MG
M. Guo
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
3 records found
1
Agriculture accounts for roughly 72% of global freshwater withdrawals, but irrigation is often still based on intuition or fixed schedules. Model-based and data-driven approaches have shown promise, but they mostly rely on historical datasets or crop-specific knowledge that are unavailable in many settings. This thesis addresses that gap by proposing an irrigation control framework that requires no prior data and can learn the system dynamics online during the growing season. The framework combines three components: a Zone Model Predictive Control strategy, an online model estimator based on Recursive Least Squares (RLS), and a Readily Available Water (RAW) estimator. The framework is evaluated using the AquaCrop simulator on a sugarcane case study in southern Mozambique. Results show that the proposed framework performs comparably to a static controller preconfigured with historical data and crop-specific knowledge, while requiring neither. A sparse measurement strategy is also evaluated, reducing the number of required soil moisture measurements by around 65% with little impact on performance. That said, learning the system online comes with trade-offs, and the framework does not consistently outperform a well-configured static model. Together, the results suggest that effective predictive irrigation control is achievable in data-scarce environments.
...
...
Agriculture accounts for roughly 72% of global freshwater withdrawals, but irrigation is often still based on intuition or fixed schedules. Model-based and data-driven approaches have shown promise, but they mostly rely on historical datasets or crop-specific knowledge that are unavailable in many settings. This thesis addresses that gap by proposing an irrigation control framework that requires no prior data and can learn the system dynamics online during the growing season. The framework combines three components: a Zone Model Predictive Control strategy, an online model estimator based on Recursive Least Squares (RLS), and a Readily Available Water (RAW) estimator. The framework is evaluated using the AquaCrop simulator on a sugarcane case study in southern Mozambique. Results show that the proposed framework performs comparably to a static controller preconfigured with historical data and crop-specific knowledge, while requiring neither. A sparse measurement strategy is also evaluated, reducing the number of required soil moisture measurements by around 65% with little impact on performance. That said, learning the system online comes with trade-offs, and the framework does not consistently outperform a well-configured static model. Together, the results suggest that effective predictive irrigation control is achievable in data-scarce environments.
Omnidirectional Mobile Robots in Agricultural Automation
Data-Efficient Modelling and Robust Control
Food production in agriculture is facing significant challenges from population growth and labour shortages, increasing the need to automate labour-intensive tasks. Omnidirectional mobile robots (OMRs) with three planar degrees of freedom are well suited to navigating narrow greenhouse aisles for harvesting, pruning, pest detection, and related applications. This thesis identifies a nonlinear model of such an OMR and designs a trajectory-tracking controller for the MIRTE Master platform developed in the Cognitive Robotics department at TU Delft. Limited data availability and onboard computation make this problem especially challenging.
Sparse identification of nonlinear dynamics with control (SINDYc) is used to learn a sparse, physics-informed model of the MIRTE Master from data. On top of this model, robust tube-based nonlinear model predictive control (NMPC) is implemented for real-time trajectory tracking. The controller uses a two-layer structure that combines nominal planning with an invariant error tube to reject disturbances and model mismatch.
The proposed modelling and control pipeline is validated both in simulation and experimentally on the robot. The results demonstrate real-time feasibility and robust tracking performance, supporting the development of reliable and efficient control systems for agricultural OMRs. ...
Sparse identification of nonlinear dynamics with control (SINDYc) is used to learn a sparse, physics-informed model of the MIRTE Master from data. On top of this model, robust tube-based nonlinear model predictive control (NMPC) is implemented for real-time trajectory tracking. The controller uses a two-layer structure that combines nominal planning with an invariant error tube to reject disturbances and model mismatch.
The proposed modelling and control pipeline is validated both in simulation and experimentally on the robot. The results demonstrate real-time feasibility and robust tracking performance, supporting the development of reliable and efficient control systems for agricultural OMRs. ...
Food production in agriculture is facing significant challenges from population growth and labour shortages, increasing the need to automate labour-intensive tasks. Omnidirectional mobile robots (OMRs) with three planar degrees of freedom are well suited to navigating narrow greenhouse aisles for harvesting, pruning, pest detection, and related applications. This thesis identifies a nonlinear model of such an OMR and designs a trajectory-tracking controller for the MIRTE Master platform developed in the Cognitive Robotics department at TU Delft. Limited data availability and onboard computation make this problem especially challenging.
Sparse identification of nonlinear dynamics with control (SINDYc) is used to learn a sparse, physics-informed model of the MIRTE Master from data. On top of this model, robust tube-based nonlinear model predictive control (NMPC) is implemented for real-time trajectory tracking. The controller uses a two-layer structure that combines nominal planning with an invariant error tube to reject disturbances and model mismatch.
The proposed modelling and control pipeline is validated both in simulation and experimentally on the robot. The results demonstrate real-time feasibility and robust tracking performance, supporting the development of reliable and efficient control systems for agricultural OMRs.
Sparse identification of nonlinear dynamics with control (SINDYc) is used to learn a sparse, physics-informed model of the MIRTE Master from data. On top of this model, robust tube-based nonlinear model predictive control (NMPC) is implemented for real-time trajectory tracking. The controller uses a two-layer structure that combines nominal planning with an invariant error tube to reject disturbances and model mismatch.
The proposed modelling and control pipeline is validated both in simulation and experimentally on the robot. The results demonstrate real-time feasibility and robust tracking performance, supporting the development of reliable and efficient control systems for agricultural OMRs.
Noise, Vibration, and Harshness (NVH) testing plays a pivotal role in assessing the performance and quality of automotive components and machinery. Traditional manual methods often suffer from inconsistency, inefficiency, and a high dependency on operator skill, leading to challenges in ensuring precise impact force, accurate targeting, and optimal impact angles. This thesis introduces an integrated framework that automates NVH testing through the synergistic use of advanced normal vector extraction and multi-objective path planning techniques.
The first contribution of this work is a novel normal vector extraction method grounded in advanced 3D signal processing—a fundamental component of systems and control. This approach robustly computes surface orientations from noisy point cloud data while significantly reducing computational overhead and minimizing data requirements. By leveraging these core 3D signal processing techniques, the method ensures precise alignment of the robotic arm’s end effector, enabling impacts to be delivered perpendicularly to the target surface and thereby enhancing the reliability of vibration measurements.
Complementing this, the thesis proposes a multi-objective path planning framework that employs rigorous optimization techniques—another cornerstone of systems and control curricula—to navigate complex, dynamic, and obstacle-rich environments. By simultaneously addressing factors such as collision avoidance, accessibility, troubleshooting minimization, and targeting accuracy, the framework optimally selects trajectories for the robotic arm, ensuring consistent and repeatable testing even in the presence of irregular component geometries.
Extensive simulations and real-world experiments demonstrate that the integrated approach not only enhances the precision of NVH measurements but also reduces testing time and operational costs. Overall, this research paves the way for more intelligent, efficient, and adaptable automated NVH testing systems suitable for a wide range of industrial applications. ...
The first contribution of this work is a novel normal vector extraction method grounded in advanced 3D signal processing—a fundamental component of systems and control. This approach robustly computes surface orientations from noisy point cloud data while significantly reducing computational overhead and minimizing data requirements. By leveraging these core 3D signal processing techniques, the method ensures precise alignment of the robotic arm’s end effector, enabling impacts to be delivered perpendicularly to the target surface and thereby enhancing the reliability of vibration measurements.
Complementing this, the thesis proposes a multi-objective path planning framework that employs rigorous optimization techniques—another cornerstone of systems and control curricula—to navigate complex, dynamic, and obstacle-rich environments. By simultaneously addressing factors such as collision avoidance, accessibility, troubleshooting minimization, and targeting accuracy, the framework optimally selects trajectories for the robotic arm, ensuring consistent and repeatable testing even in the presence of irregular component geometries.
Extensive simulations and real-world experiments demonstrate that the integrated approach not only enhances the precision of NVH measurements but also reduces testing time and operational costs. Overall, this research paves the way for more intelligent, efficient, and adaptable automated NVH testing systems suitable for a wide range of industrial applications. ...
Noise, Vibration, and Harshness (NVH) testing plays a pivotal role in assessing the performance and quality of automotive components and machinery. Traditional manual methods often suffer from inconsistency, inefficiency, and a high dependency on operator skill, leading to challenges in ensuring precise impact force, accurate targeting, and optimal impact angles. This thesis introduces an integrated framework that automates NVH testing through the synergistic use of advanced normal vector extraction and multi-objective path planning techniques.
The first contribution of this work is a novel normal vector extraction method grounded in advanced 3D signal processing—a fundamental component of systems and control. This approach robustly computes surface orientations from noisy point cloud data while significantly reducing computational overhead and minimizing data requirements. By leveraging these core 3D signal processing techniques, the method ensures precise alignment of the robotic arm’s end effector, enabling impacts to be delivered perpendicularly to the target surface and thereby enhancing the reliability of vibration measurements.
Complementing this, the thesis proposes a multi-objective path planning framework that employs rigorous optimization techniques—another cornerstone of systems and control curricula—to navigate complex, dynamic, and obstacle-rich environments. By simultaneously addressing factors such as collision avoidance, accessibility, troubleshooting minimization, and targeting accuracy, the framework optimally selects trajectories for the robotic arm, ensuring consistent and repeatable testing even in the presence of irregular component geometries.
Extensive simulations and real-world experiments demonstrate that the integrated approach not only enhances the precision of NVH measurements but also reduces testing time and operational costs. Overall, this research paves the way for more intelligent, efficient, and adaptable automated NVH testing systems suitable for a wide range of industrial applications.
The first contribution of this work is a novel normal vector extraction method grounded in advanced 3D signal processing—a fundamental component of systems and control. This approach robustly computes surface orientations from noisy point cloud data while significantly reducing computational overhead and minimizing data requirements. By leveraging these core 3D signal processing techniques, the method ensures precise alignment of the robotic arm’s end effector, enabling impacts to be delivered perpendicularly to the target surface and thereby enhancing the reliability of vibration measurements.
Complementing this, the thesis proposes a multi-objective path planning framework that employs rigorous optimization techniques—another cornerstone of systems and control curricula—to navigate complex, dynamic, and obstacle-rich environments. By simultaneously addressing factors such as collision avoidance, accessibility, troubleshooting minimization, and targeting accuracy, the framework optimally selects trajectories for the robotic arm, ensuring consistent and repeatable testing even in the presence of irregular component geometries.
Extensive simulations and real-world experiments demonstrate that the integrated approach not only enhances the precision of NVH measurements but also reduces testing time and operational costs. Overall, this research paves the way for more intelligent, efficient, and adaptable automated NVH testing systems suitable for a wide range of industrial applications.