Live Stats

Neural Certificates for Safe Robotic System Planning and Control Abstract: Achieving safety, scalability, and high performance in complex systems, such as multi-agent systems (MAS) control, is a central challenge in many real-world robotic deployments due to its computational complexity as a large-scale constrained optimal control problem. To address this, we introduce a novel graph control barrier function (GCBF) as a core tool for large-scale distributed safe control, which guarantees safety for arbitrarily large MAS with only local observations. For MAS with known dynamic models, we present a self-supervised learning framework that can jointly learn GCBF and distributed control policies that consider actuation limits. For MAS with unknown dynamics, we discuss how to blend GCBF in multi-agent reinforcement learning (MARL) to achieve high-performance and safe distributed policies. Bio: Chuchu Fan is an Associate Professor (pre-tenure) in the Department of Aeronautics and Astronautics (AeroAstro) and Laboratory for Information and Decision Systems (LIDS) at MIT. Before that, she was a postdoc researcher at Caltech and got her Ph.D. at the University of Illinois at Urbana-Champaign. She earned her bachelor’s degree from Tsinghua University. Her research group, the Realm at MIT, works on developing computational tools that integrate rigorous mathematics into machine learning and AI for the design, analysis, and verification of safe, large-scale, and complex systems. Chuchu is the recipient of an NSF CAREER Award, an AFOSR Young Investigator Program (YIP) Award, an ONR YIP Award, and the 2020 ACM Doctoral Dissertation Award.

Looking for a way to make your day less stressful and more mindful...take some much-needed time for yourself and join us for Mindful Thursdays! Drop-in meditation sessions are open to the entire WPI community, and no experience is necessary. A certified meditation teacher will offer guided meditations appropriate for both beginners as well as experienced meditators. People can join in person or via zoom. Mindful Thursdays: 2:15PM to 2:35PM Center for Well-Being, Daniels Hall 102E Zoom: https://wpi.zoom.us/j/186050714 Each Friday an email will be sent out to the group called Mindfulness Tools To-Go which will include information about meditations, poems shared during the week, and mindful resources. If you have questions or suggestions, please do not hesitate to contact Robin Benoit, rbenoit@wpi.edu

Global Asia Hub invites Dr. Andrew Erickson, Visiting Scholar Harvard Fairbank Center for Chinese Studies and Prof of Strategy,China Maritime Studies Institute, US Naval War College to give a presentation discussing China's sea forces and XI seeks to use them in a time of dangerous shifting power dynamics. China under Xi Jinping has become a great maritime power, possessing the world's largest fleets numerically in every maritime category.

Be well at home while celebrating Wellness Day on November 4th. Drop by the Center for Well-Being or the lobby of Gateway 1 (60 Prescott) starting on Friday, October 31st to pick up your Wellness @ Home Kit to help de-stress and relax. Kits will be available October 31-November 4 or until we run out. Get one before they are gone! Sponsored by the CWB.

Department of Mathematical SciencesColloquiumFriday, October 31st, 202511:00AM-11:50AMStratton Hall 202Speaker: George Yin, University of ConnecticutTitle: Computational Nonlinear Filtering: A Deep Learning ApproachAbstract: Nonlinear filtering is a fundamental problem in signal processing, information theory, communication, control and optimization, and systems theory. In the 1960s, celebrated results on nonlinear filtering such the Kushner equation and the Duncan-Motensen-Zakai equation were obtained. Nevertheless, the computational issues for nonlinear filtering remained to be a long-standing and challenging problem. In this talk, in lieu of treating the stochastic partial differential equations for obtaining the conditional distribution or conditional measure, we construct finite-dimensional approximations using deep neural networks for the optimal weights. Two recursions are used in the algorithm. One of them is the approximation of the optimal weight and the other is for approximating the optimal learning rate. Convergence and rates of convergence will be discussed together with some examples. [This is a joint work with Hongjiang Qian (Auburn University) and Qing Zhang (University of Georgia).]