Eric Aislan Antonelo
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
Eric Aislan Antonelo has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Eduardo Camponogara
Department of Automation and Systems Engineering, Federal University of Santa Catarina, Florianópolis, Brazil
9 shared publications - Gustavo Claudio Karl Couto
Department of Automation and Systems Engineering Federal University of Santa Catarina (UFSC) Florianópolis Brazil
5 shared publications - Alexey Pavlov
Norwegian University of Science and Technology, S.P. Andersens vei 15a, Trondheim, 7031, Norway [NO
3 shared publications - Christian Möller
Faculty of Science and Engineering Information Technology Åbo Akademi University Finland
3 shared publications Eduardo Camponogara
3 shared publications- Jean Panaioti Jordanou
Department of Automation and Systems Engineering Universidade Federal de Santa Catarina, Florianpolis, Santa Catarina, Brazil
3 shared publications
Latest Publications
- Open Access
- 19 June 2026
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 213
Physics-Informed Neural Networks for two-phase flow modeling in pipelines with state-dependent properties: Parameter estimation and experiment design
- 19 June 2026
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 213
Open AccessPhysics-Informed Neural Networks for two-phase flow modeling in pipelines with state-dependent properties: Parameter estimation and experiment design
- Open Access
- 25 March 2026
- Published by Elsevier in SSRN Electronic Journal
Physics-Informed Neural Networks for Two-Phase Flow Modeling in Pipelines with State-Dependent Properties: Parameter Estimation and Experiment Design
This work proposes a Physics-Informed Neural Network (PINN) framework for steady-state two-phase flow modeling in pipelines, where pressure and temperature are state variables and fluid properties are functions of these states using PVT (Pressure–Volume–Temperature) tabulated data. The formulation accounts for the mass, momentum, and energy equations, resulting in a PINN model that is orders of magnitude faster than traditional solvers while maintaining comparable accuracy.Once trained, the PINN model is used for inverse modeling in virtual flow metering applications, where the parameters, such as water cut, are inferred from pressure and temperature measurements along the pipeline. By serving as a fast surrogate, the PINN accelerates parameter uncertainty quantification, eliminating the need for repeated evaluations of traditional solvers.Moreover, the framework supports the design of optimal trajectories for manipulated variables to maximize the Fisher Information from sensor measurements, thereby reducing parameter uncertainty. This integration of physics-informed modeling and information-based experiment design provides a fast and physics-based framework for parameter estimation in multiphase flow pipelines.
- 25 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessPhysics-Informed Neural Networks for Two-Phase Flow Modeling in Pipelines with State-Dependent Properties: Parameter Estimation and Experiment Design
This work proposes a Physics-Informed Neural Network (PINN) framework for steady-state two-phase flow modeling in pipelines, where pressure and temperature are state variables and fluid properties are functions of these states using PVT (Pressure–Volume–Temperature) tabulated data. The formulation accounts for the mass, momentum, and energy equations, resulting in a PINN model that is orders of magnitude faster than traditional solvers while maintaining comparable accuracy.Once trained, the PINN model is used for inverse modeling in virtual flow metering applications, where the parameters, such as water cut, are inferred from pressure and temperature measurements along the pipeline. By serving as a fast surrogate, the PINN accelerates parameter uncertainty quantification, eliminating the need for repeated evaluations of traditional solvers.Moreover, the framework supports the design of optimal trajectories for manipulated variables to maximize the Fisher Information from sensor measurements, thereby reducing parameter uncertainty. This integration of physics-informed modeling and information-based experiment design provides a fast and physics-based framework for parameter estimation in multiphase flow pipelines.
- 29 September 2025
- Published by Sociedade Brasileira de Computação
- p. 962-973
Exploring multimodal implicit behavior learning for vehicle navigation in simulated cities
Standard Behavior Cloning (BC) fails to learn multimodal driving decisions, where multiple valid actions exist for the same scenario. We explore Implicit Behavioral Cloning (IBC) with Energy-Based Models (EBMs) to better capture this multimodality. We propose Data-Augmented IBC (DA-IBC), which improves learning by perturbing expert actions to form the counterexamples of IBC training and using better initialization for derivative-free inference. Experiments in the CARLA simulator with Bird’s-Eye View inputs demonstrate that DA-IBC outperforms standard IBC in urban driving tasks designed to evaluate multimodal behavior learning in a test environment. The learned energy landscapes are able to represent multimodal action distributions, which BC fails to achieve.
- 29 September 2025
- Published by Sociedade Brasileira de Computação
- p. 962-973
Exploring multimodal implicit behavior learning for vehicle navigation in simulated cities
Standard Behavior Cloning (BC) fails to learn multimodal driving decisions, where multiple valid actions exist for the same scenario. We explore Implicit Behavioral Cloning (IBC) with Energy-Based Models (EBMs) to better capture this multimodality. We propose Data-Augmented IBC (DA-IBC), which improves learning by perturbing expert actions to form the counterexamples of IBC training and using better initialization for derivative-free inference. Experiments in the CARLA simulator with Bird’s-Eye View inputs demonstrate that DA-IBC outperforms standard IBC in urban driving tasks designed to evaluate multimodal behavior learning in a test environment. The learned energy landscapes are able to represent multimodal action distributions, which BC fails to achieve.
- 29 September 2025
- Published by Sociedade Brasileira de Computação
- p. 855-866
An Initial Study of Bird’s-Eye View Generation for Autonomous Vehicles using Cross-View Transformers
Bird’s-Eye View (BEV) maps provide a structured, top-down abstraction that is crucial for autonomous-driving perception. In this work, we employ Cross-View Transformers (CVT) for learning to map camera images to three BEV’s channels - road, lane markings, and planned trajectory - using a realistic simulator for urban driving. Our study examines generalization to unseen towns, the effect of different camera layouts, and two loss formulations (focal and L1). Using training data from only a town, a four-camera CVT trained with the L1 loss delivers the most robust test performance, evaluated in a new town. Overall, our results underscore CVT’s promise for mapping camera inputs to reasonably accurate BEV maps.
- 29 September 2025
- Published by Sociedade Brasileira de Computação
- p. 855-866
An Initial Study of Bird’s-Eye View Generation for Autonomous Vehicles using Cross-View Transformers
Bird’s-Eye View (BEV) maps provide a structured, top-down abstraction that is crucial for autonomous-driving perception. In this work, we employ Cross-View Transformers (CVT) for learning to map camera images to three BEV’s channels - road, lane markings, and planned trajectory - using a realistic simulator for urban driving. Our study examines generalization to unseen towns, the effect of different camera layouts, and two loss formulations (focal and L1). Using training data from only a town, a four-camera CVT trained with the L1 loss delivers the most robust test performance, evaluated in a new town. Overall, our results underscore CVT’s promise for mapping camera inputs to reasonably accurate BEV maps.
- Open Access
Exploring multimodal implicit behavior learning for vehicle navigation in simulated cities
Standard Behavior Cloning (BC) fails to learn multimodal driving decisions, where multiple valid actions exist for the same scenario. We explore Implicit Behavioral Cloning (IBC) with Energy-Based Models (EBMs) to better capture this multimodality. We propose Data-Augmented IBC (DA-IBC), which improves learning by perturbing expert actions to form the counterexamples of IBC training and using better initialization for derivative-free inference. Experiments in the CARLA simulator with Bird's-Eye View inputs demonstrate that DA-IBC outperforms standard IBC in urban driving tasks designed to evaluate multimodal behavior learning in a test environment. The learned energy landscapes are able to represent multimodal action distributions, which BC fails to achieve.
Open AccessExploring multimodal implicit behavior learning for vehicle navigation in simulated cities
Standard Behavior Cloning (BC) fails to learn multimodal driving decisions, where multiple valid actions exist for the same scenario. We explore Implicit Behavioral Cloning (IBC) with Energy-Based Models (EBMs) to better capture this multimodality. We propose Data-Augmented IBC (DA-IBC), which improves learning by perturbing expert actions to form the counterexamples of IBC training and using better initialization for derivative-free inference. Experiments in the CARLA simulator with Bird's-Eye View inputs demonstrate that DA-IBC outperforms standard IBC in urban driving tasks designed to evaluate multimodal behavior learning in a test environment. The learned energy landscapes are able to represent multimodal action distributions, which BC fails to achieve.
- Open Access
An Initial Study of Bird's-Eye View Generation for Autonomous Vehicles using Cross-View Transformers
Bird's-Eye View (BEV) maps provide a structured, top-down abstraction that is crucial for autonomous-driving perception. In this work, we employ Cross-View Transformers (CVT) for learning to map camera images to three BEV's channels - road, lane markings, and planned trajectory - using a realistic simulator for urban driving. Our study examines generalization to unseen towns, the effect of different camera layouts, and two loss formulations (focal and L1). Using training data from only a town, a four-camera CVT trained with the L1 loss delivers the most robust test performance, evaluated in a new town. Overall, our results underscore CVT's promise for mapping camera inputs to reasonably accurate BEV maps.
Open AccessAn Initial Study of Bird's-Eye View Generation for Autonomous Vehicles using Cross-View Transformers
Bird's-Eye View (BEV) maps provide a structured, top-down abstraction that is crucial for autonomous-driving perception. In this work, we employ Cross-View Transformers (CVT) for learning to map camera images to three BEV's channels - road, lane markings, and planned trajectory - using a realistic simulator for urban driving. Our study examines generalization to unseen towns, the effect of different camera layouts, and two loss formulations (focal and L1). Using training data from only a town, a four-camera CVT trained with the L1 loss delivers the most robust test performance, evaluated in a new town. Overall, our results underscore CVT's promise for mapping camera inputs to reasonably accurate BEV maps.
- Open Access
Physics-Informed Neural Networks for Control of Single-Phase Flow Systems Governed by Partial Differential Equations
The modeling and control of single-phase flow systems governed by Partial Differential Equations (PDEs) present challenges, especially under transient conditions. In this work, we extend the Physics-Informed Neural Nets for Control (PINC) framework, originally proposed to modeling and control of Ordinary Differential Equations (ODE) without the need of any labeled data, to the PDE case, particularly to single-phase incompressible and compressible flows, integrating neural networks with physical conservation laws. The PINC model for PDEs is structured into two stages: a steady-state network, which learns equilibrium solutions for a wide range of control inputs, and a transient network, which captures dynamic responses under time-varying boundary conditions. We propose a simplifying assumption that reduces the dimensionality of the spatial coordinate regarding the initial condition, allowing the efficient training of the PINC network. This simplification enables the derivation of optimal control policies using Model Predictive Control (MPC). We validate our approach through numerical experiments, demonstrating that the PINC model, which is trained exclusively using physical laws, i.e., without labeled data, accurately represents flow dynamics and enables real-time control applications. The results highlight the PINC's capability to efficiently approximate PDE solutions without requiring iterative solvers, making it a promising alternative for fluid flow monitoring and optimization in engineering applications.
Open AccessPhysics-Informed Neural Networks for Control of Single-Phase Flow Systems Governed by Partial Differential Equations
The modeling and control of single-phase flow systems governed by Partial Differential Equations (PDEs) present challenges, especially under transient conditions. In this work, we extend the Physics-Informed Neural Nets for Control (PINC) framework, originally proposed to modeling and control of Ordinary Differential Equations (ODE) without the need of any labeled data, to the PDE case, particularly to single-phase incompressible and compressible flows, integrating neural networks with physical conservation laws. The PINC model for PDEs is structured into two stages: a steady-state network, which learns equilibrium solutions for a wide range of control inputs, and a transient network, which captures dynamic responses under time-varying boundary conditions. We propose a simplifying assumption that reduces the dimensionality of the spatial coordinate regarding the initial condition, allowing the efficient training of the PINC network. This simplification enables the derivation of optimal control policies using Model Predictive Control (MPC). We validate our approach through numerical experiments, demonstrating that the PINC model, which is trained exclusively using physical laws, i.e., without labeled data, accurately represents flow dynamics and enables real-time control applications. The results highlight the PINC's capability to efficiently approximate PDE solutions without requiring iterative solvers, making it a promising alternative for fluid flow monitoring and optimization in engineering applications.
- 22 April 2025
- Published by Elsevier in Neurocomputing
- Vol. 639
Physics-informed Echo State Networks for modeling controllable dynamical systems
- 22 April 2025
- Published by Elsevier in Neurocomputing
- Vol. 639
Physics-informed Echo State Networks for modeling controllable dynamical systems
- 30 January 2025
- Published by Springer Nature
- p. 155-168
Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving Based on Bird’s-Eye View in Simulated Cities
- 30 January 2025
- Published by Springer Nature
- p. 155-168
Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving Based on Bird’s-Eye View in Simulated Cities