News & EventsDepartment Events
Events
-
Feb4
EVENT DETAILS
lessAbstract: This talk introduces a framework for creating interactive, physically-realistic world models by merging advanced computer vision with differentiable physics simulations. Traditional approaches to building world models often force a trade-off between high visual fidelity and accurate physics. Our work bridges this gap by leveraging differentiable programming to build high-fidelity, interactive digital twins directly from real-world sensor data. We demonstrate how modern computer vision techniques, including Neural Radiance Fields (NeRF) and 3D Gaussian Splatting, can reconstruct detailed 3D scenes from sparse video inputs. The core of our methodology is the integration of these reconstructions with fully differentiable physics engines, such as the Differentiable Material Point Method (DiffMPM). This novel combination enables us to solve challenging inverse problems: by comparing simulated outcomes with real-world observations, we use gradient-based optimization to automatically infer latent physical properties, such as soil friction angles and material stiffness, directly from video. To overcome the computational demands of these physics solvers, we utilize Graph Neural Simulators (GNS) as a learned surrogate model that significantly accelerates simulation time. GNS represents physical systems as graphs of interacting particles, achieving speedups of over 100x compared to traditional methods while generalizing effectively to new scenarios. We also present a hybrid GNS-MPM approach that interleaves the learned simulator with the numerical solver to ensure long-term accuracy and conservation of physical laws. The practical applications of this framework are highlighted through several key examples in robotics and autonomy. We present a system for generating Dynamic Costmaps from drone footage, where real-time 3D reconstruction and GNS-powered weather simulations predict terrain changes to enable safer navigation for autonomous vehicles. We also apply these methods to critical challenges in lunar exploration, such as simulating rover-regolith interaction to mitigate operational hazards. Ultimately, this research paves the way toward interactive "X2Sim" systems that can generate complex physical simulations from natural language or video prompts, opening a new paradigm for the design, control, and optimization of autonomous systems.
Bio: Dr. Krishna Kumar is a J. Neils Thompson Centennial Teaching Fellow and Associate Professor at the University of Texas at Austin and a Core-Faculty at the Oden Institute of Computational Sciences. His research is at the intersection of AI/ML, numerical simulations, and robotics. He directs a $7M NSF-funded national ecosystem for AI integration in engineering and received an NSF CAREER Award in 2024. His research involves developing physical AI and control methods for autonomous manipulation of deformable materials and navigation in extreme environments. As an educator, he received the Dean's Outstanding Teaching Award and runs coding clubs for kids at Austin Public Libraries.
TIME Wednesday, February 4, 2026 at 11:00 AM - 12:00 PM
LOCATION A230, Technological Institute map it
CONTACT Andrew Liguori andrew.liguori@northwestern.edu EMAIL
CALENDAR McCormick - Civil and Environmental Engineering (CEE)
-
Feb11
EVENT DETAILS
lessAbstract: The wildland-urban interface (WUI) fire problem continues to confound countries across the globe. The WUI fire problem is not improving and globally harmonized test standards are required to help provide community resilience in the event of WUI fire disasters. During WUI fire disasters, it has long been known that firebrand showers are a significant culprit of home ignition, leading to destruction of entire communities. Yet, an international standard to generate firebrand showers safely in a laboratory setting has only been published by the International Organization for Standardization (ISO) in 2024. An overview of the firebrand problem will be presented, including the path to develop the ISO standard firebrand generator. The presentation will also delve into ongoing efforts amongst Japan, Botswana, and South Africa, to enable the resilient communities of tomorrow in light of the increasing WUI fire danger in these countries. The presentation will close with a perspective as to whether Chicago is prepared for a potential WUI fire disaster.
Biography: Professor Samuel L. Manzello is current visiting Professor at the Institute of Fluid Science (IFS), Tohoku University, Japan and also with Reax Engineering, Inc. His research is published in more than 100 journal articles, focused on heat and mass transfer, combustion, fluid dynamics, and public health. Professor Manzello has had research features in the journal Nature and the journal Science and received several awards including a NASA Graduate Student Researcher Fellowship (NASA-GSRP), a National Research Council Post-Doctoral Fellowship (NRC), a fellowship from the Japan Society for the Promotion of Science (JSPS), a NIST Individual Bronze Medal, the 2015 Harry C. Biggelstone Award from NFPA, the 2016 Tibor Z. Harmathy Award from Springer Nature, the 2016 and 2020 Best Journal Paper Award from the Combustion Society of Japan, the 2024 Jack Bono Award from the Society of Fire Protection Engineers (SFPE) Foundation, and the 2017 Samuel Wesley Stratton Award as an individual from NIST, NIST’s highest award for fundamental research. The firebrand generator he designed and invented, known as the Dragon, is an international standard by ISO TC92, Fire Safety. He obtained a PhD in Mechanical Engineering from the University of Illinois-Chicago in microgravity droplet combustion.
TIME Wednesday, February 11, 2026 at 11:00 AM - 12:00 PM
LOCATION A230, Technological Institute map it
CONTACT Andrew Liguori andrew.liguori@northwestern.edu EMAIL
CALENDAR McCormick - Civil and Environmental Engineering (CEE)
-
Feb18
EVENT DETAILS
lessTBA
TIME Wednesday, February 18, 2026 at 11:00 AM - 12:00 PM
LOCATION A230, Technological Institute map it
CONTACT Andrew Liguori andrew.liguori@northwestern.edu EMAIL
CALENDAR McCormick - Civil and Environmental Engineering (CEE)
-
Feb27
EVENT DETAILS
lessTBA
TIME Friday, February 27, 2026 at 2:00 PM - 3:00 PM
LOCATION A230, Technological Institute map it
CONTACT Andrew Liguori andrew.liguori@northwestern.edu EMAIL
CALENDAR McCormick - Civil and Environmental Engineering (CEE)
-
Mar11
EVENT DETAILS
lessTBA
TIME Wednesday, March 11, 2026 at 11:00 AM - 12:00 PM
LOCATION A230, Technological Institute map it
CONTACT Andrew Liguori andrew.liguori@northwestern.edu EMAIL
CALENDAR McCormick - Civil and Environmental Engineering (CEE)