RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features

arXiv:2403.01731v1 Announce Type: new
Abstract: In order to successfully perform manipulation tasks in new environments, such as grasping, robots must be proficient in segmenting unseen objects from the background and/or other objects. Previous works perform unseen object instance segmentation (UOIS) by training deep neural networks on large-scale data to learn RGB/RGB-D feature embeddings, where cluttered environments often result in inaccurate segmentations. We build upon these methods and introduce a novel approach to correct inaccurate segmentation, such as under-segmentation, of static …

abstract arxiv cs.cv cs.ro data environments features grasping instance interactive learn manipulation networks neural networks objects rgb-d robot robots scale segmentation tasks training type via