English

Embodied Uncertainty-Aware Object Segmentation

Robotics 2024-08-12 v1 Artificial Intelligence Computer Vision and Pattern Recognition

Abstract

We introduce uncertainty-aware object instance segmentation (UncOS) and demonstrate its usefulness for embodied interactive segmentation. To deal with uncertainty in robot perception, we propose a method for generating a hypothesis distribution of object segmentation. We obtain a set of region-factored segmentation hypotheses together with confidence estimates by making multiple queries of large pre-trained models. This process can produce segmentation results that achieve state-of-the-art performance on unseen object segmentation problems. The output can also serve as input to a belief-driven process for selecting robot actions to perturb the scene to reduce ambiguity. We demonstrate the effectiveness of this method in real-robot experiments. Website: https://sites.google.com/view/embodied-uncertain-seg

Keywords

Cite

@article{arxiv.2408.04760,
  title  = {Embodied Uncertainty-Aware Object Segmentation},
  author = {Xiaolin Fang and Leslie Pack Kaelbling and Tomás Lozano-Pérez},
  journal= {arXiv preprint arXiv:2408.04760},
  year   = {2024}
}

Comments

IROS 2024

R2 v1 2026-06-28T18:08:11.117Z