remotesensing-logo

Journal Browser

Journal Browser

Data Fusion Methods and AI Technologies for Resilient PNT in Challenging Observation Areas

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".

Deadline for manuscript submissions: 25 November 2024 | Viewed by 4927

Special Issue Editors


E-Mail Website
Guest Editor
School of Instrument Science and Engineering, Southeast University, No. 2 Sipailou, Nanjing 210096, China
Interests: visual SLAM; integrated positioning; map matching; spatial information processing

E-Mail Website
Guest Editor
1. School of Instrument Science and Engineering, Southeast University, No. 2 Sipailou, Nanjing 210096, China
2. Department of Civil and Environmental Engineering, Skempton Building, South Kensington Campus, London SW7 2AZ, UK
Interests: GNSS; AI; structural health monitoring; intelligent mobility; remote sensing; smart city
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Architecture, Building and Civil Engineering, Loughborough University, Loughborough LE11 3TU, UK
Interests: GNSS; ionospheric delay; digital construction; geospatial
Special Issues, Collections and Topics in MDPI journals
School of Instrument Science and Engineering, Southeast University, No. 2 Sipailou, Nanjing 210096, China
Interests: Indoor positioning; integrated positioning; motion capture
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Instrument Science and Engineering, Southeast University, No. 2 Sipailou, Nanjing 210096, China
Interests: SLAM; integrated positioning; 3D modeling; deep learning

Special Issue Information

Dear Colleagues,

The provision of continuous and high-precision positioning information is crucial for activities such as route planning, vehicle navigation, and autonomous driving, especially in challenging observation environments such as city canyons and underground or partially obstructed areas. In recent years, significant progress has been made in the following aspects:

  • The development of multi-constellation global navigation satellite systems (GNSS) and their ground- and satellite-based augmentation infrastructure, along with advancements in 5G/LEO communication technologies.
  • The steady increase in the manufacturing level of sensors such as laser scanners, IMUs, vision systems, mm-wave radars, etc.
  • Embedded systems for positioning and navigation have become increasingly powerful in their hardware configurations, which enables faster program speed, more run-time storage, and better concurrent computation ability.
  • Advances in nonlinear optimization theory, such as bundle adjustment and factor graph theories which support sensors to work in a plug-and-play manner, combined with the latest artificial intelligence technologies, especially deep learning, provide a better and more robust non-linear optimization framework for fusing multi-sensor data in real-time.

The aforementioned progress offers enormous potential and possibilities to obtain increasingly robust and precise positioning ability and deliver resilient PNT services in challenging areas.

This Special Issue of Remote Sensing aims to provide a platform for researchers to publish innovative work that pushes the boundaries of real-time GNSS utilization and enhances the opportunity to provide increasingly precise and robust positioning ability through multi-sensor data fusion and support with the latest AI technologies, even when GNSS services are totally blocked. For instance, technologies that enable the quick capture of GNSS services and provide reliable positioning ability in semi-obscured environments, support high-precision absolute positioning information injection in long-term GNSS-denied areas, and provide continuous positioning ability through the fusion of IMU/vision/map technology are welcome for publication in this Special Issue. Potential topics include, but are not limited to, the following:

  • Fast capture and evaluation of GNSS service quality in semi-obscured environments;
  • Integrated GNSS/5G positioning and navigation approaches;
  • The application of high-resolution map in positioning, for example map-matching;
  • Scene matching algorithm;
  • Approaches for a priori and real-time map construction;
  • Vision positioning technologies such as SLAM;
  • Integrated Kalman and AI applications in resilient PNT;
  • Advanced algorithms for integrated GNSS/IMU/LiDAR/Vision multi-sensor positioning and navigation;
  • Real-time corrections of accumulated error and sensor parameter calibration.

Prof. Dr. Xiaoguo Zhang
Prof. Dr. Xiaolin Meng
Dr. Craig M. Hancock
Dr. Yuan Yang
Dr. Yujia Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • continuous positioning
  • GNSS
  • SLAM
  • tight integration
  • Kalman filter
  • factor graph
  • artificial intelligence
  • non-linear optimization
  • map aided positioning
  • multi-sensor integration
  • machine learning

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Related Special Issue

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

26 pages, 9809 KiB  
Article
Tightly Coupled LIDAR/IMU/UWB Fusion via Resilient Factor Graph for Quadruped Robot Positioning
by Yujin Kuang, Tongfei Hu, Mujiao Ouyang, Yuan Yang and Xiaoguo Zhang
Remote Sens. 2024, 16(22), 4171; https://doi.org/10.3390/rs16224171 - 8 Nov 2024
Viewed by 703
Abstract
Continuous accurate positioning in global navigation satellite system (GNSS)-denied environments is essential for robot navigation. Significant advances have been made with light detection and ranging (LiDAR)-inertial measurement unit (IMU) techniques, especially in challenging environments with varying lighting and other complexities. However, the LiDAR/IMU [...] Read more.
Continuous accurate positioning in global navigation satellite system (GNSS)-denied environments is essential for robot navigation. Significant advances have been made with light detection and ranging (LiDAR)-inertial measurement unit (IMU) techniques, especially in challenging environments with varying lighting and other complexities. However, the LiDAR/IMU method relies on a recursive positioning principle, resulting in the gradual accumulation and dispersion of errors over time. To address these challenges, this study proposes a tightly coupled LiDAR/IMU/UWB fusion approach that integrates an ultra-wideband (UWB) positioning technique. First, a lightweight point cloud segmentation and constraint algorithm is designed to minimize elevation errors and reduce computational demands. Second, a multi-decision non-line-of-sight (NLOS) recognition module using information entropy is employed to mitigate NLOS errors. Finally, a tightly coupled framework via a resilient mechanism is proposed to achieve reliable position estimation for quadruped robots. Experimental results demonstrate that our system provides robust positioning results even in LiDAR-limited and NLOS conditions, maintaining low time costs. Full article
Show Figures

Figure 1

16 pages, 1550 KiB  
Article
A New Data Fusion Method for GNSS/INS Integration Based on Weighted Multiple Criteria
by Chen Jiang, Qiuzhao Zhang and Dongbao Zhao
Remote Sens. 2024, 16(17), 3275; https://doi.org/10.3390/rs16173275 - 3 Sep 2024
Cited by 1 | Viewed by 655
Abstract
The standard Kalman filter and most of its enhancements are typically designed based on the criterion that minimizes the mean squared error, with little discussion of multiple criteria in the positioning and navigation fields. Therefore, a novel data fusion method that takes into [...] Read more.
The standard Kalman filter and most of its enhancements are typically designed based on the criterion that minimizes the mean squared error, with little discussion of multiple criteria in the positioning and navigation fields. Therefore, a novel data fusion method that takes into account weighted multiple criteria is proposed in this paper, implementing a filtering algorithm based on integrated criteria with different weights determined by a weight adjustment factor. The proposed algorithm and conventional filtering algorithms were utilized for data fusion in GNSS/INS integration. Experiments were conducted using actual data collected from an urban environment. Comparative analysis revealed that, when utilizing the proposed algorithm, the precision of the position, velocity, and attitude of the tested land vehicle could be improved by approximately 24%, 48%, and 35%, respectively. Furthermore, a series of filtering algorithms with different weight adjustment factors was performed to test their influence on the filtering. The application of the proposed algorithm should be accompanied by an appropriate weight adjustment factor. Full article
Show Figures

Graphical abstract

20 pages, 7094 KiB  
Article
DualNet-PoiD: A Hybrid Neural Network for Highly Accurate Recognition of POIs on Road Networks in Complex Areas with Urban Terrain
by Yongchuan Zhang, Caixia Long, Jiping Liu, Yong Wang and Wei Yang
Remote Sens. 2024, 16(16), 3003; https://doi.org/10.3390/rs16163003 - 16 Aug 2024
Viewed by 769
Abstract
For high-precision navigation, obtaining and maintaining high-precision point-of-interest (POI) data on the road network is crucial. In urban areas with complex terrains, the accuracy of traditional road network POI acquisition methods often falls short. To address this issue, we introduce DualNet-PoiD, a hybrid [...] Read more.
For high-precision navigation, obtaining and maintaining high-precision point-of-interest (POI) data on the road network is crucial. In urban areas with complex terrains, the accuracy of traditional road network POI acquisition methods often falls short. To address this issue, we introduce DualNet-PoiD, a hybrid neural network designed for the efficient recognition of road network POIs in intricate urban environments. This method leverages multimodal sensory data, incorporating both vehicle trajectories and remote sensing imagery. Through an enhanced dual-attention dilated link network (DAD-LinkNet) based on ResNet18, the system extracts static geometric features of roads from remote sensing images. Concurrently, an improved gated recirculation unit (GRU) captures dynamic traffic characteristics implied by vehicle trajectories. The integration of a fully connected layer (FC) enables the high-precision identification of various POIs, including traffic light intersections, gas stations, parking lots, and tunnels. To validate the efficacy of DualNet-PoiD, we collected 500 remote sensing images and 50,000 taxi trajectory data samples covering road POIs in the central urban area of the mountainous city of Chongqing. Through comprehensive area comparison experiments, DualNet-PoiD demonstrated a high recognition accuracy of 91.30%, performing robustly even under conditions of complex occlusion. This confirms the network’s capability to significantly improve POI detection in challenging urban settings. Full article
Show Figures

Figure 1

19 pages, 9432 KiB  
Article
Temporal Characteristics Based Outlier Detection and Prediction Methods for PPP-B2b Orbit and Clock Corrections
by Zhenhao Xu, Rui Shang, Chengfa Gao, Wang Gao, Qi Liu, Fengyang Long and Dawei Xu
Remote Sens. 2024, 16(13), 2337; https://doi.org/10.3390/rs16132337 - 26 Jun 2024
Viewed by 1032
Abstract
The BeiDou Global Navigation Satellite System (BDS-3) provides real-time precise point positioning (PPP) service via B2b signals, offering real-time decimeter-level positioning for users in China and surrounding areas. However, common interruptions and outliers in PPP-B2b services arise due to factors such as the [...] Read more.
The BeiDou Global Navigation Satellite System (BDS-3) provides real-time precise point positioning (PPP) service via B2b signals, offering real-time decimeter-level positioning for users in China and surrounding areas. However, common interruptions and outliers in PPP-B2b services arise due to factors such as the Geostationary Orbit (GEO) satellite “south wall effect”, Issue of Data (IOD) matching errors, and PPP-B2b signal broadcast priorities, posing challenges to continuous high-precision positioning. This study meticulously examines the completeness, continuity, and jumps in PPP-B2b orbit and clock correction using extensive observational data. Based on this analysis, a two-step method for detecting outliers in PPP-B2b orbit and clock corrections is devised, leveraging epoch differences and median absolute deviation. Subsequently, distinct prediction methods are developed for BDS-3 and GPS orbit and clock corrections. Results from simulated and real-time dynamic positioning experiments indicate that predicted corrections can maintain the same accuracy as normal correction values for up to 10 min and sustain decimeter-level positioning accuracy within 30 min. The adoption of predicted correction values significantly enhances the duration of sustaining real-time PPP during signal interruptions. Full article
Show Figures

Figure 1

Back to TopTop