# Embodied Uncertainty-Aware Object Segmentation

Source: [Embodied Uncertainty-Aware Object Segmentation](<https://www.sota2.com/research/paper/68fa746f1e209131cea61b9b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:08.618Z

Authors: Xiaolin Fang, Leslie Pack Kaelbling, Tom\\'as Lozano-P\\'erez

Published: 2024-08-08T21:29:22.000Z

## 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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2408.04760>)

[PDF](<https://arxiv.org/pdf/2408.04760.pdf>)
