Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Sep 13, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

RGB-D camera and graph neural network-based SLAM for dynamic and low-texture environments.

Xiaoran Liu¹, Xiaowei Zhang², Xiaochen Yan²

¹HDU-ITMO Joint Institute, Hangzhou Dianzi University, Hangzhou, China.

Scientific Reports

|August 2, 2025

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

STICformer: spatio-temporal intrinsic connections transformer for traffic flow prediction.

Scientific reports·2025

Same author

Z-Selectivity in olefin metathesis with chelated Ru catalysts: computational studies of mechanism and selectivity.

Journal of the American Chemical Society·2012

Same author

Complications after pancreaticoduodenectomy for pancreatic cancer: a retrospective study.

International surgery·2012

Same author

[Inhibitory effect of valproic acid on xenografted Kasumi-1 tumor growth in nude mouse and its mechanism].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2012

Same author

[Foix syndrome secondary to chemotherapy of acute nonlymphocytic leukemia: a case report and review of the literature].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2012

Same author

Effect of resistant starch film properties on the colon-targeting release of drug from coated pellets.

Journal of controlled release : official journal of the Controlled Release Society·2011

This study introduces an enhanced Simultaneous Localization and Mapping (SLAM) framework using RGB-D sensing and a novel neural network. It improves positioning accuracy and mapping reliability for unmanned systems in challenging GPS-denied environments.

Area of Science:

Robotics and Autonomous Systems
Computer Vision
Artificial Intelligence

Background:

Unmanned systems (e.g., UAVs) are vital in agriculture, logistics, and military operations.
Operational effectiveness is hindered by positioning inaccuracies in GPS-denied and complex terrains.
Existing Simultaneous Localization and Mapping (SLAM) methods struggle with robustness in challenging environments.

Purpose of the Study:

To propose an enhanced SLAM framework for improved navigation in GPS-denied environments.
To address limitations in feature matching and localization accuracy for unmanned systems.
To develop a robust mapping solution for complex and low-texture terrains.

Main Methods:

Integration of RGB-D sensing with a novel Depth-aware Point-Line Attentional Graph Neural Network (DPLAGNN).

More Related Videos

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Author Spotlight: An Alternative Approach to Protein Quantification by Bradford Assay Using a Smartphone

Author Spotlight: An Alternative Approach to Protein Quantification by Bradford Assay Using a Smartphone

Published on: September 8, 2023

Related Experiment Videos

Last Updated: Sep 13, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Author Spotlight: An Alternative Approach to Protein Quantification by Bradford Assay Using a Smartphone

Author Spotlight: An Alternative Approach to Protein Quantification by Bradford Assay Using a Smartphone

Published on: September 8, 2023

Development of a feature fusion mechanism combining geometric primitives and attention-weighted descriptors.

Implementation of dynamic scene adaptation via spatiotemporal feature consistency verification and multi-modal optimization.

Main Results:

The proposed DPLAGNN-enhanced SLAM framework demonstrates improved robustness in feature matching.
Enhanced localization consistency was observed across three benchmark datasets.
Measurable improvements in positioning accuracy and mapping reliability were achieved in challenging conditions.

Conclusions:

The novel DPLAGNN framework significantly enhances SLAM performance for unmanned systems.
The approach offers a robust solution for navigation and mapping in GPS-denied and complex environments.
This research contributes to the advancement of reliable autonomous operations in previously inaccessible terrains.