Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kassab, Christina, Mattamala, Matias, Zhang, Lintong, Fallon, Maurice
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914703046868992
author Kassab, Christina
Mattamala, Matias
Zhang, Lintong
Fallon, Maurice
author_facet Kassab, Christina
Mattamala, Matias
Zhang, Lintong
Fallon, Maurice
contents Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this work, we introduce LEXIS, a real-time indoor Simultaneous Localization and Mapping (SLAM) system that harnesses the open-vocabulary nature of Large Language Models (LLMs) to create a unified approach to scene understanding and place recognition. The approach first builds a topological SLAM graph of the environment (using visual-inertial odometry) and embeds Contrastive Language-Image Pretraining (CLIP) features in the graph nodes. We use this representation for flexible room classification and segmentation, serving as a basis for room-centric place recognition. This allows loop closure searches to be directed towards semantically relevant places. Our proposed system is evaluated using both public, simulated data and real-world data, covering office and home environments. It successfully categorizes rooms with varying layouts and dimensions and outperforms the state-of-the-art (SOTA). For place recognition and trajectory estimation tasks we achieve equivalent performance to the SOTA, all also utilizing the same pre-trained model. Lastly, we demonstrate the system's potential for planning.
format Preprint
id arxiv_https___arxiv_org_abs_2309_15065
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding
Kassab, Christina
Mattamala, Matias
Zhang, Lintong
Fallon, Maurice
Robotics
Computer Vision and Pattern Recognition
Image and Video Processing
Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this work, we introduce LEXIS, a real-time indoor Simultaneous Localization and Mapping (SLAM) system that harnesses the open-vocabulary nature of Large Language Models (LLMs) to create a unified approach to scene understanding and place recognition. The approach first builds a topological SLAM graph of the environment (using visual-inertial odometry) and embeds Contrastive Language-Image Pretraining (CLIP) features in the graph nodes. We use this representation for flexible room classification and segmentation, serving as a basis for room-centric place recognition. This allows loop closure searches to be directed towards semantically relevant places. Our proposed system is evaluated using both public, simulated data and real-world data, covering office and home environments. It successfully categorizes rooms with varying layouts and dimensions and outperforms the state-of-the-art (SOTA). For place recognition and trajectory estimation tasks we achieve equivalent performance to the SOTA, all also utilizing the same pre-trained model. Lastly, we demonstrate the system's potential for planning.
title Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding
topic Robotics
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2309.15065