BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250422T100000
DTEND;TZID=America/New_York:20250422T110000
DTSTAMP:20260403T174649
CREATED:20250414T200632Z
LAST-MODIFIED:20250414T200632Z
UID:10008364-1745316000-1745319600@seasevents.nmsdev7.com
SUMMARY:MEAM Master's Thesis Defense: "In Situ Additive Manufacturing of Metal-Graphene Composites by Upcycling Polymers"
DESCRIPTION:Laser powder bed fusion (LPBF) is a bourgeoning additive manufacturing technique for rapid prototyping and creating unconventional designs using metal alloys. In parallel\, graphene has garnered significant research interest since its discovery\, owing to its remarkable mechanical and transport properties. Driven by the potential advances in additive manufacturing\, this project aims to harness the intrinsically high energy densities characteristic of LPBF for in situ formation of graphene using polymers as a direct carbon source during the metal 3D printing process. This innovative approach provides a comprehensive understanding of the underlying graphene formation mechanisms and to thoroughly characterize the resulting metal-graphene systems produced via LPBF. This thesis project investigates the processing parameters and properties of these 3D metal-graphene composites in comparison to conventional metal alloys.
URL:https://seasevents.nmsdev7.com/event/meam-masters-thesis-defense-in-situ-additive-manufacturing-of-metal-graphene-composites-by-upcycling-polymers/
LOCATION:4E9\, DRLB\, 209 S. 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Dissertation or Thesis Defense,Master's
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250422T100000
DTEND;TZID=America/New_York:20250422T110000
DTSTAMP:20260403T174649
CREATED:20250421T142135Z
LAST-MODIFIED:20250421T142135Z
UID:10008374-1745316000-1745319600@seasevents.nmsdev7.com
SUMMARY:Spring 2025 GRASP Seminar: Robin Walters\, Northeastern University\, "Pushing the Limits of Equivariant Neural Networks"
DESCRIPTION:This will be a hybrid event with in-person attendance in AGH 306 and virtual attendance on Zoom. \nABSTRACT\nDespite the success of deep learning\, there remain challenges to progress. Deep models require vast datasets to train\, can fail to generalize under surprisingly small changes in domain\, and lack guarantees on performance. Incorporating symmetry constraints into neural networks has resulted in models called equivariant neural networks (ENN) which have helped address these challenges. I will discuss several successful applications\, such as trajectory prediction\, ocean currents forecasting\, and robotic control. However\, there are also limits to the effectiveness of current ENNs.  In many applications where symmetry is only approximate or does apply across the entire input distribution\, equivariance may not be the correct inductive bias to aid learning and may even hurt model performance.  I will discuss recent work theoretically characterizing errors that can result from mismatched symmetry biases which can be used for model selection. I will also suggest different methods for relaxing symmetry constraints so that approximately equivariant models can still be used in these situations.
URL:https://seasevents.nmsdev7.com/event/spring-2025-grasp-seminar-robin-walters-northeastern-university-pushing-the-limits-of-equivariant-neural-networks/
LOCATION:Amy Gutmann Hall\, Room 306\, 3317 Chestnut Street\, Philadelphia\, PA\, 19104\, United States
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250422T101500
DTEND;TZID=America/New_York:20250422T111500
DTSTAMP:20260403T174649
CREATED:20250401T205301Z
LAST-MODIFIED:20250401T205301Z
UID:10008346-1745316900-1745320500@seasevents.nmsdev7.com
SUMMARY:MEAM Seminar: "Biomedical Innovations for Global Health Research and Technology (BIGHEART): NOAS\, EXODUS\, iTEARS\, and BOAS"
DESCRIPTION:This presentation will discuss the concept of BIGHEART and present various illustrative examples of this approach. The initial focus will be on NOAS (Nanoscale Optical Antennas) within the context of quantitative life sciences and transformative medicine. NOAS facilitates the visualization of quantum biological electron transfer processes occurring in mitochondria within living cells\, supports the precise release of siRNAs with accurate spatiotemporal control\, enables the detection of oscillatory communication among living bacteria via extracellular vesicles\, and innovates ultrafast photonic PCR technology for enhanced precision in preventive medicine. EXODUS (Exosome Detection via the Ultrafast-Purification System) is meticulously designed to facilitate accurate diagnostics and therapeutic applications through the utilization of exosomes. The effective purification of exosomes from patients’ liquid biopsies enables comprehensive analyses and the advancement of translational medical treatments. iTEARS (Integrated Tear Exosome Analysis via Rapid-Isolation System) allows the detection of protein and miRNA biomarkers\, thereby enhancing the diagnostic capability of various diseases through the analysis of tear samples. BOAS (Brain Organoid Analysis System)\, which integrates biosensors and EEG for real-time\, non-invasive monitoring of brainwaves and extracellular vesicles (EVs)\, was developed to explore the connections between molecular signals and neurophysiological brainwaves. This study critically analyzes and offers insights into the interrelationships among secretomes\, electrophysiological brainwaves\, and the networks generated from human brain organoids. The in vitro models of BOAS serve as valuable tools for researchers investigating neuropathogenesis\, developing treatments for neurodegenerative diseases\, and exploring preventive medical therapies by studying the interactions between EVs and brainwaves. Furthermore\, the BIGHEART initiative endeavors to create solutions for preventive and personalized medicine that contribute to affordable global healthcare.
URL:https://seasevents.nmsdev7.com/event/meam-seminar-biomedical-innovations-for-global-health-research-and-technology-bigheart-noas-exodus-itears-and-boas/
LOCATION:Wu & Chen Auditorium
CATEGORIES:Seminar
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250422T101500
DTEND;TZID=America/New_York:20250422T114500
DTSTAMP:20260403T174649
CREATED:20250421T154457Z
LAST-MODIFIED:20250421T154457Z
UID:10008375-1745316900-1745322300@seasevents.nmsdev7.com
SUMMARY:CBE Doctoral Dissertation Defense: "Designing Solvent-Based Order Parameters for Characterizing Binding of Surfaces with Different Hydrophobicity Using Molecular Dynamics Simulations" (Jun Lu)
DESCRIPTION:Abstract: \n\n\n\nLife is dependent on water: most self-assembly and binding processes of biomolecules take place in water. Water-mediated interactions are an essential driving force behind these processes\, which is largely affected by the hydrophobicity of the binding surfaces. As many biomolecular binding interfaces are amphiphilic\, the hydrophobic interactions are largely affected by polar and charged groups near hydrophobic binding domains. Therefore\, the study of interactions between hydrophobic surfaces and hydrophilic surfaces are of great importance. We find that on the two extremes: purely hydrophobic and hydrophilic systems\, traditional sampling approaches in molecular dynamics (MD) simulations become ineffective for different reasons. Here\, we study the binding of surfaces with different hydrophobicity using the MD approach with specifically designed solvent-based order parameters to control. By sensibly choosing order parameter sets from 1. Separation distance\, 2. Solvent coordinates\, and 3. Electrostatic energy to control\, sampling pathologies can be mostly solved and the thermodynamics of binding of surfaces with different hydrophobicity can be studied.
URL:https://seasevents.nmsdev7.com/event/cbe-doctoral-dissertation-defense-designing-solvent-based-order-parameters-for-characterizing-binding-of-surfaces-with-different-hydrophobicity-using-molecular-dynamics-simulations-jun-lu/
LOCATION:Greenberg Lounge (Room 114)\, Skirkanich Hall\, 210 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Doctoral,Student,Dissertation or Thesis Defense
ORGANIZER;CN="Chemical and Biomolecular Engineering":MAILTO:cbemail@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250422T121500
DTEND;TZID=America/New_York:20250422T131500
DTSTAMP:20260403T174649
CREATED:20250417T140906Z
LAST-MODIFIED:20250417T140906Z
UID:10008369-1745324100-1745327700@seasevents.nmsdev7.com
SUMMARY:ESE Ph.D. Thesis Defense: "Graph Neural Networks for Communication in Multi-Agent Systems"
DESCRIPTION:Communication networks support a wide range of applications in multi-agent systems by solving core problems such as routing\, scheduling\, and resource allocation. In this thesis\, we focus on data-driven routing and scheduling strategies using local information subject to constraints using Graph Neural Networks (GNNs). First\, we study information routing in communication networks with constant channel conditions and formulate it as a constrained learning problem. We propose a novel State Augmentation strategy to achieve faster convergence and achieve decentralized implementation using GNNs. The state augmentation based optimization framework leverages graph convolutions to generate optimal routing decisions using only local information from the nearby neighbors and achieves competitive performance without the need for supervision or global knowledge. Second\, we extend the framework to opportunistic routing in wireless networks\, where we leverage the broadcast nature of wireless channels for dynamic relay node selection. We integrate state augmentation with GNN-based distributed optimization to learn efficient routing policies that maximize end-to-end throughput. The learned models can be generalized across varying network sizes and multiple flows which are very robust to network variations. Third\, we design a real-time wireless ad-hoc network testbed to validate the proposed routing strategies under realistic channel conditions. Our evaluation demonstrates that the state augmentation combined GNN framework validates the simulational algorithms in terms of queue length stability while retaining stability and transferability properties without the requirement for retraining. Overall\, this thesis presents a scalable and decentralized approach to intelligent routing and scheduling in multi-agent systems by bridging graph-based learning with network optimization\, offering practical solutions for large-scale and dynamic communication systems.
URL:https://seasevents.nmsdev7.com/event/ese-ph-d-thesis-defense-graph-neural-networks-for-communication-in-multi-agent-systems/
LOCATION:Room 313\, Singh Center for Nanotechnology\, 3205 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Dissertation or Thesis Defense
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250423T104500
DTEND;TZID=America/New_York:20250423T120000
DTSTAMP:20260403T174649
CREATED:20250403T132903Z
LAST-MODIFIED:20250403T132903Z
UID:10008348-1745405100-1745409600@seasevents.nmsdev7.com
SUMMARY:ESE Guest Seminar - "Efficient Computing for AI and Robotics: From Hardware Accelerators to Algorithm Design"
DESCRIPTION:The compute demands of AI and robotics continue to rise due to the rapidly growing volume of data to be processed; the increasingly complex algorithms for higher quality of results; and the demands for energy efficiency and real-time performance. In this talk\, we will discuss the design of efficient tailored hardware accelerators and the co-design of algorithms and hardware that reduce the energy consumption while delivering swift real-time and robust performance for applications including deep neural networks\, data analytics with sparse tensor algebra\, and autonomous navigation. Throughout the talk\, we will highlight important design principles\, methodologies\, and tools that can facilitate an effective design process and various forms of co-design that can broaden the design space. \n*Distinguished lecture supported by the IEEE Solid-State Circuits Society
URL:https://seasevents.nmsdev7.com/event/ese-guest-seminar-efficient-computing-for-ai-and-robotics-from-hardware-accelerators-to-algorithm-design/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar,Distinguished Lecture,Colloquium
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250423T120000
DTEND;TZID=America/New_York:20250423T131500
DTSTAMP:20260403T174649
CREATED:20250404T165640Z
LAST-MODIFIED:20250404T165640Z
UID:10008353-1745409600-1745414100@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: "Fake News\, Echo Chambers\, and Algorithms: A Data Science Perspective"
DESCRIPTION:Abstract: \nAmerican democracy has been undermined by an “infodemic” of fake news\, coupled with the widespread segregation of consumers into ideologically homogenous echo chambers by inscrutable algorithms deployed by rapacious social media platforms—or so we are told. In this talk\, I will critically examine claims of this sort—made frequently by politicians\, journalists\, and public intellectuals—summarizing several recent papers that leverage large-scale representative panel data for US media consumption. Contrary to conventional wisdom\, I argue that fake news is relatively rare\, echo chambers on television are much larger and stickier than their online equivalents\, and individual preferences dominate algorithmic filtering in determining consumption patterns. I further argue that it is trivially easy to mislead people without resorting to outright falsehoods and that researchers should accordingly pay more attention to biased information\, even when it is factually accurate. I conclude by introducing the media bias detector\, a recently launched project of Penn’s Computational Social Science Lab\, that seeks to characterize and expose bias in mainstream media. \nZoom Link: https://upenn.zoom.us/j/94075987313
URL:https://seasevents.nmsdev7.com/event/asset-seminar-duncan-watts-university-of-pennsylvania/
LOCATION:Amy Gutmann Hall\, Room 414\, 3333 Chestnut Street\, Philadelphia\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250423T150000
DTEND;TZID=America/New_York:20250423T160000
DTSTAMP:20260403T174649
CREATED:20250110T160305Z
LAST-MODIFIED:20250110T160305Z
UID:10008214-1745420400-1745424000@seasevents.nmsdev7.com
SUMMARY:Spring 2025 GRASP SFI: Haimin Hu\, Princeton University\, “From Gambits to Assurances: Game-Theoretic Integration of Safety and Learning for Human-Centered Robotics”
DESCRIPTION:This will be a hybrid event with in-person attendance in Levine 307 and virtual attendance on Zoom. \nABSTRACT\nFrom autonomous vehicles navigating busy intersections to quadrupeds deployed in household environments\, robots must operate safely and efficiently around people in uncertain and unstructured situations. However\, today’s robots still struggle to robustly handle low- probability events without becoming overly conservative. In this talk\, I will discuss how planning in the joint space of physical and information states (e.g.\, beliefs) allows robots to make safe\, adaptive decisions in human-centered scenarios. I will begin by introducing a unified safety filter framework that combines robust safety analysis with probabilistic reasoning to enable trustworthy human–robot interaction. I will discuss how robots can reduce conservativeness without compromising safety by closing their interaction–learning loop. Next\, I will show how game-theoretic reinforcement learning tractably synthesizes a safety filter for high-dimensional systems\, guarantees training convergence\, and reduces the policy’s exploitability. Finally\, I will present a scalable game-theoretic algorithm for optimizing social welfare in multi-agent coordination scenarios. I will conclude with a vision for next-generation human-centered robotic systems that actively align with their human peers and enjoy verifiable safety assurances.
URL:https://seasevents.nmsdev7.com/event/spring-2025-grasp-sfi-haimin-hu/
LOCATION:Levine 307\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250423T153000
DTEND;TZID=America/New_York:20250423T163000
DTSTAMP:20260403T174649
CREATED:20241216T202548Z
LAST-MODIFIED:20241216T202548Z
UID:10008203-1745422200-1745425800@seasevents.nmsdev7.com
SUMMARY:CBE Seminar: "From Molecules to Supply Chains: Transforming Data to Decisions using Geometry\, Optimization\, and Machine Learning" (Victor Zavala\, University of Wisconsin-Madison)
DESCRIPTION:Abstract: \n\nWe discuss how geometry\, optimization\, and machine learning are key technologies that are revolutionizing the way we think about data and the way we transform data into actionable models and decisions. Specifically\, we explain how complex data (e.g.\, text\, molecules\, time series\, images/video\, supply chain flows) can be represented as geometrical objects and how this facilitates the interpretation and extraction of useful information from data. We also discuss how extracted information can be mapped into decisions using optimization and machine learning models. We illustrate how to use these powerful math tools in innovative ways for analyzing complex datasets arising in molecular dynamics simulation\, microscopy\, chemical processes\, and supply chains. Specifically\, we show that these tools can help link the microstructure of soft gels to their rheological properties\, can help analyze complex responses of liquid crystals from video data\, and can help detect faults and optimize large-scale systems.
URL:https://seasevents.nmsdev7.com/event/cbe-seminar-from-molecules-to-supply-chains-transforming-data-to-decisions-using-geometry-optimization-and-machine-learning-victor-zavala-university-of-wisconsin-madison/
LOCATION:Wu & Chen Auditorium
CATEGORIES:Seminar
ORGANIZER;CN="Chemical and Biomolecular Engineering":MAILTO:cbemail@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250424T103000
DTEND;TZID=America/New_York:20250424T120000
DTSTAMP:20260403T174649
CREATED:20250407T191931Z
LAST-MODIFIED:20250407T191931Z
UID:10008354-1745490600-1745496000@seasevents.nmsdev7.com
SUMMARY:MSE Seminar: "Engineered Biomaterials for Regeneration\, Therapy\, and Beyond" Akhilesh K Gaharwar\, Texas A&M University
DESCRIPTION:Engineered biomaterials have emerged as powerful tools for a range of biomedical applications\, including regenerative medicine\, drug delivery\, and additive manufacturing. These engineered biomaterials possess tunable biophysical properties\, specific biochemical cues\, and complex architecture\, enabling precise control over cellular behavior. In this talk\, I will outline three biomaterials-based approaches developed in our lab for biomedical applications. Firstly\, I will highlight how engineered biomaterials can be used to control and direct cellular functions. Our work has resulted in a new class of biomaterials for bone regeneration\, and mitochondrial biogenesis. The second approach emphasizes the design of biomaterials tailored for the sustained and controlled release of therapeutics\, targeting osteoarthritis treatment\, angiogenesis promotion\, and wound healing. We have pioneered a suite of nano-toolkits adept at delivering both small molecular drugs and sizeable proteins\, characterized by efficient loading and adaptable release dynamics. Lastly\, I will demonstrate the design of 3D printing bioelectronics and anatomical-size tissue constructs. These advanced tissue structures enable the creation of physiologically accurate tissue models\, replicating complex disease conditions like vascular pathophysiology and intricate vascularized tumor representations.
URL:https://seasevents.nmsdev7.com/event/mse-seminar-engineered-biomaterials-for-regeneration-therapy-and-beyond-akhilesh-k-gaharwar-texas-am-university/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Materials Science and Engineering":MAILTO:johnruss@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250424T120000
DTEND;TZID=America/New_York:20250424T131500
DTSTAMP:20260403T174649
CREATED:20250131T222656Z
LAST-MODIFIED:20250131T222656Z
UID:10008263-1745496000-1745500500@seasevents.nmsdev7.com
SUMMARY:IDEAS/STAT Optimization Seminar: "Negative Stepsizes Make Gradient-Descent-Ascent Converge"
DESCRIPTION:Zoom link: https://upenn.zoom.us/j/98220304722 \nAbstract: Solving min-max problems is a central question in optimization\, games\, learning\, and controls. Arguably the most natural algorithm is Gradient-Descent-Ascent (GDA)\, however since the 1970s\, conventional wisdom has argued that it fails to converge even on simple problems. This failure spurred the extensive literature on modifying GDA with extragradients\, optimism\, momentum\, anchoring\, etc. In contrast\, we show that GDA converges in its original form by simply using a judicious choice of stepsizes. \nThe key innovation is the proposal of unconventional stepsize schedules that are time-varying\, asymmetric\, and (most surprisingly) periodically negative. We show that all three properties are necessary for convergence\, and that altogether this enables GDA to converge on the classical counterexamples (e.g.\, unconstrained convex-concave problems). The core intuition is that although negative stepsizes make backward progress\, they de-synchronize the min/max variables (overcoming the cycling issue of GDA) and lead to a slingshot phenomenon in which the forward progress in the other iterations is overwhelmingly larger. This results in fast overall convergence. Geometrically\, the slingshot dynamics leverage the non-reversibility of gradient flow: positive/negative steps cancel to first order\, yielding a second-order net movement in a new direction that leads to convergence and is otherwise impossible for GDA to move in. Joint work with Henry Shugart. \n 
URL:https://seasevents.nmsdev7.com/event/ideas-stat-optimization-seminar-jason-altschuler/
LOCATION:Amy Gutmann Hall\, Room 414\, 3333 Chestnut Street\, Philadelphia\, 19104\, United States
CATEGORIES:Seminar,Colloquium
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250424T130000
DTEND;TZID=America/New_York:20250424T140000
DTSTAMP:20260403T174649
CREATED:20250414T201128Z
LAST-MODIFIED:20250414T201128Z
UID:10008365-1745499600-1745503200@seasevents.nmsdev7.com
SUMMARY:MEAM Master's Thesis Defense: "Learning a Vision-Based Footstep Planner for Hierarchical Walking Control on Unstructured Terrain"
DESCRIPTION:Bipedal robots demonstrate high potential in navigating challenging terrains through dynamic ground contact. However\, current frameworks often depend solely on proprioception or use manually designed visual processing pipelines\, which are fragile in real-world settings and complicate real-time footstep planning in unstructured environments. To overcome this problem\, this work proposes a vision-based hierarchical control framework that integrates a reinforcement learning-based footstep planner\, which generates footstep commands based on a local elevation map\, with a low-level model-based controller that tracks the generated trajectories. The proposed framework is evaluated using the underactuated bipedal robot Cassie in both simulation and hardware. A detailed analysis identifies key challenges in sim-to-real transfer and potential strategies to improve the robustness and real-world applicability of hierarchical control frameworks.
URL:https://seasevents.nmsdev7.com/event/meam-masters-thesis-defense-learning-a-vision-based-footstep-planner-for-hierarchical-walking-control-on-unstructured-terrain/
LOCATION:David Rittenhouse Laboratory Building\, Room 4C4\, 209 S. 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Dissertation or Thesis Defense,Master's
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250424T153000
DTEND;TZID=America/New_York:20250424T163000
DTSTAMP:20260403T174649
CREATED:20250305T184414Z
LAST-MODIFIED:20250305T184414Z
UID:10008314-1745508600-1745512200@seasevents.nmsdev7.com
SUMMARY:BE-Grace Hopper Distinguished Lecture:  Melody Swartz\, PhD "Immunoregulatory roles of lymphatic vessels in cancer and opportunities for immunoengineering"
DESCRIPTION:Tumor lymphangiogenesis\, which involves both the activation and growth induction of surrounding lymphatic vessels\, is well-known to correlate with tumor progression and metastasis in many solid tumors. While it is typically assumed that lymphangiogenesis supports an ‘escape route’ for cells to leave the primary tumor\, the tumor-draining lymph node serves as the key site of immune surveillance. Our lab has been exploring how lymphatic involvement affects the tumor immune microenvironment and anti-tumor immunity while promoting metastasis at the same time. In doing so\, we have discovered new fundamental roles for lymphatic endothelial cells (LECs) as direct modulators of immunity. This is important because LECs are constantly bathed with peripheral antigens\, cytokines\, danger signals and immune cells travelling from peripheral tissues to lymph nodes. In terms of promoting metastasis\, we have learned that tumor-activated lymphatics alter the tumor microenvironment in multiple ways\, including (i) increasing immune suppressive cell types and factors in the tumor microenvironment both directly and indirectly\, (ii) inhibiting maturation of antigen-presenting cells and T cell activation\, and (iii) driving changes in the stromal microenvironment that promote both cancer invasion and immune suppression.  However\, lymphatic activation also enhances communication with cells in the draining lymph node by antigen and cell transport\, and leads to increased immune cell infiltration within the tumor. As a consequence\, lymphangiogenic tumors can be exceptionally responsive to immunotherapy\, paradoxically. This ‘lymphangiogenic potentiation’ of immunotherapy depends on tumor cell infiltration of both cross-presenting dendritic cells and naïve T cells\, driving local T cell education post-immunotherapy and antigen spreading.  On the translational side\, we are engineering novel strategies to exploit lymphangiogenesis for cancer immunotherapy.  Beyond cancer\, our findings suggest that LECs may be potential targets for immunomodulation in vaccination\, autoimmunity\, and allergy.  
URL:https://seasevents.nmsdev7.com/event/be-grace-hopper-distinguished-lecture-melody-swartz-phd-immunoregulatory-roles-of-lymphatic-vessels-in-cancer-and-opportunities-for-immunoengineering/
LOCATION:Berger Auditorium (Room 13)\, Skirkanich Hall\, 210 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
ORGANIZER;CN="Bioengineering":MAILTO:be@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250425T103000
DTEND;TZID=America/New_York:20250425T114500
DTSTAMP:20260403T174649
CREATED:20250228T211433Z
LAST-MODIFIED:20250228T211433Z
UID:10008307-1745577000-1745581500@seasevents.nmsdev7.com
SUMMARY:Spring 2025 GRASP on Robotics: Phillip Isola\, Massachusetts Institute of Technology\, “Robots and Artificial Life from Visual Foundation Models”
DESCRIPTION:This will be a hybrid event with in-person attendance in Wu and Chen and virtual attendance on Zoom. \nABSTRACT\nI will talk about two ways we can design agents with the help of powerful vision/graphics models. In the first project\, LucidSim\, we augment a traditional robotics simulation engine (MuJoCo) with visual detail from an image generative model. The generator adds diversity and realism to the barebones MuJoCo content\, and results in a RGB-only policy trained entirely in sim that generalizes zero-shot to the real world. In the second project\, ASAL\, we use a visual recognition model to search for artificial lifeforms that display distinct and interesting behaviors. This process can discover cellular automata that are open-ended like Conway’s Game of Life\, particle swarms that flock like Boids\, and more.
URL:https://seasevents.nmsdev7.com/event/spring-2025-grasp-on-robotics-phillip-isola-massachusetts-institute-of-technology-robots-and-artificial-life-from-visual-foundation-models/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250429T101500
DTEND;TZID=America/New_York:20250429T111500
DTSTAMP:20260403T174649
CREATED:20250303T151648Z
LAST-MODIFIED:20250303T151648Z
UID:10008309-1745921700-1745925300@seasevents.nmsdev7.com
SUMMARY:MEAM Seminar: "Atmospheric Boundary Layer Simulations for Wind Energy"
DESCRIPTION:The growth in wind energy is driving a need to understand how wind turbines perform under a range of atmospheric conditions. Under stably stratified conditions\, for example\, wind turbine wakes can persist for long distances and impact the performance of downwind turbines. Additionally\, variations in surface topography\, from shallow depressions to steep mountains\, can deflect wind turbine wakes upward or downward. These and other factors must be captured accurately by atmospheric models that provide predictions for wind turbine micro-siting and operational wind power forecasting over complex terrain. Here we present examples of mesoscale to microscale simulations at real wind farms with complex terrain\, including implementation of detailed models for turbine wake effects. The focus is on understanding how simulation of wind turbine wakes is influenced not only by topography and thermal stratification\, but by numerical techniques such as turbulence closure models and grid nesting strategies. The Weather Research and Forecasting (WRF) model is used here in grid nested configurations starting from the mesoscale (~10 km resolution) and ending with fine scale resolutions (~10 m) suitable for large-eddy simulation (LES). Wind turbine wake behavior is examined under stably stratified and convective conditions over complex terrain with comparison to field campaign data.
URL:https://seasevents.nmsdev7.com/event/meam-seminar-atmospheric-boundary-layer-simulations-for-wind-energy/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250429T103000
DTEND;TZID=America/New_York:20250429T113000
DTSTAMP:20260403T174649
CREATED:20250415T151134Z
LAST-MODIFIED:20250415T151134Z
UID:10008367-1745922600-1745926200@seasevents.nmsdev7.com
SUMMARY:CBE Special Guest Lecture: "Preventing\, Understanding and Reducing End-Customers' Power Supply Outages with Digital Twins" (Panayiotis Moutis\, City College of New York)
DESCRIPTION:Abstract: \nBlackouts have become rarer in the last decade. However\, equipment wear and faults (some predictable)affect smaller scales but many parts of Distribution Networks (DNs) more frequently and add up to several hours of interruptions per customer per year. Also\, utilities will preemptively de-energize thousands of customers in the path or vicinity of forest fires and floods to minimize damages and loss of life. The limited\, if not zero\, visibility into the medium and low voltage DNs is partly to blame for the causes\, length and extent of these disruptions\, as also their recurrence\, due to lack of insights. Monitoring DNs\, however\, is hard\, because they are spatially dispersed with hundreds of critical points. This talk\, first introduces the digital twin of DN transformers to identify load behaviors\, effects of distributed resources and power quality issues leading to DN grid faults. Secondly\, we present the digital twin of overhead conductors to detect approaching forest fires and\, thus\, enable utilities to interrupt customers’ service only when it otherwise unavoidable. Digital twins rely on the rising use of synchrophasor measurements within DNs\, that enable highly granular and time-synchronized sensing of power system assets.
URL:https://seasevents.nmsdev7.com/event/cbe-special-guest-lecture-preventing-understanding-and-reducing-end-customers-power-supply-outages-with-digital-twins-panayiotis-moutis-city-college-of-new-york/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Chemical and Biomolecular Engineering":MAILTO:cbemail@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250429T160000
DTEND;TZID=America/New_York:20250429T170000
DTSTAMP:20260403T174649
CREATED:20250424T152232Z
LAST-MODIFIED:20250424T152232Z
UID:10008379-1745942400-1745946000@seasevents.nmsdev7.com
SUMMARY:Steering Higher Ed Through Rough Seas: Three Bold Strategies to Navigate the Future
DESCRIPTION:Higher education is navigating intense political pressure\, shifting demographics\, rising costs and evolving workforce demands. This session will detail three strategies for sustaining academic excellence while lowering administrative costs\, expanding reach and impact\, and regaining public trust.
URL:https://seasevents.nmsdev7.com/event/14005/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Academic Innovation Speaker Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250430T083000
DTEND;TZID=America/New_York:20250430T120000
DTSTAMP:20260403T174649
CREATED:20250401T173030Z
LAST-MODIFIED:20250401T173030Z
UID:10008345-1746001800-1746014400@seasevents.nmsdev7.com
SUMMARY:Benjamin Franklin Medal in Electrical Engineering Symposium Honoring Kurt Petersen: "Small Tech\, Big Impact: The Development and Commercialization of MEMS Sensors & Actuators"
DESCRIPTION:For two centuries\, The Franklin Insitute has honored pioneering achievements in science\, engineering\, and industry. As the oldest comprehensive science awards program in the United States. The Franklin Insitute Awards celebrates Benjamin Franklin’s legacy by honoring the Franklins of today. Through their remarkable contributions\, our laureates inspire the Franklins of tomorrow. \nThe 2025 Benjamin Franklin Medal in Electrical Engineering is awarded to Kurt Petersen\, Co-Chair at the HardTech Group of the Silicon Valley Band of Angels. This Symposium celebrates Kurt for his pioneering research and development of micro-electromechanical systems (MEMS) technology – microscopic systems that merge mechanical and electrical functionality and which have wide ranging applications such as medical devices\, inkjet printers\, IoT\, optical projectors\, and automotive sensors. \nClick here for more information and to register.
URL:https://seasevents.nmsdev7.com/event/benjamin-franklin-medal-in-electrical-engineering-symposium-honoring-kurt-petersen-small-tech-big-impact-the-development-and-commercialization-of-mems-sensors-actuators/
LOCATION:Glandt Forum\, Singh Center for Nanotechnology\, 3205 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Symposium
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250430T083000
DTEND;TZID=America/New_York:20250430T120000
DTSTAMP:20260403T174649
CREATED:20250417T181011Z
LAST-MODIFIED:20250417T181011Z
UID:10008370-1746001800-1746014400@seasevents.nmsdev7.com
SUMMARY:Franklin Awards Symposium: Honoring Professor Naomi J. Halas - Rice University - Recipient of the 2025 Franklin Medal in Chemistry
DESCRIPTION:This symposium will feature cutting-edge contributions in plasmonics and nanonphonics research that are enabling advances in life sciences\, energy sustainability\, and information technology. \nEvent Schedule \n8:50 am:  Welcome\n9:00 am: Prof. Rizia Bardhan\, Iowa State University.\n9:35 am: Prof. Stephan Link\, University of Illinois Urbana-Champaign (UIUC)\n10:10 am: Break\n10:30 am: Prof. Peter J. A. Nordlander\, Rice University\n11:05 am: Prof. Naomi J. Halas\, Rice University (2025 Laureate in Chemistry) \n  \n 
URL:https://seasevents.nmsdev7.com/event/franklin-awards-symposium-honoring-professor-naomi-j-halas-rice-university-recipient-of-the-2025-franklin-medal-in-chemistry/
LOCATION:Vagelos Institute for Energy Science and Technology\, Room 121\, 231 S 34th Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Symposium
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250430T120000
DTEND;TZID=America/New_York:20250430T131500
DTSTAMP:20260403T174649
CREATED:20241118T151225Z
LAST-MODIFIED:20241118T151225Z
UID:10008178-1746014400-1746018900@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: "Neurosymbolic Program Synthesis: Bridging Perception and Reasoning in Real-World Applications"
DESCRIPTION:Abstract: \nNeurosymbolic Program Synthesis (NSP) integrates neural networks and symbolic reasoning to tackle complex tasks requiring both perception and logical reasoning. This talk provides an overview of the NSP framework and its applications in domains such as image editing\, data extraction\, and robot learning from demonstrations. We will delve into the key ideas behind NSP learning algorithms\, focusing on the synergistic interplay between neural guidance and symbolic reasoning. Finally\, we will discuss recent advances in ensuring the correctness of synthesized neurosymbolic programs\, paving the way for robust and reliable AI systems. \nZoom Link (if unable to attend in-person): https://upenn.zoom.us/j/95763386582
URL:https://seasevents.nmsdev7.com/event/asset-seminar-isil-dillig-university-of-texas-at-austin/
LOCATION:Levine 307\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250430T153000
DTEND;TZID=America/New_York:20250430T163000
DTSTAMP:20260403T174649
CREATED:20241216T205032Z
LAST-MODIFIED:20241216T205032Z
UID:10008204-1746027000-1746030600@seasevents.nmsdev7.com
SUMMARY:JOHN A. QUINN DISTINGUISHED LECTURE IN CHEMICAL ENGINEERING: "Sticky Nanoparticles: Electrostatic Assembly of Targeted Delivery Agents" (Paula Hammond\, MIT)
DESCRIPTION:Abstract: \n\nElectrostatic assembly can be used to engineer coatings that yield release of different drugs\, DNA or protein\, resulting in highly tunable multi -agent delivery nanolayered release systems for tissue engineering\, biomedical devices\, and wound healing applications. Most recently\, we have developed a modular nanoparticle approach using liposomal core particles and layering them with an electrostatic layer-by-layer (LBL) process in a simple and elegant method of constructing highly tailored ultrathin polymer coatings. The resulting LbL nanoparticles (LbL NPs) have negatively charged outer layers that present polyelectrolytes such as dextran sulfate or hyaluronic acid in a hydrated brush arrangement that enables hydration\, steric repulsion\, colloidal and serum stability\, and specific or non-specific targeting. We have demonstrated that these particles have long systemic plasma blood half-lives and good tumor accumulation over time\, and demonstrate efficacy in advanced breast and lung cancer models in which siRNA targets have been delivered with chemotherapy drugs in the same nanoparticle system. \nBy staging the release of different drug components via the adaptation of the nanoparticle structure\, we can achieve highly synergistic release behavior in these systems. We have found that certain LbL nanoparticle formulations traffic differently in cells based on the negatively charged polypeptide\, and we are exploring ways to utilize these differences in affinity for more selective tumor cell binding and deliver within cells. \nOngoing work includes addressing barriers to transport of these nanoparticles relevant to tumor or other tissue penetration\, and will be discussed\, including new work involving the understanding of these trafficking patterns and a means to leverage them toward the delivery of cytokines for activation of the immune system against ovarian cancer\, a cancer which has not previously benefitted from immunotherapeutic approaches. In vitro and in vivo results will be discussed\, as well as release mechanisms\, toxicity studies and clinical outlook for these targeted systems. Ongoing work includes examination of how these LbL NP systems might be adapted to enhance delivery across the blood-brain barrier for glioblastoma\, or modified to enhance tumor accumulation and penetration. These and other uses of controlled polyelectrolytes and their complexes for delivery within tissues and across barriers will be addressed.
URL:https://seasevents.nmsdev7.com/event/john-a-quinn-distinguished-lecture-in-chemical-engineering-sticky-nanoparticles-electrostatic-assembly-of-targeted-delivery-agents-paula-hammond-mit/
LOCATION:Wu & Chen Auditorium
CATEGORIES:Seminar
ORGANIZER;CN="Chemical and Biomolecular Engineering":MAILTO:cbemail@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250501T130000
DTEND;TZID=America/New_York:20250501T150000
DTSTAMP:20260403T174649
CREATED:20250321T180708Z
LAST-MODIFIED:20250321T180708Z
UID:10008324-1746104400-1746111600@seasevents.nmsdev7.com
SUMMARY:Energy-Efficient AI: The Franklin Institute Awards Laureate Symposium Honoring William James Dally
DESCRIPTION:The Franklin Institute Awards Laureate Symposium is dedicated to honoring William James Dally\, recipient of the 2025 Benjamin Franklin Medal in Computer and Cognitive Science \nThe event will feature Margaret Martonosi (H. T. Adams ’35 Professor of Computer Science\, Princeton University)\, Yakun Sophia Shao (Associate Professor in Electrical Engineering and Computer Sciences\, UC Berkeley)\, Joe Devietti (Computer and Information Science\, Penn Engineering) and Benjamin Lee (Computer and Information Science; Electrical and Systems Engineering\, Penn Engineering). \nAwards Week Sponsors: JPMorganChase\, Morgan Lewis\, Marsha and Jeffrey Perelman \nThis event is part of AI Month 2025\, which will explore AI’s impact on human well-being. \nClick here to RSVP.
URL:https://seasevents.nmsdev7.com/event/energy-efficient-ai-the-franklin-institute-awards-laureate-symposium-honoring-william-james-dally/
LOCATION:Amy Gutmann Hall\, Auditorium\, 3333 Chestnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Symposium,AI Month
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250501T150000
DTEND;TZID=America/New_York:20250501T160000
DTSTAMP:20260403T174649
CREATED:20250417T193602Z
LAST-MODIFIED:20250417T193602Z
UID:10008371-1746111600-1746115200@seasevents.nmsdev7.com
SUMMARY:MEAM Master's Thesis Defense: "A Computational Model of Caenorhabditis elegans Locomotion"
DESCRIPTION:Since discovered in 1897\, the nematode Caenorhabditis elegans has surfaced as an excellent model organism for medical and genetic research. The worm propels itself through viscous-dominated creeping flows via undulatory motion. Moreover\, experiments have revealed that the netamode’s swimming gait alters as a function of fluid viscosity. In the current research\, we proposed a new solid-mechanics-based auto-propulsion model featuring a closed-form displacement field that better captures the nematode’s swimming gait in water. A series of decoupled/coupled (Fluid-Structure Interaction) finite-element simulations exploiting the Arbitrary Lagrangian-Eulerian (moving mesh) technique were then conducted to investigate how different gaits affect the free-swimming speed\, and how the interaction with fluids of various viscosities and the presence of wall boundaries deviate the swimming gait from the solid-mechanics-based closed-form solution.
URL:https://seasevents.nmsdev7.com/event/meam-masters-thesis-defense-a-computational-model-of-caenorhabditis-elegans-locomotion/
LOCATION:Towne 319\, 220 S. 33rd Street\, Philadelphia\, 19104\, United States
CATEGORIES:Dissertation or Thesis Defense,Master's
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250502T140000
DTEND;TZID=America/New_York:20250502T150000
DTSTAMP:20260403T174649
CREATED:20250130T153439Z
LAST-MODIFIED:20250130T153439Z
UID:10008250-1746194400-1746198000@seasevents.nmsdev7.com
SUMMARY:PICS Colloquium: Learning to Model the World (and Yourself) from Vision
DESCRIPTION:In this talk\, I will discuss recent publications from my group that attempt at learning models of the world and the effect of the actions of an agent within that world self-supervised\, solely via interaction. In particular\, I will discuss the potential and challenges of video generative models as a candidate for such a world model\, the role of inductive biases using our recent work that discovers the kinematics of a robot as an example\, and finally a new research direction in which we attempt to discover the physical rules underlying our world without any inductive biases whatsoever.
URL:https://seasevents.nmsdev7.com/event/pics-colloquium-with-vincent-sitzmann/
LOCATION:PICS Conference Room 534 – A Wing \, 5th Floor\, 3401 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Colloquium
ATTACH;FMTTYPE=image/jpeg:https://seasevents.nmsdev7.com/wp-content/uploads/2025/01/portrait-scaled-1.jpeg
ORGANIZER;CN="Penn Institute for Computational Science (PICS)":MAILTO:dkparks@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250506T100000
DTEND;TZID=America/New_York:20250506T100000
DTSTAMP:20260403T174649
CREATED:20250423T124226Z
LAST-MODIFIED:20250423T124226Z
UID:10008377-1746525600-1746525600@seasevents.nmsdev7.com
SUMMARY:ESE Ph.D. Thesis Defense: "Multiferroic Resonators for Wireless Power Transfer and Magnetic Field Sensing in Biomedical Systems"
DESCRIPTION:Micro-electromechanical systems (MEMS) composed of magnetostrictive and piezoelectric materials can translate information between the electrical and magnetic domains while exploiting mechanical resonance enhancement. Multiferroic MEMS devices such as these can be designed to perform magnetic field sensing and wireless power transfer (WPT) while maintaining device sizes on the order of 0.125 mm 2 . This thesis will focus on the theory\, design\, and characterization of these MEMS magnetometers and WPT devices.
URL:https://seasevents.nmsdev7.com/event/ese-ph-d-thesis-defense-multiferroic-resonators-for-wireless-power-transfer-and-magnetic-field-sensing-in-biomedical-systems/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Dissertation or Thesis Defense
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250506T140000
DTEND;TZID=America/New_York:20250506T160000
DTSTAMP:20260403T174649
CREATED:20250425T200924Z
LAST-MODIFIED:20250425T200924Z
UID:10008380-1746540000-1746547200@seasevents.nmsdev7.com
SUMMARY:Spring 2025 Robotics MSE Thesis and Capstone Lightning Talks and Poster Session
DESCRIPTION:This is an in-person event with in-person attendance in Wu and Chen Auditorium for Lightning Talks and Levine Lobby for Poster Session.  \nThis year we will have an “Audience Choice” for best Lightning Talk and Poster. Please be sure to vote for your favorite! Voting will take place during the Poster Session using a QR code. \n2:00pm – Lightning Talks \nWelcome Remarks\nDr. Cynthia Sung – ROBO Program Chair \nRahul Aggarwal\nAdvised By: Dr. Rahul Mangharam\nGeneralizable Visual Prediction Via Disentangled Diffusion \n  \n  \n  \n  \n  \n  \n \nJack Campanella\nAdvised By: Dr. Vijay Kumar\nIntegrated Hardware and Software Codesign for Controlling Underactuated Aerial Robots \n  \n  \n  \n  \n  \n  \nSatrajit Chatterjee\nAdvised By: Dr. Rahul Mangharam\nWorld Modeling via Sparse Conditioning of Temporal Context \n  \n  \n  \n  \n  \n  \nMichaela Feehery\nAdvised By: Dr. Eric Eaton\nEvent-Based Respiration Detection for Autonomous Robotic Triage \n  \n  \n  \n  \n  \n  \nGeorge Gao\nAdvised By: Dr. Nadia Figueroa\nOCR: Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learning \n  \n  \n  \n  \n  \n  \nFrank Gonzalez\nAdvised By: Dr. Vijay Kumar\nRisk-aware MPC Planning for Unmanned Ground Vehicles \n  \n  \n  \n  \n  \n  \nPei-An Hsieh\nAdvised By: Dr. Ani Hsieh\nStable and Robust Tight Formation Flights of Quadrotors with MPC \n  \n  \n  \n  \n  \n  \nRoyina Jayanth\nAdvised By: Dr. Kostas Daniilidis\nExploring Generalization and Robustness of Neural Inertial Odometry \n  \n  \n  \n  \nAlexander Kyimpopkin\nAdvised By: Dr. Pratik Chaudhari\nMagic-8-Ball: World Models for Vision-Based Quadruped Path Planning \n  \n  \n  \n  \n  \n  \nSanghyub Lee\nAdvised By: Dr. Nadia Figueroa\nHuman-Robot Interactive Muscle-in-the-loop Upper Limb Training Using Real-time Muscle Dynamics Tracking via AI-driven Wearable Ultrasound Processing \n  \n  \n  \n  \n  \nRuirui Ma\nAdvised By: Dr. Linh Thi Xuan Phan\nConnectivity Constrained Multi-Robot Sparse Coverage \n  \n  \n  \n  \n  \n  \nLee Milburn\nAdvised By: Dr. Rahul Mangharam\nCluster-Funk: Clustering for Friction Estimation Under Nonlinear Knowledge \n  \n  \n  \n  \n  \n  \nEmily Paul\nAdvised By: Dr. Vijay Kumar\nMulti-Agent Reinforcement Learning with Reward Shaping for Coverage Control \n  \n  \n  \n  \n  \n  \nNishanth Rao\nAdvised By: Dr. Kostas Daniilidis and Dr. Vijay Kumar\nExploring Symmetries and Equivariance in Robot Learning \n  \n  \n  \n  \n  \n  \nHungju Wang\nAdvised By: Dinesh Jayaraman\nFoundation Models for Realworld Robotics \n  \n  \n  \n  \n  \n  \n   \nBrice Diomande\, Chris Lee\, Henry Licht\nAdvised By Ani Hsieh\nSponsored By: Saint Gobain CertainTeed\nAutonomous Mobile Robot for Installing Blown-In Insulation \n2:30pm – Poster Session in Levine Lobby \n4:00pm – Awards for Best Lightning Talk and Poster Announced \n 
URL:https://seasevents.nmsdev7.com/event/spring-2025-robotics-mse-thesis-and-capstone-lightning-talks-and-poster-session/
LOCATION:Wu & Chen Auditorium
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250506T150000
DTEND;TZID=America/New_York:20250506T160000
DTSTAMP:20260403T174649
CREATED:20250423T134701Z
LAST-MODIFIED:20250423T134701Z
UID:10008378-1746543600-1746547200@seasevents.nmsdev7.com
SUMMARY:MEAM Ph.D. Thesis Defense: "Real-Time Perception and Mixed-Integer Footstep Control for Underactuated Bipedal Walking on Rough Terrain"
DESCRIPTION:The promise of bipedal robots is to go where people go\, serving as surrogates for human labor in dangerous\, unstructured environments. For the most part\, this promise remains unrealized. The primary challenge for controlling bipedal locomotion is underactuation. Standing on a single leg limits control authority\, requiring appropriate foot placement to generate or absorb momentum and maintain balance. Rough terrain exacerbates this challenge by introducing restrictions on where the robot can step. These restrictions must be identified from onboard sensing modalities and accounted for in the footstep plan\, all while meeting the strict real-time requirements of feedback control. In this thesis\, we examine systems\, modeling choices\, and algorithms for solving this problem\, ultimately enabling dynamic bipedal walking over previously unseen discontinuous terrain. \nConventional approaches decouple the problem of walking over rough terrain into separate modules for footstep planning and motion control\, limiting walking speed and online adaptability. The beginning of this thesis introduces a new model-predictive-control-style footstep planner which eliminates this decomposition. We jointly optimize over the robot’s dynamics and discrete choice of stepping surface in real time to stabilize underactuated walking over constrained footholds. \nOur footstep controller depends on approximating the safe terrain as a union of convex planar polygon “stepping stones”. In order to generate such an approximation from onboard sensors in real time\, we propose novel safe terrain segmentation and convex decomposition algorithms. Our segmentation approach avoids the common design choice of plane segmentation\, which we argue makes segmentation algorithms slower and less reliable. Instead\, we classify terrain as safe based only on local features\, yielding a segmentation which is both fast to compute and temporally consistent. We present full stack perceptive locomotion experiments on the underactuated biped Cassie\, leveraging our novel footstep controller and perception pipeline to walk over previously unseen discontinuous terrain. \nFinally\, we present an exploratory study of a cascaded-fidelity model predictive footstep controller\, which combines elements of our first footstep planner with whole-body model predictive control in order to navigate even more challenging terrains.
URL:https://seasevents.nmsdev7.com/event/meam-ph-d-thesis-defense-real-time-perception-and-mixed-integer-footstep-control-for-underactuated-bipedal-walking-on-rough-terrain/
LOCATION:Towne 319\, 220 S. 33rd Street\, Philadelphia\, 19104\, United States
CATEGORIES:Doctoral,Dissertation or Thesis Defense
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250507T140000
DTEND;TZID=America/New_York:20250507T153000
DTSTAMP:20260403T174649
CREATED:20250428T175423Z
LAST-MODIFIED:20250428T175423Z
UID:10008381-1746626400-1746631800@seasevents.nmsdev7.com
SUMMARY:AI at the Crossroads: Ethics\, Innovation and Impact  
DESCRIPTION:As part of Philly Tech Week and AI Month\, this panel explores the balance between cutting-edge AI advancements and responsible development\, with a focus on the broader societal impact of artificial intelligence. \nPanelists: \n\nChris Callison-Burch\, Professor\, CIS; Program Director\, Online Master of Science in Engineering in Artificial Intelligence\nMelissa Kelly\, Deputy Managing Director\, Penn Center for Innovation\nAaron Roth\, Henry Salvatori Professor of Computer and Cognitive Science\, CIS\n\n 
URL:https://seasevents.nmsdev7.com/event/ai-at-the-crossroads-ethics-innovation-and-impact/
LOCATION:Amy Gutmann Hall\, Auditorium\, 3333 Chestnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:AI Month
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250507T153000
DTEND;TZID=America/New_York:20250507T163000
DTSTAMP:20260403T174649
CREATED:20250505T165504Z
LAST-MODIFIED:20250505T165504Z
UID:10008382-1746631800-1746635400@seasevents.nmsdev7.com
SUMMARY:CBE Seminar: "Redox-responsive Interfaces for Selective Electrochemical Separations" (Xiao Su\, University of Illinois\, Urbana-Champaign)
DESCRIPTION:Abstract: \nElectric fields and electrochemical reactions can unlock new separation pathways. While electrochemical separations have been explored previously for water desalination\, their translation to value-added chemical manufacturing or resource recovery has been hampered by the lack of molecular selectivity. Here\, we present the molecular design of redox-responsive materials for enabling selective electrochemical separations. \nRedox electron-transfer can be leveraged to tune interfacial selectivity\, reversibility\, and even synergistic coupling of reaction and separations. We combine synthetic design\, in-situ interfacial measurements\, and computational simulations to investigate the binding mechanisms of target ions at electrodes\, and elucidate the contributing effects of charge-transfer\, electrostatics\, and solvation. These mechanistic insights can guide the discrimination of structurally similar ions\, for applications ranging from critical element recovery to even enantioselective separations. Separately\, we demonstrate how copolymer design and electrochemical systems engineering can innovate redox-electrodialysis. These integrated processes can have an impact on multicomponent separations\, including the simultaneous abatement of ultra-short-\, short-\, and long-chain PFAS from semiconductor manufacturing. \nFinally\, we highlight the generalizability of the redox-mediated separations beyond adsorption\, and extend the concepts to electrochemical liquid-liquid extraction platforms. We discuss how these continuous technologies can be scalable\, and provide a path for industrial translation in e-waste recycling and mineral processing.
URL:https://seasevents.nmsdev7.com/event/cbe-seminar-redox-responsive-interfaces-for-selective-electrochemical-separations-xiao-su-university-of-illinois-urbana-champaign/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Chemical and Biomolecular Engineering":MAILTO:cbemail@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250508T100000
DTEND;TZID=America/New_York:20250508T110000
DTSTAMP:20260403T174649
CREATED:20250422T161444Z
LAST-MODIFIED:20250422T161444Z
UID:10008376-1746698400-1746702000@seasevents.nmsdev7.com
SUMMARY:Spring 2025 GRASP Seminar: Mike Shou\, National University of Singapore\, "Video intelligence in the era of multimodal"
DESCRIPTION:This will be a hybrid event with a VIRTUAL speaker. The GRASP seminar will be streamed for in-person attendance in Levine 307 and virtual attendance on Zoom.\nABSTRACT\nThe past few years have witnessed great success in video intelligence\, as supercharged by multimodal models. In this talk\, I will start with a brief sharing of our efforts\, in building video-language models for understanding and diffusion models for video generation. Yet\, video understanding and generation have always been two separate research pillars\, despite their strong synergy. This motivates us to develop Show-o\, one unified single transformer that can do both multimodal understanding and generation. Show-o is the first to unify autoregressive and discrete diffusion modeling\, flexibly supporting a wide range of vision-language tasks of any input/output format\, including visual question-answering\, text-to-image/video generation\, and generation of video keyframes with captions\, all within one single 1.3B transformer. Show-o sheds light for building the next-generation multimodal video foundation model\, and has sparked many follow-up works already.
URL:https://seasevents.nmsdev7.com/event/spring-2025-grasp-seminar-mike-shou-national-university-of-singapore-video-intelligence-in-the-era-of-multimodal/
LOCATION:Levine 307\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
END:VCALENDAR