Thien Hoang Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Thien Hoang Nguyen has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Lihua Xie
Nanyang Technological University
15 shared publications - Muqing Cao
Robotics Institute, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA
8 shared publications - Thien-Minh Nguyen
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
7 shared publications - Yang Lyu
Northwestern Polytechnical University
3 shared publications - Zhirong Qiu
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798
3 shared publications Erik Muller
Australian Centre for Robotics, The University of Sydney, Sydney, Australia
2 shared publications
Latest Publications
- 8 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 3, 22-39
A Semi-Autonomous Robotic System for In Situ Soil Sampling, Analysis, and Mapping in Precision Agriculture
Traditional soil sampling and analysis methods are labor-intensive, time-consuming, and lack the spatial resolution needed for precision agriculture, especially under increasing pressures of rising fertilizer costs, climate variability, and the demand for sustainable intensification. To address these challenges, we present a semi-autonomous robotic system for in situ soil sampling, analysis, and mapping of key soil properties. The system integrates three core components: a sample acquisition system (SAS) for precise, automated soil collection; a sample analysis lab (Lab) for rapid, on-site measurement of pH and macronutrients; and an adaptive sampling algorithm (IAS-Pseudo) that leverages pseudo-observations to maintain continuous operation, while analysis is in progress. We validated the system through initial field demonstrations involving 30 samples collected on a pasture field. Results show that the SAS reliably acquires soil cores of 40–50 g at a depth of 200 mm, and the Lab delivers pH and macronutrient measurements within 10 min per sample, with mean errors of 7.8% (N), 13% (P), and 7.1% (K) relative to laboratory analysis. While nitrogen and potassium measurements showed strong agreement with lab ground truth, phosphorus accuracy remains limited by current sensor technology. The IAS-Pseudo strategy reduced mission duration by mitigating analysis delays while maintaining competitive prediction accuracy. These results represent a proof-of-concept validation of a semi-autonomous, integrated system, providing a foundation for future advances toward fully autonomous, scalable, and data-driven soil monitoring and nutrient management.
- 8 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 3, 22-39
A Semi-Autonomous Robotic System for In Situ Soil Sampling, Analysis, and Mapping in Precision Agriculture
Traditional soil sampling and analysis methods are labor-intensive, time-consuming, and lack the spatial resolution needed for precision agriculture, especially under increasing pressures of rising fertilizer costs, climate variability, and the demand for sustainable intensification. To address these challenges, we present a semi-autonomous robotic system for in situ soil sampling, analysis, and mapping of key soil properties. The system integrates three core components: a sample acquisition system (SAS) for precise, automated soil collection; a sample analysis lab (Lab) for rapid, on-site measurement of pH and macronutrients; and an adaptive sampling algorithm (IAS-Pseudo) that leverages pseudo-observations to maintain continuous operation, while analysis is in progress. We validated the system through initial field demonstrations involving 30 samples collected on a pasture field. Results show that the SAS reliably acquires soil cores of 40–50 g at a depth of 200 mm, and the Lab delivers pH and macronutrient measurements within 10 min per sample, with mean errors of 7.8% (N), 13% (P), and 7.1% (K) relative to laboratory analysis. While nitrogen and potassium measurements showed strong agreement with lab ground truth, phosphorus accuracy remains limited by current sensor technology. The IAS-Pseudo strategy reduced mission duration by mitigating analysis delays while maintaining competitive prediction accuracy. These results represent a proof-of-concept validation of a semi-autonomous, integrated system, providing a foundation for future advances toward fully autonomous, scalable, and data-driven soil monitoring and nutrient management.
- Open Access
- 11 September 2025
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 239
A heterogeneous sensing system for soil moisture mapping in agricultural environments
- 11 September 2025
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 239
Open AccessA heterogeneous sensing system for soil moisture mapping in agricultural environments
- 14 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (7) , 6584-6591
Multivariate Active Learning and Adaptive Sampling With Multi-Kernel Gaussian Processes
In agriculture, understanding the distribution and relationship between different aspects of the environment is important for minimizing chemical use and reducing environmental impact. Traditionally, it is done by manually collecting samples on the field and then sending them to a laboratory for analysis. This is not only labor-intensive and costly, but the results will still be outdated. There is thus a growing interest in developing robotic systems to map these variables and uncover their correlations in real time. However, existing learning and sampling methods only focus on one quantity of interest (QoI) or make assumptions that might lead to sub-optimal results when there are multiple QoIs. In this work, we propose a multivariate active transfer learning and intelligent adaptive sampling system that can simultaneously learn the most accurate models for multiple QoIs as well as the relationship between them, and leverage that knowledge to select the next best locations to sample. Performance benchmarking against existing methods shows that QoIs are mapped more accurately, complex correlations between QoIs are identified more precisely, and travel routes are planned more efficiently.
- 14 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (7) , 6584-6591
Multivariate Active Learning and Adaptive Sampling With Multi-Kernel Gaussian Processes
In agriculture, understanding the distribution and relationship between different aspects of the environment is important for minimizing chemical use and reducing environmental impact. Traditionally, it is done by manually collecting samples on the field and then sending them to a laboratory for analysis. This is not only labor-intensive and costly, but the results will still be outdated. There is thus a growing interest in developing robotic systems to map these variables and uncover their correlations in real time. However, existing learning and sampling methods only focus on one quantity of interest (QoI) or make assumptions that might lead to sub-optimal results when there are multiple QoIs. In this work, we propose a multivariate active transfer learning and intelligent adaptive sampling system that can simultaneously learn the most accurate models for multiple QoIs as well as the relationship between them, and leverage that knowledge to select the next best locations to sample. Performance benchmarking against existing methods shows that QoIs are mapped more accurately, complex correlations between QoIs are identified more precisely, and travel routes are planned more efficiently.
- Open Access
- 1 September 2024
- Published by KEAI Publishing in Journal of Automation and Intelligence
- Vol. 3 (3) , 144-151
AV-FDTI: Audio-visual fusion for drone threat identification
- 1 September 2024
- Published by KEAI Publishing in Journal of Automation and Intelligence
- Vol. 3 (3) , 144-151
Open AccessAV-FDTI: Audio-visual fusion for drone threat identification
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 39 (4) , 2861-2877
Relative Transformation Estimation Based on Fusion of Odometry and UWB Ranging Data
In this article, we study the problem of estimating the four-degree-of-freedom (3-D position and heading) robot-to-robot relative frame transformation using onboard odometry and interrobot distance measurements. First, we present a theoretical analysis of the problem, namely, the derivation and interpretation of the Cramèr–Rao lower bound, the Fisher information matrix, and its determinant. Second, we propose optimization-based solutions, including a quadratically constrained quadratic programming (QCQP) formulation and its semidefinite programming (SDP) relaxation. Third, based on the theoretical results, we can detect singular configurations as well as measure the uncertainty of each individual parameter. We perform extensive simulations and real-life experiments with aerial robots to show that the proposed QCQP and SDP methods can outperform state-of-the-art approaches, especially in geometrically poor or large measurement noise conditions. In general, the QCQP method provides the best results at the expense of computational time, while the SDP method runs much faster and is sufficiently accurate in most cases.
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 39 (4) , 2861-2877
Relative Transformation Estimation Based on Fusion of Odometry and UWB Ranging Data
In this article, we study the problem of estimating the four-degree-of-freedom (3-D position and heading) robot-to-robot relative frame transformation using onboard odometry and interrobot distance measurements. First, we present a theoretical analysis of the problem, namely, the derivation and interpretation of the Cramèr–Rao lower bound, the Fisher information matrix, and its determinant. Second, we propose optimization-based solutions, including a quadratically constrained quadratic programming (QCQP) formulation and its semidefinite programming (SDP) relaxation. Third, based on the theoretical results, we can detect singular configurations as well as measure the uncertainty of each individual parameter. We perform extensive simulations and real-life experiments with aerial robots to show that the proposed QCQP and SDP methods can outperform state-of-the-art approaches, especially in geometrically poor or large measurement noise conditions. In general, the QCQP method provides the best results at the expense of computational time, while the SDP method runs much faster and is sufficiently accurate in most cases.
- Open Access
VR-SLAM: A Visual-Range Simultaneous Localization and Mapping System using Monocular Camera and Ultra-wideband Sensors
In this work, we propose a simultaneous localization and mapping (SLAM) system using a monocular camera and Ultra-wideband (UWB) sensors. Our system, referred to as VRSLAM, is a multi-stage framework that leverages the strengths and compensates for the weaknesses of each sensor. Firstly, we introduce a UWB-aided 7 degree-of-freedom (scale factor, 3D position, and 3D orientation) global alignment module to initialize the visual odometry (VO) system in the world frame defined by the UWB anchors. This module loosely fuses up-to-scale VO and ranging data using either a quadratically constrained quadratic programming (QCQP) or nonlinear least squares (NLS) algorithm based on whether a good initial guess is available. Secondly, we provide an accompanied theoretical analysis that includes the derivation and interpretation of the Fisher Information Matrix (FIM) and its determinant. Thirdly, we present UWBaided bundle adjustment (UBA) and UWB-aided pose graph optimization (UPGO) modules to improve short-term odometry accuracy, reduce long-term drift as well as correct any alignment and scale errors. Extensive simulations and experiments show that our solution outperforms UWB/camera-only and previous approaches, can quickly recover from tracking failure without relying on visual relocalization, and can effortlessly obtain a global map even if there are no loop closures.
Open AccessVR-SLAM: A Visual-Range Simultaneous Localization and Mapping System using Monocular Camera and Ultra-wideband Sensors
In this work, we propose a simultaneous localization and mapping (SLAM) system using a monocular camera and Ultra-wideband (UWB) sensors. Our system, referred to as VRSLAM, is a multi-stage framework that leverages the strengths and compensates for the weaknesses of each sensor. Firstly, we introduce a UWB-aided 7 degree-of-freedom (scale factor, 3D position, and 3D orientation) global alignment module to initialize the visual odometry (VO) system in the world frame defined by the UWB anchors. This module loosely fuses up-to-scale VO and ranging data using either a quadratically constrained quadratic programming (QCQP) or nonlinear least squares (NLS) algorithm based on whether a good initial guess is available. Secondly, we provide an accompanied theoretical analysis that includes the derivation and interpretation of the Fisher Information Matrix (FIM) and its determinant. Thirdly, we present UWBaided bundle adjustment (UBA) and UWB-aided pose graph optimization (UPGO) modules to improve short-term odometry accuracy, reduce long-term drift as well as correct any alignment and scale errors. Extensive simulations and experiments show that our solution outperforms UWB/camera-only and previous approaches, can quickly recover from tracking failure without relying on visual relocalization, and can effortlessly obtain a global map even if there are no loop closures.
- Open Access
Relative Transformation Estimation Based on Fusion of Odometry and UWB Ranging Data
In this work, the problem of 4 degree-of-freedom (3D position and heading) robot-to-robot relative frame transformation estimation using onboard odometry and inter-robot distance measurements is studied. Firstly, we present a theoretical analysis of the problem, namely the derivation and interpretation of the Cramer-Rao Lower Bound (CRLB), the Fisher Information Matrix (FIM) and its determinant. Secondly, we propose optimization-based methods to solve the problem, including a quadratically constrained quadratic programming (QCQP) and the corresponding semidefinite programming (SDP) relaxation. Moreover, we address practical issues that are ignored in previous works, such as accounting for spatial-temporal offsets between the ultra-wideband (UWB) and odometry sensors, rejecting UWB outliers and checking for singular configurations before commencing operation. Lastly, extensive simulations and real-life experiments with aerial robots show that the proposed QCQP and SDP methods outperform state-of-the-art methods, especially in geometrically poor or large measurement noise conditions. In general, the QCQP method provides the best results at the expense of computational time, while the SDP method runs much faster and is sufficiently accurate in most cases.
Open AccessRelative Transformation Estimation Based on Fusion of Odometry and UWB Ranging Data
In this work, the problem of 4 degree-of-freedom (3D position and heading) robot-to-robot relative frame transformation estimation using onboard odometry and inter-robot distance measurements is studied. Firstly, we present a theoretical analysis of the problem, namely the derivation and interpretation of the Cramer-Rao Lower Bound (CRLB), the Fisher Information Matrix (FIM) and its determinant. Secondly, we propose optimization-based methods to solve the problem, including a quadratically constrained quadratic programming (QCQP) and the corresponding semidefinite programming (SDP) relaxation. Moreover, we address practical issues that are ignored in previous works, such as accounting for spatial-temporal offsets between the ultra-wideband (UWB) and odometry sensors, rejecting UWB outliers and checking for singular configurations before commencing operation. Lastly, extensive simulations and real-life experiments with aerial robots show that the proposed QCQP and SDP methods outperform state-of-the-art methods, especially in geometrically poor or large measurement noise conditions. In general, the QCQP method provides the best results at the expense of computational time, while the SDP method runs much faster and is sufficiently accurate in most cases.
- Open Access
SPINS: Structure Priors aided Inertial Navigation System
Although Simultaneous Localization and Mapping (SLAM) has been an active research topic for decades, current state-of-the-art methods still suffer from instability or inaccuracy due to feature insufficiency or its inherent estimation drift, in many civilian environments. To resolve these issues, we propose a navigation system combing the SLAM and prior-map-based localization. Specifically, we consider additional integration of line and plane features, which are ubiquitous and more structurally salient in civilian environments, into the SLAM to ensure feature sufficiency and localization robustness. More importantly, we incorporate general prior map information into the SLAM to restrain its drift and improve the accuracy. To avoid rigorous association between prior information and local observations, we parameterize the prior knowledge as low dimensional structural priors defined as relative distances/angles between different geometric primitives. The localization is formulated as a graph-based optimization problem that contains sliding-window-based variables and factors, including IMU, heterogeneous features, and structure priors. We also derive the analytical expressions of Jacobians of different factors to avoid the automatic differentiation overhead. To further alleviate the computation burden of incorporating structural prior factors, a selection mechanism is adopted based on the so-called information gain to incorporate only the most effective structure priors in the graph optimization. Finally, the proposed framework is extensively tested on synthetic data, public datasets, and, more importantly, on the real UAV flight data obtained from a building inspection task. The results show that the proposed scheme can effectively improve the accuracy and robustness of localization for autonomous robots in civilian applications.
Open AccessSPINS: Structure Priors aided Inertial Navigation System
Although Simultaneous Localization and Mapping (SLAM) has been an active research topic for decades, current state-of-the-art methods still suffer from instability or inaccuracy due to feature insufficiency or its inherent estimation drift, in many civilian environments. To resolve these issues, we propose a navigation system combing the SLAM and prior-map-based localization. Specifically, we consider additional integration of line and plane features, which are ubiquitous and more structurally salient in civilian environments, into the SLAM to ensure feature sufficiency and localization robustness. More importantly, we incorporate general prior map information into the SLAM to restrain its drift and improve the accuracy. To avoid rigorous association between prior information and local observations, we parameterize the prior knowledge as low dimensional structural priors defined as relative distances/angles between different geometric primitives. The localization is formulated as a graph-based optimization problem that contains sliding-window-based variables and factors, including IMU, heterogeneous features, and structure priors. We also derive the analytical expressions of Jacobians of different factors to avoid the automatic differentiation overhead. To further alleviate the computation burden of incorporating structural prior factors, a selection mechanism is adopted based on the so-called information gain to incorporate only the most effective structure priors in the graph optimization. Finally, the proposed framework is extensively tested on synthetic data, public datasets, and, more importantly, on the real UAV flight data obtained from a building inspection task. The results show that the proposed scheme can effectively improve the accuracy and robustness of localization for autonomous robots in civilian applications.
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (3) , 7359-7366
Estimating Odometry Scale and UWB Anchor Location Based on Semidefinite Programming Optimization
In this letter, we study the problem of estimating the unknown metric scale of an odometry system and the 3D location of an Ultra-wideband (UWB) anchor in the environment. Firstly, we present a theoretical analysis of the problem which includes the derivation of Fisher Information Matrix (FIM) and its determinant. Secondly, based on the FIM we provide an evaluation and geometric interpretation of singular configurations. Thirdly, we present an estimation-trajectory optimization framework, which consists of a semidefinite programming (SDP) relaxation approach that solves the problem more effectively by exploiting the relationship between the parameters, and an FIM-based trajectory optimization approach that aims to minimize the uncertainty volume while remains easily adaptable to various scenarios. Simulation results show that our estimation method is more accurate and robust than previous approaches, while our trajectory optimization method can improve the estimator’s performance even under challenging constraints.
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (3) , 7359-7366
Estimating Odometry Scale and UWB Anchor Location Based on Semidefinite Programming Optimization
In this letter, we study the problem of estimating the unknown metric scale of an odometry system and the 3D location of an Ultra-wideband (UWB) anchor in the environment. Firstly, we present a theoretical analysis of the problem which includes the derivation of Fisher Information Matrix (FIM) and its determinant. Secondly, based on the FIM we provide an evaluation and geometric interpretation of singular configurations. Thirdly, we present an estimation-trajectory optimization framework, which consists of a semidefinite programming (SDP) relaxation approach that solves the problem more effectively by exploiting the relationship between the parameters, and an FIM-based trajectory optimization approach that aims to minimize the uncertainty volume while remains easily adaptable to various scenarios. Simulation results show that our estimation method is more accurate and robust than previous approaches, while our trajectory optimization method can improve the estimator’s performance even under challenging constraints.
- 17 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 928-935
Flexible and Resource-Efficient Multi-Robot Collaborative Visual-Inertial-Range Localization
In multi-robot systems, two important research problems are relative localization between the robots and global localization of all robots in a common frame. Traditional methods rely on detecting inter and intra-robot loop closures, which can be restrictive operation-wise since the robot must form loops. Ultra-wideband sensors, which provide direct distance measurements and robot ID, can replace loop closures in many applications. However, existing research on UWB-aided multi-robot state estimation often ignores the odometry drift which leads to inaccurate global position in the long run. In this work, we present a UWB-aided multi-robot localization system that does not rely on loop closure (flexible) and only requires odometry data from neighbors (resource-efficient). We propose a two-stage approach: 1) with a long sliding window, the relative transformation is refined based on range and odometry data, 2) onboard visual-inertial-range data are tightly fused in a short-term sliding window to provide more accurate local and global estimates. Simulation and real-life experiments with two quadrotors show that the system as a whole outperforms previous approaches as well as its individual parts.
- 17 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 928-935
Flexible and Resource-Efficient Multi-Robot Collaborative Visual-Inertial-Range Localization
In multi-robot systems, two important research problems are relative localization between the robots and global localization of all robots in a common frame. Traditional methods rely on detecting inter and intra-robot loop closures, which can be restrictive operation-wise since the robot must form loops. Ultra-wideband sensors, which provide direct distance measurements and robot ID, can replace loop closures in many applications. However, existing research on UWB-aided multi-robot state estimation often ignores the odometry drift which leads to inaccurate global position in the long run. In this work, we present a UWB-aided multi-robot localization system that does not rely on loop closure (flexible) and only requires odometry data from neighbors (resource-efficient). We propose a two-stage approach: 1) with a long sliding window, the relative transformation is refined based on range and odometry data, 2) onboard visual-inertial-range data are tightly fused in a short-term sliding window to provide more accurate local and global estimates. Simulation and real-life experiments with two quadrotors show that the system as a whole outperforms previous approaches as well as its individual parts.