The development history and advanced frameworks of SLAM

Beiyi Wang; Liang Wu; Zhongpeng Zhao; Hao Zheng

doi:10.1063/5.0173865

The development history and advanced frameworks of SLAM

Beiyi Wang, Liang Wu^*, Zhongpeng Zhao, Hao Zheng

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

Abstract

In 1988, the concept of simultaneous localization and mapping (SLAM) was proposed. ORB-SLAM is a monocular real-time SLAM system based on features. It fundamentally continues the algorithmic structure of Parallel Tracking And Mapping (PTAM), improving the majority of its components, and so has a larger field of vision in terms of variance, with improved resilience and bundle adjustment (BA) efficiency. Artificial intelligence and machine learning have advanced significantly since the inception of SLMA. Furthermore, in the presence of extreme motion clutter, ORB-SLAM has significantly enhanced loop-back detection and relocation. As a result, it is evident that SLAM and ORB-SLAM approaches are highly worth investigating and expanding. This document presents a detailed chronological account of SLAM development and compares the features of several versions of ORB-SLAM enhancements. It compares two existing ORB-SLAM3 enhancement strategies in dynamic situations in particular. In addition, the article includes a perspective and predictions for the future and later stages.

Original language	English
Title of host publication	2023 International Conference on Computer Science and Mechatronics (ICCSM 2023)
Editors	R. Badlishah Ahmad, Jessiev Zhang, Mengfan Zheng
Publisher	American Institute of Physics Inc.
Edition	1st
ISBN (Electronic)	9780735447233
DOIs	https://doi.org/10.1063/5.0173865
Publication status	Published - 15 Nov 2023
Event	2023 International Conference on Computer Science and Mechatronics, ICCSM 2023 - Shanghai, China Duration: 10 Mar 2023 → 12 Mar 2023 https://pubs.aip.org/aip/acp/issue/3017/1

Publication series

Name	AIP Conference Proceedings
Number	1
Volume	3017
ISSN (Print)	0094-243X
ISSN (Electronic)	1551-7616

Conference

Conference	2023 International Conference on Computer Science and Mechatronics, ICCSM 2023
Country/Territory	China
City	Shanghai
Period	10/03/23 → 12/03/23
Internet address	https://pubs.aip.org/aip/acp/issue/3017/1

UN SDGs

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

Access to Document

10.1063/5.0173865

Cite this

Wang, B., Wu, L., Zhao, Z., & Zheng, H. (2023). The development history and advanced frameworks of SLAM. In R. B. Ahmad, J. Zhang, & M. Zheng (Eds.), 2023 International Conference on Computer Science and Mechatronics (ICCSM 2023) (1st ed.). Article 020004 (AIP Conference Proceedings; Vol. 3017, No. 1). American Institute of Physics Inc.. https://doi.org/10.1063/5.0173865

@inproceedings{21d49aa43e004af78d8114b7e59fdcd5,

title = "The development history and advanced frameworks of SLAM",

abstract = "In 1988, the concept of simultaneous localization and mapping (SLAM) was proposed. ORB-SLAM is a monocular real-time SLAM system based on features. It fundamentally continues the algorithmic structure of Parallel Tracking And Mapping (PTAM), improving the majority of its components, and so has a larger field of vision in terms of variance, with improved resilience and bundle adjustment (BA) efficiency. Artificial intelligence and machine learning have advanced significantly since the inception of SLMA. Furthermore, in the presence of extreme motion clutter, ORB-SLAM has significantly enhanced loop-back detection and relocation. As a result, it is evident that SLAM and ORB-SLAM approaches are highly worth investigating and expanding. This document presents a detailed chronological account of SLAM development and compares the features of several versions of ORB-SLAM enhancements. It compares two existing ORB-SLAM3 enhancement strategies in dynamic situations in particular. In addition, the article includes a perspective and predictions for the future and later stages.",

author = "Beiyi Wang and Liang Wu and Zhongpeng Zhao and Hao Zheng",

note = "Publisher Copyright: {\textcopyright} 2023 Authors. Published by AIP Publishing.; 2023 International Conference on Computer Science and Mechatronics, ICCSM 2023 ; Conference date: 10-03-2023 Through 12-03-2023",

year = "2023",

month = nov,

day = "15",

doi = "10.1063/5.0173865",

language = "English",

series = "AIP Conference Proceedings",

publisher = "American Institute of Physics Inc.",

number = "1",

editor = "Ahmad, {R. Badlishah} and Jessiev Zhang and Mengfan Zheng",

booktitle = "2023 International Conference on Computer Science and Mechatronics (ICCSM 2023)",

edition = "1st",

url = "https://pubs.aip.org/aip/acp/issue/3017/1",

}

Wang, B, Wu, L, Zhao, Z & Zheng, H 2023, The development history and advanced frameworks of SLAM. in RB Ahmad, J Zhang & M Zheng (eds), 2023 International Conference on Computer Science and Mechatronics (ICCSM 2023). 1st edn, 020004, AIP Conference Proceedings, no. 1, vol. 3017, American Institute of Physics Inc., 2023 International Conference on Computer Science and Mechatronics, ICCSM 2023, Shanghai, China, 10/03/23. https://doi.org/10.1063/5.0173865

The development history and advanced frameworks of SLAM. / Wang, Beiyi; Wu, Liang; Zhao, Zhongpeng et al.
2023 International Conference on Computer Science and Mechatronics (ICCSM 2023). ed. / R. Badlishah Ahmad; Jessiev Zhang; Mengfan Zheng. 1st. ed. American Institute of Physics Inc., 2023. 020004 (AIP Conference Proceedings; Vol. 3017, No. 1).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - The development history and advanced frameworks of SLAM

AU - Wang, Beiyi

AU - Wu, Liang

AU - Zhao, Zhongpeng

AU - Zheng, Hao

PY - 2023/11/15

Y1 - 2023/11/15

N2 - In 1988, the concept of simultaneous localization and mapping (SLAM) was proposed. ORB-SLAM is a monocular real-time SLAM system based on features. It fundamentally continues the algorithmic structure of Parallel Tracking And Mapping (PTAM), improving the majority of its components, and so has a larger field of vision in terms of variance, with improved resilience and bundle adjustment (BA) efficiency. Artificial intelligence and machine learning have advanced significantly since the inception of SLMA. Furthermore, in the presence of extreme motion clutter, ORB-SLAM has significantly enhanced loop-back detection and relocation. As a result, it is evident that SLAM and ORB-SLAM approaches are highly worth investigating and expanding. This document presents a detailed chronological account of SLAM development and compares the features of several versions of ORB-SLAM enhancements. It compares two existing ORB-SLAM3 enhancement strategies in dynamic situations in particular. In addition, the article includes a perspective and predictions for the future and later stages.

AB - In 1988, the concept of simultaneous localization and mapping (SLAM) was proposed. ORB-SLAM is a monocular real-time SLAM system based on features. It fundamentally continues the algorithmic structure of Parallel Tracking And Mapping (PTAM), improving the majority of its components, and so has a larger field of vision in terms of variance, with improved resilience and bundle adjustment (BA) efficiency. Artificial intelligence and machine learning have advanced significantly since the inception of SLMA. Furthermore, in the presence of extreme motion clutter, ORB-SLAM has significantly enhanced loop-back detection and relocation. As a result, it is evident that SLAM and ORB-SLAM approaches are highly worth investigating and expanding. This document presents a detailed chronological account of SLAM development and compares the features of several versions of ORB-SLAM enhancements. It compares two existing ORB-SLAM3 enhancement strategies in dynamic situations in particular. In addition, the article includes a perspective and predictions for the future and later stages.

UR - http://www.scopus.com/inward/record.url?scp=85179785267&partnerID=8YFLogxK

UR - https://printorders.aip.org/proceedings/3017

U2 - 10.1063/5.0173865

DO - 10.1063/5.0173865

M3 - Conference proceeding

AN - SCOPUS:85179785267

T3 - AIP Conference Proceedings

BT - 2023 International Conference on Computer Science and Mechatronics (ICCSM 2023)

A2 - Ahmad, R. Badlishah

A2 - Zhang, Jessiev

A2 - Zheng, Mengfan

PB - American Institute of Physics Inc.

T2 - 2023 International Conference on Computer Science and Mechatronics, ICCSM 2023

Y2 - 10 March 2023 through 12 March 2023

ER -

The development history and advanced frameworks of SLAM

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this