Robotic Perception

Follow this topic Ask about this topic

Latest papers 303

64 papers in the last four weeks, up 191% on the four weeks before. 0.4% of all new papers.

All topics

XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexity
May 31, 2025Junwen Huang, Jiaqi Hu, Peter KT Yu +3Object Pose Estimation Robotic Manipulation
Technical University of Munich · Munich Center for Machine Learning (MCML) · XYZ Robotics +2
GO: The Great Outdoors Multimodal Dataset
Jan 31, 2025Peng Jiang, Kasi Viswanath, Akhil Nagariya +8Mobile Robotics Robotic Perception
Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University, College Station, TX, USA. · DEVCOM Army Research Laboratory, Adelphi, MD, USA. · University of Texas at Austin Center for Autonomy, Austin, TX, USA.
iTeach: In the Wild Interactive Teaching for Failure-Driven Adaptation of Robot Perception
Oct 1, 2024Jishnu Jaykumar P, Cole Salvato, Vinaya Bomnale +4Continual Learning Human-in-the-Loop AI
The University of Texas at Dallas

May 31, 2025J/K move · Enter open · S save

XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexity

Junwen Huang, Jiaqi Hu, Peter KT Yu, Slobodan Ilic+2

Technical University of Munich · Munich Center for Machine Learning (MCML) · XYZ Robotics+2

Object Pose Estimation Robotic Manipulation Robot Manipulation Benchmarks Robotic Perception

Open paper AskPDF arXiv

While current 6D pose estimation benchmarks have reached near-saturation on household objects, they often fail to capture the stochastic and optical complexities of industrial environments. We introduce XYZ-IBD, a high-precision benchmark for object detection and 6D pose estimation specifically designed for industrial bin-picking. XYZ-IBD addresses the domain gap by providing 75 multi-view real-world scenes containing approximately 273k annotated instances of metallic, symmetrical, and specular objects. Unlike existing datasets, our benchmark features high-density stochastic stacking and multi-instance ambiguity, reflecting authentic robotic manipulation challenges. We employ a rigorous multi-stage and semi-automatic annotation pipeline, ensuring sub-millimeter annotation accuracy. The annotations are validated through our designed error quantification scheme, securing the reliability of the annotation quality. In addition to real-world evaluation data, we provide a large-scale complementary synthetic training set that is rendered under a realistic bin-picking simulation. Benchmarking state-of-the-art (SOTA) methods for 2D detection and 6D pose estimation reveals a significant performance degradation compared to standard household benchmarks, highlighting the unsolved challenges of industrial vision. XYZ-IBD establishes a new frontier for robust pose estimation in complex, high-occlusion, and reflective scenarios. The dataset and benchmark are publicly available at https://xyz-ibd.github.io.

Latest papers 303

XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexity

GO: The Great Outdoors Multimodal Dataset

iTeach: In the Wild Interactive Teaching for Failure-Driven Adaptation of Robot Perception