GlassLoc: Plenoptic Grasp Pose Detection in Transparent Clutter

TL;DR

GlassLoc is a novel algorithm that uses plenoptic sensing and Depth Likelihood Volume to detect grasp poses for transparent objects in cluttered environments, improving robotic manipulation capabilities.

Contribution

The paper introduces GlassLoc, a new method leveraging plenoptic sensing and DLV for transparent object grasp detection in cluttered scenes, addressing a key perception challenge.

Findings

Effective grasp detection on transparent glassware in clutter

Successful grasp execution in real-world experiments

Improved perception of transparent objects using plenoptic sensing

Abstract

Transparent objects are prevalent across many environments of interest for dexterous robotic manipulation. Such transparent material leads to considerable uncertainty for robot perception and manipulation, and remains an open challenge for robotics. This problem is exacerbated when multiple transparent objects cluster into piles of clutter. In household environments, for example, it is common to encounter piles of glassware in kitchens, dining rooms, and reception areas, which are essentially invisible to modern robots. We present the GlassLoc algorithm for grasp pose detection of transparent objects in transparent clutter using plenoptic sensing. GlassLoc classifies graspable locations in space informed by a Depth Likelihood Volume (DLV) descriptor. We extend the DLV to infer the occupancy of transparent objects over a given space from multiple plenoptic viewpoints. We demonstrate and evaluate the GlassLoc algorithm on a Michigan Progress Fetch mounted with a first-generation Lytro. The effectiveness of our algorithm is evaluated through experiments for grasp detection and execution with a variety of transparent glassware in minor clutter.