Translucent Object Dataset and Automated 6D Pose Annotation Method for Robotic Manipulation

Humanoid robots are anticipated to play integral roles in domestic settings, aiding individuals with everyday tasks. Given the prevalence of translucent storage containers in house-holds, 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 of objects is a crucial area of research to advance 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. The fine-tuned PoET achieves 94% accuracy on translucent objects from the new dataset. The dataset is available at this Link<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>https://ieee-dataport.org/documents/translucent-object-dataset.