A neural network approach to image-based navigation and localization

Daniel L.  Short; Tingjun Lei; Lantao  Liu; Chaomin  Luo; Erfu Yang

doi:10.1109/IJCNN64981.2025.11227291

A neural network approach to image-based navigation and localization

Daniel L. Short, Tingjun Lei, Lantao Liu, Chaomin Luo^*, Erfu Yang

^*Corresponding author for this work

Design, Manufacturing And Engineering Management

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

1 Downloads (Pure)

Abstract

With the increasing use of autonomous robots and vehicles in unfamiliar environments, image-based navigation and localization have gained significant attention. Some advanced algorithms address robust and efficient global path planning. However, reliable local reactive navigation is crucial for obstacle avoidance in close proximity. This paper introduces a biologically inspired neural networks (BNN) model with a dynamic moving window method (DMWM) for local navigation, complemented by a bio-inspired Bat algorithm (BA) for global path planning. The BA utilizes visual features extracted from images using convolutional neural networks (CNNs) to generate paths for autonomous robots. This paper outlines the requirements for image-based navigation, addresses the BA’s principles and its suitability for global path planning, and details the development of the BNN with DMWM for local navigation. Finally, simulations and comparative studies validate the performance and reliability of the proposed methods.

Original language	English
Title of host publication	2025 International Joint Conference on Neural Networks (IJCNN)
Publisher	IEEE
Number of pages	7
ISBN (Electronic)	979-8-3315-1042-8
ISBN (Print)	979-8-3315-1043-5
DOIs	https://doi.org/10.1109/IJCNN64981.2025.11227291
Publication status	Published - 14 Nov 2025
Event	International Joint Conference on Neural Networks 2025 - Rome, Rome, Italy Duration: 30 Jun 2025 → 5 Jul 2025 https://2025.ijcnn.org/

Publication series

Name	2025 International Joint Conference on Neural Networks (IJCNN)
Publisher	IEEE
ISSN (Print)	2161-4393
ISSN (Electronic)	2161-4407

Conference

Conference	International Joint Conference on Neural Networks 2025
Abbreviated title	IJCNN 2025
Country/Territory	Italy
City	Rome
Period	30/06/25 → 5/07/25
Internet address	https://2025.ijcnn.org/

Keywords

image-based localization
bio-inspired neural networks (BNN),
ynamic moving window method (DMWM)
bat algorithm
navigation
mapping

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IJCNN64981.2025.11227291

Short-etal-2025-A-neural-network-approach-to-image-based-navigation-andAccepted author manuscript, 1.68 MBLicence: CC BY 4.0

Cite this

@inproceedings{54e914e65cce403d9921bc523ac5ec48,

title = "A neural network approach to image-based navigation and localization",

abstract = "With the increasing use of autonomous robots and vehicles in unfamiliar environments, image-based navigation and localization have gained significant attention. Some advanced algorithms address robust and efficient global path planning. However, reliable local reactive navigation is crucial for obstacle avoidance in close proximity. This paper introduces a biologically inspired neural networks (BNN) model with a dynamic moving window method (DMWM) for local navigation, complemented by a bio-inspired Bat algorithm (BA) for global path planning. The BA utilizes visual features extracted from images using convolutional neural networks (CNNs) to generate paths for autonomous robots. This paper outlines the requirements for image-based navigation, addresses the BA{\textquoteright}s principles and its suitability for global path planning, and details the development of the BNN with DMWM for local navigation. Finally, simulations and comparative studies validate the performance and reliability of the proposed methods.",

keywords = "image-based localization, bio-inspired neural networks (BNN),, ynamic moving window method (DMWM), bat algorithm, navigation, mapping",

author = "Short, \{Daniel L.\} and Tingjun Lei and Lantao Liu and Chaomin Luo and Erfu Yang",

year = "2025",

month = nov,

day = "14",

doi = "10.1109/IJCNN64981.2025.11227291",

language = "English",

isbn = "979-8-3315-1043-5",

series = "2025 International Joint Conference on Neural Networks (IJCNN)",

publisher = "IEEE",

booktitle = "2025 International Joint Conference on Neural Networks (IJCNN)",

note = "International Joint Conference on Neural Networks 2025, IJCNN 2025 ; Conference date: 30-06-2025 Through 05-07-2025",

url = "https://2025.ijcnn.org/",

}

Short, DL, Lei, T, Liu, L, Luo, C & Yang, E 2025, A neural network approach to image-based navigation and localization. in 2025 International Joint Conference on Neural Networks (IJCNN). 2025 International Joint Conference on Neural Networks (IJCNN), IEEE, International Joint Conference on Neural Networks 2025, Rome, Italy, 30/06/25. https://doi.org/10.1109/IJCNN64981.2025.11227291

TY - GEN

T1 - A neural network approach to image-based navigation and localization

AU - Short, Daniel L.

AU - Lei, Tingjun

AU - Liu, Lantao

AU - Luo, Chaomin

AU - Yang, Erfu

PY - 2025/11/14

Y1 - 2025/11/14

N2 - With the increasing use of autonomous robots and vehicles in unfamiliar environments, image-based navigation and localization have gained significant attention. Some advanced algorithms address robust and efficient global path planning. However, reliable local reactive navigation is crucial for obstacle avoidance in close proximity. This paper introduces a biologically inspired neural networks (BNN) model with a dynamic moving window method (DMWM) for local navigation, complemented by a bio-inspired Bat algorithm (BA) for global path planning. The BA utilizes visual features extracted from images using convolutional neural networks (CNNs) to generate paths for autonomous robots. This paper outlines the requirements for image-based navigation, addresses the BA’s principles and its suitability for global path planning, and details the development of the BNN with DMWM for local navigation. Finally, simulations and comparative studies validate the performance and reliability of the proposed methods.

AB - With the increasing use of autonomous robots and vehicles in unfamiliar environments, image-based navigation and localization have gained significant attention. Some advanced algorithms address robust and efficient global path planning. However, reliable local reactive navigation is crucial for obstacle avoidance in close proximity. This paper introduces a biologically inspired neural networks (BNN) model with a dynamic moving window method (DMWM) for local navigation, complemented by a bio-inspired Bat algorithm (BA) for global path planning. The BA utilizes visual features extracted from images using convolutional neural networks (CNNs) to generate paths for autonomous robots. This paper outlines the requirements for image-based navigation, addresses the BA’s principles and its suitability for global path planning, and details the development of the BNN with DMWM for local navigation. Finally, simulations and comparative studies validate the performance and reliability of the proposed methods.

KW - image-based localization

KW - bio-inspired neural networks (BNN),

KW - ynamic moving window method (DMWM)

KW - bat algorithm

KW - navigation

KW - mapping

UR - https://ieeexplore.ieee.org/Xplore/home.jsp

U2 - 10.1109/IJCNN64981.2025.11227291

DO - 10.1109/IJCNN64981.2025.11227291

M3 - Conference contribution book

SN - 979-8-3315-1043-5

T3 - 2025 International Joint Conference on Neural Networks (IJCNN)

BT - 2025 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

T2 - International Joint Conference on Neural Networks 2025

Y2 - 30 June 2025 through 5 July 2025

ER -

A neural network approach to image-based navigation and localization

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this