribution

It presents a novel grasp range specification protocol that enhances data collection and validation for robotic grasping tasks.

Findings

95.38% of within-range grasps correctly identified in surveys

Small variation in grasp ranges across participants

93.75% success rate of interpolated grasps on a robot

Abstract

Leveraging human grasping skills to teach a robot to perform a manipulation task is appealing, but there are several limitations to this approach: time-inefficient data capture procedures, limited generalization of the data to other grasps and objects, and inability to use that data to learn more about how humans perform and evaluate grasps. This paper presents a data capture protocol that partially addresses these deficiencies by asking participants to specify ranges over which a grasp is valid. The protocol is verified both qualitatively through online survey questions (where 95.38% of within-range grasps are identified correctly with the nearest extreme grasp) and quantitatively by showing that there is small variation in grasps ranges from different participants as measured by joint angles, contact points, and position. We demonstrate that these grasp ranges are valid through testing on a physical robot (93.75% of grasps interpolated from grasp ranges are successful).