MR6D: Benchmarking 6D Pose Estimation for Mobile Robots

2025-08-19

AI Summary

Existing 6D pose estimation datasets focus on small household objects for robotic arm manipulation, failing to address mobile robots’ industrial requirements—long-range observation, large-scale objects, severe self-occlusion, and multi-view dynamic interaction. To bridge this gap, we introduce MR6D, the first real-world industrial 6D pose benchmark tailored for mobile robots. MR6D comprises 92 scenes featuring 16 categories of large industrial objects, encompassing both static and dynamic interactions, diverse camera poses, and complex occlusion patterns. It provides synchronized RGB-D data and high-quality 2D instance segmentation annotations. MR6D is the first benchmark to systematically incorporate long-range perception and heavy self-occlusion challenges, filling a critical void in mobile-platform-specific datasets. Extensive experiments reveal substantial performance degradation of state-of-the-art methods on MR6D—particularly in occlusion robustness and joint pose-segmentation reasoning—highlighting key algorithmic bottlenecks and establishing a rigorous evaluation standard for future research.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Biometrics, Face, Gesture & Pose
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• Addressing mobile robot 6D pose estimation limitations in industrial settings
• Overcoming challenges like distant viewpoints and heavy occlusion patterns
• Providing benchmark for segmentation and pose estimation performance evaluation

Innovation

• Dataset for mobile robot 6D pose estimation
• Captures industrial environments with varied viewpoints
• Addresses occlusion and large object challenges