Active Semantic Perception

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Huayi, Chaudhari, Pratik
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911195410202624
author Tang, Huayi
Chaudhari, Pratik
author_facet Tang, Huayi
Chaudhari, Pratik
contents We develop an approach for active semantic perception which refers to using the semantics of the scene for tasks such as exploration. We build a compact, hierarchical multi-layer scene graph that can represent large, complex indoor environments at various levels of abstraction, e.g., nodes corresponding to rooms, objects, walls, windows etc. as well as fine-grained details of their geometry. We develop a procedure based on large language models (LLMs) to sample plausible scene graphs of unobserved regions that are consistent with partial observations of the scene. These samples are used to compute an information gain of a potential waypoint for sophisticated spatial reasoning, e.g., the two doors in the living room can lead to either a kitchen or a bedroom. We evaluate this approach in complex, realistic 3D indoor environments in simulation. We show using qualitative and quantitative experiments that our approach can pin down the semantics of the environment quicker and more accurately than baseline approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05430
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Active Semantic Perception
Tang, Huayi
Chaudhari, Pratik
Robotics
We develop an approach for active semantic perception which refers to using the semantics of the scene for tasks such as exploration. We build a compact, hierarchical multi-layer scene graph that can represent large, complex indoor environments at various levels of abstraction, e.g., nodes corresponding to rooms, objects, walls, windows etc. as well as fine-grained details of their geometry. We develop a procedure based on large language models (LLMs) to sample plausible scene graphs of unobserved regions that are consistent with partial observations of the scene. These samples are used to compute an information gain of a potential waypoint for sophisticated spatial reasoning, e.g., the two doors in the living room can lead to either a kitchen or a bedroom. We evaluate this approach in complex, realistic 3D indoor environments in simulation. We show using qualitative and quantitative experiments that our approach can pin down the semantics of the environment quicker and more accurately than baseline approaches.
title Active Semantic Perception
topic Robotics
url https://arxiv.org/abs/2510.05430