ROBI: Reflective Objects In Bins Dataset

Yizhou Gao

Dong Li

 , 

 , 

 , 

A multi-view dataset for reflective objects in robotic bin-picking

  • Reflective Objects: 7 challenging industrial objects, with different levels of reflectivity.

  • Bin-Picking Scenes: 63 Scenes with full-bin and low-bin scenarios.

  • Multiple Sensors: A high-cost Ensenso N35 depth camera, and a low-cost Intel RealSense RGB-D camera.

  • Multi-View Acquisition: Data is captured with up to 125 viewpoints via an EPSON C4L 6-Axis robot.

  • Ground Truth Poses: Annotations of ground truth poses for each object in all scenes.

  • Ground Truth Depth: High quality depth maps captured by the high-cost Ensenso camera with objects coated in anti-reflective scanning spray.

 

OBJECTS

SCENES

 

Depth Map

  • We provide the ground truth depth maps captured by Ensenso camera with parts coated in anti-reflective scanning spray.

LICENSE

 

PUBLICATIONS

Jun Yang, Dong Li, and Steven L. Waslander. Probabilistic Multi-View Fusion of Active Stereo Depth Maps for Robotic Bin-Picking. IEEE Robotics and Automation Letters, presentation at the IEEE International Conference on Robotics and Automation, 2021 (Accepted).

Jun Yang, Yizhou Gao, Dong Li, and Steven L. Waslander. ROBI: A Multi-View Dataset for Reflective Objects in Robotic Bin-Picking. Submitted to IEEE Robotics and Automation Letters, 2021.

 
 

ACKNOWLEDGEMENTS

The creation of this dataset has been supported by Toronto Robotics and AI Laboratory and EPSON Canada Ltd.