Deep Learning-Enhanced Autonomous Aerial and Ground Robotics Using UWB and Lidar in GNSS-Denied Environments

Simple item page
dc.contributor.advisorSohn, Gunho
dc.contributor.advisorArmenakis, Costas
dc.contributor.authorArjmandi, Zahra
dc.date.accessioned2024-11-07T11:14:53Z
dc.date.available2024-11-07T11:14:53Z
dc.date.copyright2024-08-19
dc.date.issued2024-11-07
dc.date.updated2024-11-07T11:14:51Z
dc.degree.disciplineEarth & Space Science
dc.degree.levelDoctoral
dc.degree.namePhD - Doctor of Philosophy
dc.description.abstractOver the last decade, advancements in Unmanned Aerial Vehicle (UAV) technology and Artificial Intelligence (AI) have led to significant improvements in navigation and positioning, yet widespread adoption remains limited due to challenges in integrating various technologies and ensuring reliable real-time data processing. This thesis addresses these issues by developing a comprehensive framework that merges advanced data collection platforms, deep learning algorithms, and novel fusion methods to enhance UAV positioning accuracy and reliability. A central contribution of this research is the creation of the Q-Drone Ultra-Wideband (UWB) benchmark dataset. This dataset, generated from a UAV equipped with five UWB sensors across five diverse environments (indoor, outdoor, and semi-outdoor) over a distance of 4 km, provides a standardized benchmark for testing UAV positioning systems. It enables researchers to develop and validate algorithms under varied conditions, supporting advancements in UAV navigation and positioning research. The thesis also introduces an incremental smoothing approach, integrating high-rate and low-rate UWB measurements with inertial data within a unified pose graph framework. This method, using an "add-after-eliminating" strategy, reduces Mean Absolute Error (MAE) by 0.2 meters compared to baseline multilateration methods and achieves a 0.3-meter MAE reduction compared to two-factor pose graph methods. Further, the DeepCovPG framework is developed, combining a Variational Autoencoder (VAE) with a Long Short-Term Memory (LSTM) network to predict and incorporate dynamic covariances into the pose graph. This approach results in a 48% reduction in Root Mean Square Error (RMSE) and a 51% reduction in Range Covariance RMSE, with notable improvements of 0.41 meters in tunnels and 0.23 meters in fields. The framework also achieves a 26% reduction in multilateration RMSE and a 32% reduction in multilateration Covariance RMSE. Additionally, the thesis explores Light Detection and Ranging (LiDAR)-based positioning and proposes the INAF fusion method. This method dynamically selects relevant information from geometric and AI-based odometry techniques, improving accuracy by 3.90% over direct fusion methods and 0.25% over attention-based fusion methods. The INAF fusion method demonstrates enhanced adaptability to various driving conditions, improving accuracy in both straight and dynamic environments.
dc.identifier.urihttps://hdl.handle.net/10315/42490
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectArtificial intelligence
dc.subjectRemote sensing
dc.subjectAerospace engineering
dc.subject.keywordsUAV
dc.subject.keywordsUGV
dc.subject.keywordsAutonomous robotics
dc.subject.keywordsAutonomous aerial systems
dc.subject.keywordsUAV navigation systems
dc.subject.keywordsUAV flight patterns
dc.subject.keywordsPositioning
dc.subject.keywordsLocalization
dc.subject.keywordsReal-time localization
dc.subject.keywordsTrajectory
dc.subject.keywordsTrajectory prediction
dc.subject.keywordsPositioning accuracy
dc.subject.keywordsHigh-precision positioning
dc.subject.keywordsPosition refinement
dc.subject.keywordsLiDAR
dc.subject.keywordsUWB technology
dc.subject.keywordsIMU
dc.subject.keywordsSensor fusion
dc.subject.keywordsMulti-sensor integration
dc.subject.keywordsAdvanced sensor systems
dc.subject.keywordsSensor calibration
dc.subject.keywordsSensor data integration
dc.subject.keywordsData fusion
dc.subject.keywordsSensor performance evaluation
dc.subject.keywordsMapping
dc.subject.keywordsMap generation
dc.subject.keywordsEnvironmental mapping
dc.subject.keywordsGeospatial analysis
dc.subject.keywords3D point cloud processing
dc.subject.keywordsEnvironmental conditions
dc.subject.keywordsData refinement
dc.subject.keywordsReal-time data processing
dc.subject.keywordsDeep learning
dc.subject.keywordsArtificial intelligence
dc.subject.keywordsMachine learning
dc.subject.keywordsDeep learning-enhanced positioning
dc.subject.keywordsDeep learning for UAV
dc.subject.keywordsDeep learning-based covariance prediction
dc.subject.keywordsMachine learning algorithms
dc.subject.keywordsSLAM
dc.subject.keywordsSimultaneous Localization and Mapping
dc.subject.keywordsPose estimation
dc.subject.keywordsPose graph optimization
dc.subject.keywordsDynamic pose graphs
dc.subject.keywordsCovariance pose graph
dc.subject.keywordsPose graphs
dc.subject.keywordsINAF fusion
dc.subject.keywordsFusion methods
dc.subject.keywordsFeature selection
dc.subject.keywordsSelf-attention
dc.subject.keywordsDynamic covariance prediction
dc.subject.keywordsDynamic covariance
dc.subject.keywordsDeep learning covariance
dc.subject.keywordsPredictive modeling
dc.subject.keywordsAdvanced covariance techniques
dc.subject.keywordsCovariance modeling
dc.subject.keywordsKITTI dataset
dc.subject.keywordsRanges
dc.subject.keywordsMultilateration
dc.subject.keywordsBenchmark
dc.subject.keywordsAlgorithm development
dc.subject.keywordsInference DLL
dc.subject.keywordsGTSAM
dc.subject.keywordsiSAM2
dc.subject.keywordsCovariance analysis
dc.subject.keywordsDynamic systems
dc.subject.keywordsEnvironment dynamics
dc.subject.keywordsDeepCovPG
dc.subject.keywordsUWB-aided UAV positioning
dc.subject.keywordsReal-time positioning
dc.titleDeep Learning-Enhanced Autonomous Aerial and Ground Robotics Using UWB and Lidar in GNSS-Denied Environments
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Arjmandi_Zahra_2024_PhD.pdf
Size:
79.36 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Earth & Space Science

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.