Leonardo Luis Giovanini
Research Subjects
Leonardo Luis Giovanini has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Guido Sanchez
Sistemas e Inteligencia Computacional, sinc(i) Instituto de Investigacion en Senales UNL CONICET Ciudad Universitaria UNL 4to piso FICH S3000) Santa Fe Argentina
8 shared publications - Marina Murillo
Sistemas e Inteligencia Computacional, sinc(i) Instituto de Investigacion en Senales UNL CONICET Ciudad Universitaria UNL 4to piso FICH S3000) Santa Fe Argentina
6 shared publications - Nestor Nahuel Deniz
Instituto de Investigacin en Senales, Sistemas e Inteligencia Computacional, sinc(i), UNL-CONICET, Santa Fe, Argentina
4 shared publications - Agustín Capovilla
Research Institute for Signals, Systems and Computational Intelligence, sinc(i)-UNL/CONICET, Ciudad Universitaria UNL, Santa Fe 3000, Argentina
3 shared publications - Luciano Sebastian Martinez-Rau
Department of Computer and Electrical Engineering, Mid Sweden University, Sundsvall, Sweden
3 shared publications - Hugo Leonardo Rufiner
Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional, sinc(i), FICH-UNL/CONICET, Santa Fe, Argentina
2 shared publications
Latest Publications
- Open Access
A CE-C4D Platform Integrating 3D-Printer Ecosystems, Luer-Standard Pneumatics, and Open-Source Hardware
Capillary electrophoresis with Capacitively Coupled Contactless Conductivity Detection (CE-C4D) offers high analytical efficiency and low sample consumption. However, commercial instrumentation remains cost-prohibitive for resource-limited or citizen science settings. Here, we report the design, fabrication, and experimental validation of a low-cost, modular CE-C4D platform based on open hardware architectures (dual C4D, Arduino, RAMPS, and syringe pump modules), FDM 3D-printed parts, 3D printer hardware, Luer-standard medical supplies for pneumatic integrity, and a commercial DC–DC converter. Pressure-driven flow tests demonstrated excellent pneumatic and hydrodynamic stability, yielding variation coefficients below 0.5% for displaced sample plugs. Low-pressure Dual-Opposite Injections of nanoliter-scale sample plugs were implemented using custom hollow-electrode manifolds and a motorized medical three-way valve. Operating under suppressed electroosmotic flow in 2.3 M acetic acid, simultaneous separation of inorganic ions (K+, Ca2+, Mg2+, NO3−, Cl−, SO42−) was achieved in synthetic and commercial hydroponic nutrient samples in less than 5 min for single-detector readings and 12 min for dual-point detection. Dual-point detection enables in-line auto-verification of assay validity, continuously confirming electromigration velocity, peak identity, and hydrodynamic consistency. The hardware achieves reliable run-to-run repeatability and robust fluidic control, providing an accessible, replicable instrument foundation for decentralized chemical profiling and quantitative analytical methods.
Open AccessA CE-C4D Platform Integrating 3D-Printer Ecosystems, Luer-Standard Pneumatics, and Open-Source Hardware
Capillary electrophoresis with Capacitively Coupled Contactless Conductivity Detection (CE-C4D) offers high analytical efficiency and low sample consumption. However, commercial instrumentation remains cost-prohibitive for resource-limited or citizen science settings. Here, we report the design, fabrication, and experimental validation of a low-cost, modular CE-C4D platform based on open hardware architectures (dual C4D, Arduino, RAMPS, and syringe pump modules), FDM 3D-printed parts, 3D printer hardware, Luer-standard medical supplies for pneumatic integrity, and a commercial DC–DC converter. Pressure-driven flow tests demonstrated excellent pneumatic and hydrodynamic stability, yielding variation coefficients below 0.5% for displaced sample plugs. Low-pressure Dual-Opposite Injections of nanoliter-scale sample plugs were implemented using custom hollow-electrode manifolds and a motorized medical three-way valve. Operating under suppressed electroosmotic flow in 2.3 M acetic acid, simultaneous separation of inorganic ions (K+, Ca2+, Mg2+, NO3−, Cl−, SO42−) was achieved in synthetic and commercial hydroponic nutrient samples in less than 5 min for single-detector readings and 12 min for dual-point detection. Dual-point detection enables in-line auto-verification of assay validity, continuously confirming electromigration velocity, peak identity, and hydrodynamic consistency. The hardware achieves reliable run-to-run repeatability and robust fluidic control, providing an accessible, replicable instrument foundation for decentralized chemical profiling and quantitative analytical methods.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 24 (11) , 1320-1334
Robust Moving Horizon Estimation with Huber Loss for GNSS-Based Vehicle Localization under Outliers
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 24 (11) , 1320-1334
Robust Moving Horizon Estimation with Huber Loss for GNSS-Based Vehicle Localization under Outliers
- Open Access
SKD-1: A Modular Skid-Steer Unmanned Ground Vehicle Platform for Robotics Research
This work presents the design, construction and operation of the SKD-1, a modular skid-steer unmanned ground vehicle (UGV) developed as a low-cost research platform for mobile robotics applications. The platform integrates a differential skid-steer drive system, a Raspberry Pi-based onboard computer, and a microcontroller-based control layer implemented using an STM32 microcontroller. The sensing system includes light detection and ranging (LiDAR), global navigation satellite system (GNSS), and an inertial measurement unit (IMU), enabling experiments in localization, mapping, and autonomous navigation. The software architecture is based on the Robot Operating System (ROS) 2 framework, relying on standard ROS 2 packages for perception, mapping, and path planning, with the custom hardware-interface layer being the only non-standard software component. The mechanical and electronic subsystems were designed with a modular architecture that facilitates maintenance, sensor replacement, and hardware upgrades. The primary contribution of this work is the open-hardware design, integration, and documentation of a reproducible robotics testbed, motivated by the prohibitive cost of commercial platforms in resource-constrained research contexts. Indoor and outdoor experiments—covering velocity-tracking, SLAM, and waypoint-navigation trials—demonstrate the functional integration of the sensing, actuation, and computing subsystems.
Open AccessSKD-1: A Modular Skid-Steer Unmanned Ground Vehicle Platform for Robotics Research
This work presents the design, construction and operation of the SKD-1, a modular skid-steer unmanned ground vehicle (UGV) developed as a low-cost research platform for mobile robotics applications. The platform integrates a differential skid-steer drive system, a Raspberry Pi-based onboard computer, and a microcontroller-based control layer implemented using an STM32 microcontroller. The sensing system includes light detection and ranging (LiDAR), global navigation satellite system (GNSS), and an inertial measurement unit (IMU), enabling experiments in localization, mapping, and autonomous navigation. The software architecture is based on the Robot Operating System (ROS) 2 framework, relying on standard ROS 2 packages for perception, mapping, and path planning, with the custom hardware-interface layer being the only non-standard software component. The mechanical and electronic subsystems were designed with a modular architecture that facilitates maintenance, sensor replacement, and hardware upgrades. The primary contribution of this work is the open-hardware design, integration, and documentation of a reproducible robotics testbed, motivated by the prohibitive cost of commercial platforms in resource-constrained research contexts. Indoor and outdoor experiments—covering velocity-tracking, SLAM, and waypoint-navigation trials—demonstrate the functional integration of the sensing, actuation, and computing subsystems.
- 4 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (10) , 10815-10821
Robust Moving Horizon Estimation for Autonomous Agricultural Vehicles With GNSS Outliers Using a Robust Loss Function
We propose a Moving Horizon Estimator (MHE) for autonomous agricultural vehicles to handle GNSS outliers, a common issue in farming. To improve robustness, we replace the standard $\mathrm{L_{2}}$ stage cost with a loss function based on the square of the derivative of the General Adaptive Robust Loss (GARL). The GARL framework, controlled by parameters $\alpha \in [1,\,2)$ and $c > 0$, balances between quadratic and outlier-resistant behavior. By using the derivative, we avoid singularities at $\alpha = 0$ and $\alpha = 2$, simplifying tuning and ensuring stable optimization within MHE. This approach retains the flexibility of GARL while narrowing the design space to a singularity-free regime. We prove robust stability under standard assumptions. Simulations show our method outperforms $\mathrm{L_{2}}$-based MHE and state-of-the-art methods, rejecting GNSS outliers. Field experiments validate its practical effectiveness.
- 4 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (10) , 10815-10821
Robust Moving Horizon Estimation for Autonomous Agricultural Vehicles With GNSS Outliers Using a Robust Loss Function
We propose a Moving Horizon Estimator (MHE) for autonomous agricultural vehicles to handle GNSS outliers, a common issue in farming. To improve robustness, we replace the standard $\mathrm{L_{2}}$ stage cost with a loss function based on the square of the derivative of the General Adaptive Robust Loss (GARL). The GARL framework, controlled by parameters $\alpha \in [1,\,2)$ and $c > 0$, balances between quadratic and outlier-resistant behavior. By using the derivative, we avoid singularities at $\alpha = 0$ and $\alpha = 2$, simplifying tuning and ensuring stable optimization within MHE. This approach retains the flexibility of GARL while narrowing the design space to a singularity-free regime. We prove robust stability under standard assumptions. Simulations show our method outperforms $\mathrm{L_{2}}$-based MHE and state-of-the-art methods, rejecting GNSS outliers. Field experiments validate its practical effectiveness.
- Open Access
- 21 June 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 157
A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
- 21 June 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 157
Open AccessA multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
- Open Access
Adaptive Dynamic Social Networks Using an Agent-Based Model to Study the Role of Social Awareness in Infectious Disease Spread
The synergy between the spread of infectious diseases and individual behavior is widely recognized. Our pioneering methodology introduces a model based on agents embedded within adaptive temporal networks, providing a nuanced portrayal of daily interactions through an agent-based paradigm. Each agent encapsulates the interactions of individuals, with external stimuli and environmental cues influencing their conduct. Comprising three intertwined elements—individual behavior, social dynamics, and epidemiological factors—the model has been validated against real-world influenza outbreaks, demonstrating superior performance compared to traditional methodologies. Our framework exhibits extensive versatility and applicability by encapsulating individual-level dynamics through elementary rules and simulating complex social behaviors such as social consciousness.
Open AccessAdaptive Dynamic Social Networks Using an Agent-Based Model to Study the Role of Social Awareness in Infectious Disease Spread
The synergy between the spread of infectious diseases and individual behavior is widely recognized. Our pioneering methodology introduces a model based on agents embedded within adaptive temporal networks, providing a nuanced portrayal of daily interactions through an agent-based paradigm. Each agent encapsulates the interactions of individuals, with external stimuli and environmental cues influencing their conduct. Comprising three intertwined elements—individual behavior, social dynamics, and epidemiological factors—the model has been validated against real-world influenza outbreaks, demonstrating superior performance compared to traditional methodologies. Our framework exhibits extensive versatility and applicability by encapsulating individual-level dynamics through elementary rules and simulating complex social behaviors such as social consciousness.
- 12 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
On-Device Feeding Behavior Analysis of Grazing Cattle
Precision livestock farming leverages cutting-edge technologies and data-driven solutions to enhance the efficiency of livestock production, its associated management and its welfare. Continuous monitoring of the masticatory sound of cattle allows the estimation of dry-matter intake, classification of jaw movements, and recognition of grazing and rumination bouts. Over the past two decades, algorithms for analyzing feeding sounds have seen improvements in performance and computational requirements. Nevertheless, in some cases, these algorithms have been implemented on resource-constrained electronic devices, limiting their functionality to one specific task: either classifying jaw movements or recognizing feeding activities (such as grazing and rumination). In this work, we present an acoustic monitoring system that comprehensively analyzes grazing cattle’s feeding behavior at multiple scales. This embedded system classifies different types of jaw movements, identifies feeding activities, and provides predictor variables for estimating dry-matter intake. Results are transmitted remotely to a base station using long-range communication. Two variants of the system have been deployed on a Raspberry Pi Pico board, based on a low-power ARM Cortex-M0+ microcontroller. Both firmware versions make use of direct access memory, sleep mode, and clock-gating techniques to minimize energy consumption. In laboratory experiments, the first deployment consumes 20.1 mW and achieves an F1-score of 87.3% for the classification of jaw movements and 87.0% for feeding activities. The second deployment consumes 19.1 mW and reaches an F1-score of 84.1% for jaw movements and 83.5% for feeding activities. The modular design of the proposed embedded monitoring system facilitates integration with energy-harvesting power sources for autonomous operation in field conditions.
- 12 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
On-Device Feeding Behavior Analysis of Grazing Cattle
Precision livestock farming leverages cutting-edge technologies and data-driven solutions to enhance the efficiency of livestock production, its associated management and its welfare. Continuous monitoring of the masticatory sound of cattle allows the estimation of dry-matter intake, classification of jaw movements, and recognition of grazing and rumination bouts. Over the past two decades, algorithms for analyzing feeding sounds have seen improvements in performance and computational requirements. Nevertheless, in some cases, these algorithms have been implemented on resource-constrained electronic devices, limiting their functionality to one specific task: either classifying jaw movements or recognizing feeding activities (such as grazing and rumination). In this work, we present an acoustic monitoring system that comprehensively analyzes grazing cattle’s feeding behavior at multiple scales. This embedded system classifies different types of jaw movements, identifies feeding activities, and provides predictor variables for estimating dry-matter intake. Results are transmitted remotely to a base station using long-range communication. Two variants of the system have been deployed on a Raspberry Pi Pico board, based on a low-power ARM Cortex-M0+ microcontroller. Both firmware versions make use of direct access memory, sleep mode, and clock-gating techniques to minimize energy consumption. In laboratory experiments, the first deployment consumes 20.1 mW and achieves an F1-score of 87.3% for the classification of jaw movements and 87.0% for feeding activities. The second deployment consumes 19.1 mW and reaches an F1-score of 84.1% for jaw movements and 83.5% for feeding activities. The modular design of the proposed embedded monitoring system facilitates integration with energy-harvesting power sources for autonomous operation in field conditions.
- 12 October 2023
- Published by Springer Nature
- p. 672-683
Information Technologies in Feeding Behavior Livestock Monitoring
- 12 October 2023
- Published by Springer Nature
- p. 672-683
Information Technologies in Feeding Behavior Livestock Monitoring
- 23 May 2023
- Published by Springer Nature
- p. 1-12
Information Technologies in Feeding Behavior Livestock Monitoring
- 23 May 2023
- Published by Springer Nature
- p. 1-12
Information Technologies in Feeding Behavior Livestock Monitoring
- 3 April 2023
- Published by Elsevier in Biosystems Engineering
- Vol. 229, 69-84
Using segment-based features of jaw movements to recognise foraging activities in grazing cattle
- 3 April 2023
- Published by Elsevier in Biosystems Engineering
- Vol. 229, 69-84
Using segment-based features of jaw movements to recognise foraging activities in grazing cattle