Title:

Spiking Nonlinear Opinion Dynamics (S-NOD) for Agile Decision-Making and Control

Speaker:

Naomi Ehrich Leonard, Princeton University

Abstract:

I will introduce Spiking Nonlinear Opinion Dynamics (S-NOD), which enables decision-making and control with superior agility in responding to and adapting to fast and unpredictable changes in context, environment, or information received about available options. S-NOD derives through the introduction of an extra term to the previously presented Nonlinear Opinion Dynamics (NOD), which have been shown to provide fast and flexible multiagent behavior. The term is inspired by the fast-positive, slow-negative mixed-feedback structure of excitable systems. The agile behaviors brought about by the new excitable nature of decision-making driven by S-NOD are analyzed in a general setting and illustrated in applications to robot navigation around human movers and to control of soft robotics.

Bio:

Naomi Ehrich Leonard is Chair and Edwin S. Wilsey Professor of Mechanical and Aerospace Engineering, associated faculty with the Program in Applied and Computational Mathematics and the Biophysics Graduate Program, and affiliated faculty with the Princeton Neuroscience Institute at Princeton University. She is Founding Director of creativeX, a Princeton engineering-and-the-arts collective, and Founding Editor of Annual Review of Control, Robotics, and Autonomous Systems. Leonard received her B.S.E. in Mechanical Engineering from Princeton University and her Ph.D. in Electrical Engineering from the University of Maryland. She is a MacArthur Fellow, member of the American Academy of Arts and Sciences, Fellow of the ASME, IEEE, IFAC, and SIAM, and recipient of the 2023 IEEE Control Systems Award and 2024 Richard E. Bellman Control Heritage Award. Her current research focuses on dynamics, control, and learning for multiagent systems on networks with application to multi-robot teams, collective animal behavior, and other networked systems in technology, nature, and the arts.

Machine Learning Enabled Parametric Multiscale Modeling of Metals & Composites: From Fatigue Crack Nucleation to Damage Sensing

Professor Somnath Ghosh

Civil & Systems Engineering, Mechanical Engineering, and Materials Science & Engineering

Johns Hopkins University

The rapid surge of machine learning (ML) tools in developing efficient surrogate models for solving challenging problems has drawn significant attention from the Mechanics of Materials community. However, ML techniques rely on extensive training datasets and often lack physical interpretability. Also, exclusively data-driven models can result in ill-posed problems or non-physical solutions. Alternatively, the notion of ML-enhanced parametric upscaling has been introduced for multi-scale analysis of fatigue failure in metallics materials, damage and failure of unidirectional and woven composites, and damage sensing in multifunctional composites. The Parametrically Upscaled Constitutive Model (PUCM) for metallic materials like Ti alloys and the Parametrically Upscaled Continuum Damage Mechanics Model (PUCDM) for composites are thermodynamically-consistent constitutive models that bridge multiple spatial scales through the explicit representation of representative aggregated microstructural parameters (RAMPs), representing statistical distributions of morphological and crystallographic descriptors of the microstructure. ML tools, viz. genetic programming-based symbolic regression (GPSR) and artificial neural networks (ANN) are implemented for generating PUCM/PUCDM coefficients as functions of lower-scale RAMPs, using data sets of homogenized micromechanical response variables. For damage sensing in piezocomposite structures, the Parametrically Upscaled Coupled Constitutive Damage Model (PUCCDM) is developed coupling mechanical, damage, and electrical fields. An advanced machine learning model (ConvLSTM) based on the combination of a convolutional neural network and a recurrent neural network is developed to predict microstructural damage mechanisms from macroscopic electric signal and RAMPs. The computational tool chain outputs the highly efficient PUCM/PUCDM/PUCCDM, which are invaluable tools for multiscale analysis with implications in location-specific design.