MR6D: Benchmarking 6D Pose Estimation for Mobile Robots

TL;DR

MR6D introduces a new dataset tailored for 6D pose estimation in mobile robotics, addressing challenges like long-range perception and heavy occlusion, to improve evaluation and development of relevant algorithms.

Contribution

The paper presents MR6D, a novel dataset capturing mobile robot-specific scenarios, enabling better development and assessment of 6D pose estimation methods for industrial environments.

Findings

Current 6D pose estimation methods underperform on MR6D.

Heavy occlusion and distant viewpoints are significant challenges.

2D segmentation remains a major hurdle in these settings.

Abstract

Existing 6D pose estimation datasets primarily focus on small household objects typically handled by robot arm manipulators, limiting their relevance to mobile robotics. Mobile platforms often operate without manipulators, interact with larger objects, and face challenges such as long-range perception, heavy self-occlusion, and diverse camera perspectives. While recent models generalize well to unseen objects, evaluations remain confined to household-like settings that overlook these factors. We introduce MR6D, a dataset designed for 6D pose estimation for mobile robots in industrial environments. It includes 92 real-world scenes featuring 16 unique objects across static and dynamic interactions. MR6D captures the challenges specific to mobile platforms, including distant viewpoints, varied object configurations, larger object sizes, and complex occlusion/self-occlusion patterns. Initial experiments reveal that current 6D pipelines underperform in these settings, with 2D segmentation being another hurdle. MR6D establishes a foundation for developing and evaluating pose estimation methods tailored to the demands of mobile robotics. The dataset is available at https://huggingface.co/datasets/anas-gouda/mr6d.