Sanghani-students

Download

sanghani-students@cs.vt.edu

December 2023

1 participants
2 discussions

Guest Lecture (4th Dec): Advancing Modeling and Simulation with Physics-informed Machine Learning
by Abhijit Sarkar 01 Dec '23

01 Dec '23

Hello All, This is the second guest lecture in the series. Dr. Biswadip Dey from Siemens Technology will deliver a guest lecture for our class "ECE 4524: Artificial Intelligence and Engineering Applications" on 4th December, 2023 via Zoom. You are cordially invited if you find the topic interesting. More details below: Date: Friday Dec, 4th Time: 1:25 pm - 2:15 pm Platform: Zoom (Details below) Join Zoom Meeting https://virginiatech.zoom.us/j/84578041777?from=addon<https://www.google.com/url?q=https%3A%2F%2Fvirginiatech.zoom.us%2Fj%2F84578…> Meeting ID: 845 7804 1777 Title: Advancing Modeling and Simulation with Physics-informed Machine Learning Abstract: The widespread adoption of neural networks and deep learning has transformed numerous domains over the past decade. By exploiting large volumes of high-quality data, these approaches excel at uncovering the underlying functional relationships and achieving generalization beyond training data. However, industrial applications, which encompass condition monitoring, simulation, and control, pose a unique challenge due to limitations in data availability, requirements on model interpretability, and the need for robust generalization. To address these challenges, Physics-informed Machine Learning (PIML) has emerged as a highly sought-after methodology, particularly in the fields of modeling and simulation. PIML incorporates the underlying physics of a system into the design of the machine learning framework. In this presentation, we will explore several PIML use-cases that leverage the underlying physics (e.g., conservation laws, governing PDEs, etc.) to guide the choice of computation graphs and loss functions within deep learning frameworks. Bio: Biswadip Dey is a Senior Key Expert at Siemens Technology, where his current research focuses on physics-informed machine learning and its industrial applications. At Siemens, he collaborates extensively with the business stakeholders to identify technology white spaces where PIML offers advantages over the prevailing state-of-the-art and subsequently defines and leads research initiatives to address those gaps. Before joining Siemens, he was an Associate Research Scholar and Lecturer at Princeton University, where he focused on learning and control in complex, multi-agent systems. He earned a Ph.D. in Electrical Engineering from the University of Maryland, College Park. Earlier, he received an M.Tech. in Systems & Control Engineering from the Indian Institute of Technology Bombay, India, and a B.E. degree in Electrical Engineering from Jadavpur University, India. Thanks, Abhijit Sarkar, PhD (He/His/Him) Senior Research Associate Team Leader, Computer Vision and Machine Learning Division of Data and Analytics Virginia Tech Transportation Institute E-mail: asarkar(a)vtti.vt.edu<mailto:asarkar@vtti.vt.edu>, asarkar1(a)vt.edu<mailto:asarkar1@vt.edu> Work: (540) 231-1528 Fax: (540) 231-1555

1 0

Guest lecture: Rahul Mangharam, U Penn (1st Dec 2023)
by Abhijit Sarkar 01 Dec '23

01 Dec '23

Hello All, Dr. Rahul Mangharam from University of Pennsylvania will deliver a guest lecture for our class "ECE 4524: Artificial Intelligence and Engineering Applications" on 1st December, 2023 via Zoom. You are cordially invited if you find the topic interesting. More details below: Date: Friday Dec, 1st Time: 1:25 pm - 2:15 pm Platform: Zoom (Details below) Join Zoom Meeting https://virginiatech.zoom.us/j/84578041777?from=addon<https://www.google.com/url?q=https%3A%2F%2Fvirginiatech.zoom.us%2Fj%2F84578…> Meeting ID: 845 7804 1777 Title: MAD Games - Multi-Agent Dynamic Games: What can you learn from Autonomous Racing? Abstract: Balancing performance and safety are crucial to deploying autonomous vehicles in multi-agent environments. In particular, autonomous racing is a domain that penalizes safe but conservative policies, highlighting the need for robust, adaptive strategies. Current approaches either make simplifying assumptions about other agents or lack robust mechanisms for online adaptation. In this talk we will explore research themes on perception, planning and control at the limits of performance. We explore:(1) How to generate the most competitive agents who dynamically balance safety and assertiveness by using distributionally robust online adaptation and Game-theoretic planning (2) How to be better-than-the-best using imitation learning with multiple imperfect experts (3) Using invertible neural networks to solve inverse problems in localization and SLAM (4) How to build the most efficient autonomous racecar with Multi-domain optimization across vehicle design, planning and control; We realize all our research in the https://f1tenth.org autonomous racecar platform that is 10th the size, but 10x the fun! The main takeaway from this talk is how you can get involved in very exciting research on safe autonomous systems. I will also present projects on AV Gokart that we are doing in the Autoware Center of Excellence for Autonomous Driving. Bio: Rahul builds safe autonomous systems at the intersection of formal methods, machine learning and controls. He applies his work to safety-critical autonomous vehicles, urban air mobility, life-critical medical devices, and AI Co-designers for complex systems. He is the Penn Director for the Department of Transportation's $20MM Safety21 National UTC [2023-2028] both of which focus on technologies for safe and efficient movement of people and goods. Rahul is the Director of the Autoware Center of Excellence for Autonomous Driving, a consortium of 70+ companies and universities focused on open-source AV software for open-standards EV platforms. Rahul received the 2016 US Presidential Early Career Award (PECASE) from President Obama for his work on Life-Critical Systems. He also received the 2016 Department of Energy’s CleanTech Prize (Regional), the 2014 IEEE Benjamin Franklin Key Award, 2013 NSF CAREER Award, 2012 Intel Early Faculty Career Award and was selected by the National Academy of Engineering for the 2012 and 2017 US Frontiers of Engineering. He has won several ACM and IEEE best paper awards in Cyber-Physical Systems, controls, machine learning, and education. Thanks, Abhijit Sarkar, PhD (He/His/Him) Senior Research Associate Team Leader, Computer Vision and Machine Learning Division of Data and Analytics Virginia Tech Transportation Institute E-mail: asarkar(a)vtti.vt.edu, asarkar1(a)vt.edu Work: (540) 231-1528 Fax: (540) 231-1555

1 1