Date of Award

6-2024

Document Type

Thesis

Publisher

Santa Clara : Santa Clara University, 2024

Degree Name

Master of Science (MS)

Department

Electrical and Computer Engineering

First Advisor

Maria Kyrarini

Abstract

Humanoid robots are anticipated to play integral roles in domestic settings, aiding individuals with everyday tasks. Given the prevalence of translucent storage containers in households, characterized by their practicality and transparency, it becomes imperative to equip humanoid robots with the capability to localize and manipulate these objects accurately. Consequently, 6D pose estimation is a crucial area of research for advancing robotic manipulation. However, most existing 6D pose estimation methods and datasets predominantly focus on opaque objects, leaving a gap in research concerning translucent objects. We introduce a novel translucent object dataset with 6D pose and bounding box annotations tailored for robotic manipulation. The dataset includes six classes of translucent container objects in diverse environments and lighting conditions. Additionally, we introduce an automated ground truth annotation method that can be easily replicated and requires only RGB input. Finally, we fine-tune PoET, a transformer-based RGB-only 6D pose estimation framework, on the novel translucent object dataset. Finetuned PoET achieves 94% accuracy on translucent objects from the new dataset.

Available for download on Friday, August 08, 2025

Share

COinS