Home Download Contact Us RSS 2023 Workshop

News and updates

What is ARMBench?

ARMBench is a large-scale benchmark dataset for perception and manipulation challenges in a robotic pick-and-place setting. The dataset is collected in an Amazon warehouse and captures a wide variety of objects and configurations. It comprises images and videos for different stages of robotic manipulation including picking, transferring, and placing with high-quality annotations.

Currently, the dataset provides data annotations for three main computer vision tasks: Object segmentation, Object Identification, and Defect Detection on images and videos.

Research Paper

Supplementary Video


This dataset is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0). Use the following citation if you use this dataset for publication.

    title={ARMBench: An object-centric benchmark dataset for robotic manipulation},
    author={Mitash, Chaitanya and Wang, Fan and Lu, Shiyang and Terhuja, Vikedo,
            and Garaas, Tyler and Polido, Felipe and Nambi, Manikantan},
    journal={arXiv preprint arXiv:2303.16382},