135 citations · 473 across the 31 of their papers we have counts for
34 papers
MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos
Daniel Rho, Jun Myeong Choi, Matthew Thornton +2
Existing inverse physics methods recover physical parameters from multi-view videos, where geometric constraints across views resolve scale and 3D structure. In monocular settings,…
Co-Learning Port-Hamiltonian Systems and Optimal Energy-Shaping Control
Ankur Kamboj, Biswadip Dey, Vaibhav Srivastava
We develop a physics-informed learning framework for energy-shaping control of port-Hamiltonian (pH) systems from trajectory data. The proposed approach co-learns a pH system model…
ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimation
Daniel Rho, Jun Myeong Choi, Biswadip Dey +1
Neural rendering has advanced significantly in 3D reconstruction and novel view synthesis, and integrating physics into these frameworks opens new applications such as physically a…
Geometry-aware PINNs for Turbulent Flow Prediction
Shinjan Ghosh, Julian Busch, Georgia Olympia Brikis +1
Design exploration or optimization using computational fluid dynamics (CFD) is commonly used in the industry. Geometric variation is a key component of such design problems, especi…
Using Parametric PINNs for Predicting Internal and External Turbulent Flows
Shinjan Ghosh, Amit Chakraborty, Georgia Olympia Brikis +1
Computational fluid dynamics (CFD) solvers employing two-equation eddy viscosity models are the industry standard for simulating turbulent flows using the Reynolds-averaged Navier-…
Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems
Truong X. Nghiem, Ján Drgoňa, Colin Jones +10
Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathema…
RANS-PINN based Simulation Surrogates for Predicting Turbulent Flows
Shinjan Ghosh, Amit Chakraborty, Georgia Olympia Brikis +1
Physics-informed neural networks (PINNs) provide a framework to build surrogate models for dynamical systems governed by differential equations. During the learning process, PINNs…
Improving Gradient Computation for Differentiable Physics Simulation with Contacts
Yaofeng Desmond Zhong, Jiequn Han, Biswadip Dey +1
Differentiable simulation enables gradients to be back-propagated through physics simulations. In this way, one can learn the dynamics and properties of a physics system by gradien…
A Neural ODE Interpretation of Transformer Layers
Yaofeng Desmond Zhong, Tongtao Zhang, Amit Chakraborty +1
Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning pr…
Flocks, Games, and Cognition: A Geometric Approach
Udit Halder, Vidya Raju, Matteo Mischiati +2
Avian flocks display a wide variety of flight behaviors, including steady directed translation of center of mass, rapid change of overall morphology, re-shuffling of positions of i…
EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System
Haoran Su, Yaofeng D. Zhong, Joseph Y. J. Chow +2
Emergency vehicles (EMVs) play a crucial role in responding to time-critical calls such as medical emergencies and fire outbreaks in urban areas. Existing methods for EMV dispatch…
Demystifying the Data Need of ML-surrogates for CFD Simulations
Tongtao Zhang, Biswadip Dey, Krishna Veeraraghavan +2
Computational fluid dynamics (CFD) simulations, a critical tool in various engineering applications, often require significant time and compute power to predict flow properties. Th…
Physics-informed neural networks for modeling rate- and temperature-dependent plasticity
Rajat Arora, Pratik Kakkar, Biswadip Dey +1
This work presents a physics-informed neural network (PINN) based framework to model the strain-rate and temperature dependence of the deformation fields in elastic-viscoplastic so…
A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles
Haoran Su, Yaofeng Desmond Zhong, Biswadip Dey +1
Emergency vehicles (EMVs) play a critical role in a city's response to time-critical events such as medical emergencies and fire outbreaks. The existing approaches to reduce EMV tr…
EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles
Haoran Su, Yaofeng Desmond Zhong, Biswadip Dey +1
Emergency vehicles (EMVs) play a crucial role in responding to time-critical events such as medical emergencies and fire outbreaks in an urban area. The less time EMVs spend travel…
Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models
Yaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty
The incorporation of appropriate inductive bias plays a critical role in learning dynamics from data. A growing body of work has been exploring ways to enforce energy conservation…
Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Data
Yaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty
The last few years have witnessed an increased interest in incorporating physics-informed inductive bias in deep learning frameworks. In particular, a growing volume of literature…
Frequency-compensated PINNs for Fluid-dynamic Design Problems
Tongtao Zhang, Biswadip Dey, Pratik Kakkar +2
Incompressible fluid flow around a cylinder is one of the classical problems in fluid-dynamics with strong relevance with many real-world engineering problems, for example, design…
On Using Hamiltonian Monte Carlo Sampling for Reinforcement Learning Problems in High-dimension
Udari Madhushani, Biswadip Dey, Naomi Ehrich Leonard +1
Value function based reinforcement learning (RL) algorithms, for example, -learning, learn optimal policies from datasets of actions, rewards, and state transitions. However, wh…
Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning
Yaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty
In this work, we introduce Dissipative SymODEN, a deep learning architecture which can infer the dynamics of a physical system with dissipation from observed state trajectories. To…
Beacon-referenced Pursuit for Collective Motions in Three Dimensions
Kevin S. Galloway, Biswadip Dey
Motivated by real-world applications of unmanned aerial vehicles, this paper introduces a decentralized control mechanism to guide steering control of autonomous agents maneuvering…
A Conditional Generative Model for Predicting Material Microstructures from Processing Methods
Akshay Iyer, Biswadip Dey, Arindam Dasgupta +2
Microstructures of a material form the bridge linking processing conditions - which can be controlled, to the material property - which is the primary interest in engineering appli…
Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control
Yaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty
In this paper, we introduce Symplectic ODE-Net (SymODEN), a deep learning framework which can infer the dynamics of a physical system, given by an ordinary differential equation (O…
Social decision-making driven by artistic explore-exploit tension
Kayhan Ozcimder, Biswadip Dey, Alessio Franci +3
We studied social decision-making in the rule-based improvisational dance , where dancers make in-the-moment compositional choices. Rehearsals provided…