Unseen Object Instance Segmentation for Robotic Environments

In order to function in unstructured environments, robots need the ability to recognize unseen objects. We take a step in this direction by tackling the problem of segmenting unseen object instances in tabletop environments. However, the type of large-scale real-world dataset required for this task...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on robotics 2021-10, Vol.37 (5), p.1343-1359
Main Authors: Xie, Christopher, Xiang, Yu, Mousavian, Arsalan, Fox, Dieter
Format: Article
Language:English
Subjects:
Datasets
Grasping (robotics)
Image segmentation
Instance segmentation
Masks
Noise measurement
Object recognition
Robot perception
Robots
Semantics
sim-to-real
Three-dimensional displays
Training
Two dimensional displays
unseen object instance segmentation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!