SAM
https://sam.ensam.eu:443
The DSpace digital repository system captures, stores, indexes, preserves, and distributes digital research material.Sat, 13 Jul 2024 19:37:33 GMT2024-07-13T19:37:33ZReduced order modeling for physically-based augmented reality
http://hdl.handle.net/10985/13809
Reduced order modeling for physically-based augmented reality
BADIAS, Alberto; GONZALEZ, David; CUETO, Elias; ALFARO, Icíar; CHINESTA SORIA, Francisco
In this work we explore the possibilities of reduced order modeling for augmented reality applications. We consider parametric reduced order models based upon separate (affine) parametric dependence so as to speedup the associated data assimilation problems, which involve in a natural manner the minimization of a distance functional. The employ of reduced order methods allows for an important reduction in computational cost, thus allowing to comply with the stringent real time constraints of video streams, i.e., around 30 Hz. Examples are included that show the potential of the proposed technique in different situations.
Mon, 01 Jan 2018 00:00:00 GMThttp://hdl.handle.net/10985/138092018-01-01T00:00:00ZBADIAS, AlbertoGONZALEZ, DavidCUETO, EliasALFARO, IcíarCHINESTA SORIA, FranciscoIn this work we explore the possibilities of reduced order modeling for augmented reality applications. We consider parametric reduced order models based upon separate (affine) parametric dependence so as to speedup the associated data assimilation problems, which involve in a natural manner the minimization of a distance functional. The employ of reduced order methods allows for an important reduction in computational cost, thus allowing to comply with the stringent real time constraints of video streams, i.e., around 30 Hz. Examples are included that show the potential of the proposed technique in different situations.MORPH-DSLAM: Model Order Reduction for Physics-Based Deformable SLAM
http://hdl.handle.net/10985/23641
MORPH-DSLAM: Model Order Reduction for Physics-Based Deformable SLAM
BADIAS, Alberto; GONZALEZ, David; CUETO, Elias; ALFARO, Icíar; CHINESTA SORIA, Francisco
We propose a new methodology to estimate the 3D displacement field of deformable objects from video sequences using standard monocular cameras. We solve in real time the complete (possibly visco-)hyperelasticity problem to properly describe the strain and stress fields that are consistent with the displacements captured by the images, constrained by real physics. We do not impose any ad-hoc prior or energy minimization in the external surface, since the real and complete mechanics problem is solved. This means that we can also estimate the internal state of the objects, even in occluded areas, just by observing the external surface and the knowledge of material properties and geometry. Solving this problem in real time using a realistic constitutive law, usually non-linear, is out of reach for current systems. To overcome this difficulty, we solve off-line a parametrized problem that considers each source of variability in the problem as a new parameter and, consequently, as a new dimension in the formulation. Model Order Reduction methods allow us to reduce the dimensionality of the problem, and therefore, its computational cost, while preserving the visualization of the solution in the high-dimensionality space. This allows an accurate estimation of the object deformations, improving also the robustness in the 3D points estimation.
Tue, 01 Nov 2022 00:00:00 GMThttp://hdl.handle.net/10985/236412022-11-01T00:00:00ZBADIAS, AlbertoGONZALEZ, DavidCUETO, EliasALFARO, IcíarCHINESTA SORIA, FranciscoWe propose a new methodology to estimate the 3D displacement field of deformable objects from video sequences using standard monocular cameras. We solve in real time the complete (possibly visco-)hyperelasticity problem to properly describe the strain and stress fields that are consistent with the displacements captured by the images, constrained by real physics. We do not impose any ad-hoc prior or energy minimization in the external surface, since the real and complete mechanics problem is solved. This means that we can also estimate the internal state of the objects, even in occluded areas, just by observing the external surface and the knowledge of material properties and geometry. Solving this problem in real time using a realistic constitutive law, usually non-linear, is out of reach for current systems. To overcome this difficulty, we solve off-line a parametrized problem that considers each source of variability in the problem as a new parameter and, consequently, as a new dimension in the formulation. Model Order Reduction methods allow us to reduce the dimensionality of the problem, and therefore, its computational cost, while preserving the visualization of the solution in the high-dimensionality space. This allows an accurate estimation of the object deformations, improving also the robustness in the 3D points estimation.Empowering Advanced Driver-Assistance Systems from Topological Data Analysis
http://hdl.handle.net/10985/20177
Empowering Advanced Driver-Assistance Systems from Topological Data Analysis
FRAHI, Tarek; FALCO, Antonio; BADIAS, Alberto; CUETO, Elias; CHOI, Hyung Yun; HAN, Manyong; DUVAL, Jean-Louis; CHINESTA SORIA, Francisco
We are interested in evaluating the state of drivers to determine whether they are attentive to the road or not by using motion sensor data collected from car driving experiments. That is, our goal is to design a predictive model that can estimate the state of drivers given the data collected from motion sensors. For that purpose, we leverage recent developments in topological data analysis (TDA) to analyze and transform the data coming from sensor time series and build a machine learning model based on the topological features extracted with the TDA. We provide some experiments showing that our model proves to be accurate in the identification of the state of the user, predicting whether they are relaxed or tense.
Fri, 01 Jan 2021 00:00:00 GMThttp://hdl.handle.net/10985/201772021-01-01T00:00:00ZFRAHI, TarekFALCO, AntonioBADIAS, AlbertoCUETO, EliasCHOI, Hyung YunHAN, ManyongDUVAL, Jean-LouisCHINESTA SORIA, FranciscoWe are interested in evaluating the state of drivers to determine whether they are attentive to the road or not by using motion sensor data collected from car driving experiments. That is, our goal is to design a predictive model that can estimate the state of drivers given the data collected from motion sensors. For that purpose, we leverage recent developments in topological data analysis (TDA) to analyze and transform the data coming from sensor time series and build a machine learning model based on the topological features extracted with the TDA. We provide some experiments showing that our model proves to be accurate in the identification of the state of the user, predicting whether they are relaxed or tense.A thermodynamics-informed active learning approach to perception and reasoning about fluids
http://hdl.handle.net/10985/24727
A thermodynamics-informed active learning approach to perception and reasoning about fluids
MOYA GARCÍA, Beatriz; BADIAS, Alberto; GONZALEZ, David; CHINESTA SORIA, Francisco; CUETO
Learning and reasoning about physical phenomena is still a challenge in robotics development, and computational sciences
play a capital role in the search for accurate methods able to provide explanations for past events and rigorous forecasts
of future situations. We propose a thermodynamics-informed active learning strategy for fluid perception and reasoning
from observations. As a model problem, we take the sloshing phenomena of different fluids contained in a glass. Starting
from full-field and high-resolution synthetic data for a particular fluid, we develop a method for the tracking (perception)
and simulation (reasoning) of any previously unseen liquid whose free surface is observed with a commodity camera. This
approach demonstrates the importance of physics and knowledge not only in data-driven (gray-box) modeling but also in
real-physics adaptation in low-data regimes and partial observations of the dynamics. The presented method is extensible to
other domains such as the development of cognitive digital twins able to learn from observation of phenomena for which they
have not been trained explicitly.
Sun, 01 Jan 2023 00:00:00 GMThttp://hdl.handle.net/10985/247272023-01-01T00:00:00ZMOYA GARCÍA, BeatrizBADIAS, AlbertoGONZALEZ, DavidCHINESTA SORIA, FranciscoCUETOLearning and reasoning about physical phenomena is still a challenge in robotics development, and computational sciences
play a capital role in the search for accurate methods able to provide explanations for past events and rigorous forecasts
of future situations. We propose a thermodynamics-informed active learning strategy for fluid perception and reasoning
from observations. As a model problem, we take the sloshing phenomena of different fluids contained in a glass. Starting
from full-field and high-resolution synthetic data for a particular fluid, we develop a method for the tracking (perception)
and simulation (reasoning) of any previously unseen liquid whose free surface is observed with a commodity camera. This
approach demonstrates the importance of physics and knowledge not only in data-driven (gray-box) modeling but also in
real-physics adaptation in low-data regimes and partial observations of the dynamics. The presented method is extensible to
other domains such as the development of cognitive digital twins able to learn from observation of phenomena for which they
have not been trained explicitly.Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems
http://hdl.handle.net/10985/24724
Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems
HERNÁNDEZ, Quercus; BADIAS, Alberto; CHINESTA SORIA, Francisco; CUETO, Elias
We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of energy, non-negative entropy production), we modify accordingly the port-Hamiltonian formalism so as to achieve a port-metriplectic one. We show that the constructed networks are able to learn the physics of complex systems by parts, thus alleviating the burden associated to the experimental characterization and posterior learning process of this kind of systems. Predictions can be done, however, at the scale of the complete system. Examples are shown on the performance of the proposed technique.
Sun, 01 Jan 2023 00:00:00 GMThttp://hdl.handle.net/10985/247242023-01-01T00:00:00ZHERNÁNDEZ, QuercusBADIAS, AlbertoCHINESTA SORIA, FranciscoCUETO, EliasWe develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of energy, non-negative entropy production), we modify accordingly the port-Hamiltonian formalism so as to achieve a port-metriplectic one. We show that the constructed networks are able to learn the physics of complex systems by parts, thus alleviating the burden associated to the experimental characterization and posterior learning process of this kind of systems. Predictions can be done, however, at the scale of the complete system. Examples are shown on the performance of the proposed technique.Thermodynamics-informed neural networks for physically realistic mixed reality
http://hdl.handle.net/10985/24750
Thermodynamics-informed neural networks for physically realistic mixed reality
HERNÁNDEZ, Quercus; BADIAS, Alberto; CHINESTA SORIA, Francisco; CUETO, Elias
The imminent impact of immersive technologies in society urges for active research in real-time and interactive physics simulation for virtual worlds to be realistic. In this context, realistic means to be compliant to the laws of physics. In this paper we present a method for computing the dynamic response of (possibly non-linear and dissipative) deformable objects induced by real-time user interactions in mixed reality using deep learning. The graph-based architecture of the method ensures the thermodynamic consistency of the predictions, whereas the visualization pipeline allows a natural and realistic user experience. Two examples of virtual solids interacting with virtual or physical solids in mixed reality scenarios are provided to prove the performance of the method.
Sun, 01 Jan 2023 00:00:00 GMThttp://hdl.handle.net/10985/247502023-01-01T00:00:00ZHERNÁNDEZ, QuercusBADIAS, AlbertoCHINESTA SORIA, FranciscoCUETO, EliasThe imminent impact of immersive technologies in society urges for active research in real-time and interactive physics simulation for virtual worlds to be realistic. In this context, realistic means to be compliant to the laws of physics. In this paper we present a method for computing the dynamic response of (possibly non-linear and dissipative) deformable objects induced by real-time user interactions in mixed reality using deep learning. The graph-based architecture of the method ensures the thermodynamic consistency of the predictions, whereas the visualization pipeline allows a natural and realistic user experience. Two examples of virtual solids interacting with virtual or physical solids in mixed reality scenarios are provided to prove the performance of the method.Physics Perception in Sloshing Scenes With Guaranteed Thermodynamic Consistency
http://hdl.handle.net/10985/24796
Physics Perception in Sloshing Scenes With Guaranteed Thermodynamic Consistency
MOYA, Beatriz; BADIAS, Alberto; GONZALEZ, David; CHINESTA SORIA, Francisco; CUETO, Elias
Physics perception very often faces the problem that only limited data or partial measurements on the scene are available. In this work, we propose a strategy to learn the full state of sloshing liquids from measurements of the free surface. Our approach is based on recurrent neural networks (RNN) that project the limited information available to a reduced-order manifold to not only reconstruct the unknown information but also be capable of performing fluid reasoning about future scenarios in real-time. To obtain physically consistent predictions, we train deep neural networks on the reduced-order manifold that, through the employ of inductive biases, ensure the fulfillment of the principles of thermodynamics. RNNs learn from history the required hidden information to correlate the limited information with the latent space where the simulation occurs. Finally, a decoder returns data to the high-dimensional manifold, to provide the user with insightful information in the form of augmented reality. This algorithm is connected to a computer vision system to test the performance of the proposed methodology with real information, resulting in a system capable of understanding and predicting future states of the observed fluid in real-time.
Sun, 01 Jan 2023 00:00:00 GMThttp://hdl.handle.net/10985/247962023-01-01T00:00:00ZMOYA, BeatrizBADIAS, AlbertoGONZALEZ, DavidCHINESTA SORIA, FranciscoCUETO, EliasPhysics perception very often faces the problem that only limited data or partial measurements on the scene are available. In this work, we propose a strategy to learn the full state of sloshing liquids from measurements of the free surface. Our approach is based on recurrent neural networks (RNN) that project the limited information available to a reduced-order manifold to not only reconstruct the unknown information but also be capable of performing fluid reasoning about future scenarios in real-time. To obtain physically consistent predictions, we train deep neural networks on the reduced-order manifold that, through the employ of inductive biases, ensure the fulfillment of the principles of thermodynamics. RNNs learn from history the required hidden information to correlate the limited information with the latent space where the simulation occurs. Finally, a decoder returns data to the high-dimensional manifold, to provide the user with insightful information in the form of augmented reality. This algorithm is connected to a computer vision system to test the performance of the proposed methodology with real information, resulting in a system capable of understanding and predicting future states of the observed fluid in real-time.Deep learning of thermodynamics-aware reduced-order models from data
http://hdl.handle.net/10985/20176
Deep learning of thermodynamics-aware reduced-order models from data
HERNANDEZ, Quercus; BADIAS, Alberto; GONZALEZ, David; CUETO, Elias; CHINESTA SORIA, Francisco
We present an algorithm to learn the relevant latent variables of a large-scale discretized physical system and predict its time evolution using thermodynamically-consistent deep neural networks. Our method relies on sparse autoencoders, which reduce the dimensionality of the full order model to a set of sparse latent variables with no prior knowledge of the coded space dimensionality. Then, a second neural network is trained to learn the metriplectic structure of those reduced physical variables and predict its time evolution with a so-called structure-preserving neural network. This data-based integrator is guaranteed to conserve the total energy of the system and the entropy inequality, and can be applied to both conservative and dissipative systems. The integrated paths can then be decoded to the original full-dimensional manifold and be compared to the ground truth solution. This method is tested with two examples applied to fluid and solid mechanics.
Fri, 01 Jan 2021 00:00:00 GMThttp://hdl.handle.net/10985/201762021-01-01T00:00:00ZHERNANDEZ, QuercusBADIAS, AlbertoGONZALEZ, DavidCUETO, EliasCHINESTA SORIA, FranciscoWe present an algorithm to learn the relevant latent variables of a large-scale discretized physical system and predict its time evolution using thermodynamically-consistent deep neural networks. Our method relies on sparse autoencoders, which reduce the dimensionality of the full order model to a set of sparse latent variables with no prior knowledge of the coded space dimensionality. Then, a second neural network is trained to learn the metriplectic structure of those reduced physical variables and predict its time evolution with a so-called structure-preserving neural network. This data-based integrator is guaranteed to conserve the total energy of the system and the entropy inequality, and can be applied to both conservative and dissipative systems. The integrated paths can then be decoded to the original full-dimensional manifold and be compared to the ground truth solution. This method is tested with two examples applied to fluid and solid mechanics.