You Only Estimate Once: Unified, One-stage, Real-Time Category-level Articulated Object 6D Pose Estimation for Robotic Grasping

TL;DR

This paper introduces YOEO, a real-time, single-stage method for category-level articulated object 6D pose estimation, enabling robotic grasping with high efficiency and accuracy in real-world scenarios.

Contribution

The paper presents YOEO, a novel end-to-end network that estimates object pose and segmentation simultaneously, reducing computational costs and improving real-time performance.

Findings

Achieves real-time pose estimation at 200Hz.

Demonstrates effective pose estimation on the GAPart dataset.

Enables a robot to interact with unseen objects in real-world settings.

Abstract

This paper addresses the problem of category-level pose estimation for articulated objects in robotic manipulation tasks. Recent works have shown promising results in estimating part pose and size at the category level. However, these approaches primarily follow a complex multi-stage pipeline that first segments part instances in the point cloud and then estimates the Normalized Part Coordinate Space (NPCS) representation for 6D poses. These approaches suffer from high computational costs and low performance in real-time robotic tasks. To address these limitations, we propose YOEO, a single-stage method that simultaneously outputs instance segmentation and NPCS representations in an end-to-end manner. We use a unified network to generate point-wise semantic labels and centroid offsets, allowing points from the same part instance to vote for the same centroid. We further utilize a clustering algorithm to distinguish points based on their estimated centroid distances. Finally, we first separate the NPCS region of each instance. Then, we align the separated regions with the real point cloud to recover the final pose and size. Experimental results on the GAPart dataset demonstrate the pose estimation capabilities of our proposed single-shot method. We also deploy our synthetically-trained model in a real-world setting, providing real-time visual feedback at 200Hz, enabling a physical Kinova robot to interact with unseen articulated objects. This showcases the utility and effectiveness of our proposed method.