Events from the AJ Clark School of Engineering http://eng.umd.edu/events/ Tue, 04 Aug 2026 11:30:26 EDT http://eng.umd.edu/images/clark_logo_4email.gif http://eng.umd.edu/events/ Wednesday, August 05, 2026 7:00 PM, AVW 1146, Announcement: Ph.D. Dissertation Defense   Name: Utku NoyanCommittee:Professor Pamela Abshire, Chair/AdvisorProfessor Sahil Shah, Co-AdvisorProfessor Kevin DanielsProfessor Jesse MoodyProfessor Don DeVoe, Dean's RepresentativeDate/time: Wednesday, August 5, 2026 at 2:00 PM Location: AVW 1146 Title: A CMOS-Integrated Multiplexed ISFET Sensing Platform for Label-Free Cytokine Profiling and Apoptotic Monitoring   Abstract: Field-effect transistor (FET) biosensors promise label-free, electronic, and CMOS-scalable detection of biochemical signals, but their translation to continuous, multiplexed, point-of-care monitoring has been limited by sensor drift, few-device architectures that lack statistical noise redundancy, and polymer packaging that absorbs and leaches interfering species. This thesis develops and validates a scalable CMOS-integrated ion-sensitive field-effect transistor (ISFET) platform for continuous, label-free, multiplexed profiling of inflammatory cytokines and apoptotic biomarkers, advancing the state of the art across physical modeling, surface chemistry, wafer-scale fabrication, and drift-compensated circuit design. First, the thesis develops a coupled electrolyte–semiconductor model of the ISFET that combines site-binding surface chemistry, Gouy–Chapman–Stern double-layer electrostatics, and compact transistor behavior. Validated against commercial devices, the model analyzes temporal and thermal drift and guides the selection of gate-dielectric material and thickness, establishing silicon nitride as the sensing membrane used throughout the platform. Second, the thesis establishes a reproducible amine-coupling surface-functionalization protocol on silicon-nitride surfaces and demonstrates it on Annexin V–based detection of phosphatidylserine, an early marker of apoptosis, achieving near-Nernstian sensitivities and nanomolar detection limits with independent microscopy validation. Third, the thesis introduces a wafer-scale post-processing flow that makes foundry CMOS compatible with electrolyte operation, and integrates a 128×128 (16,384-pixel) CMOS ISFET array with a low-sorption thermoplastic-elastomer (FlexDym) microfluidic overlay. Whole-well spatial averaging and on-array reference channels enable simultaneous, label-free detection of interleukin-6 and interleukin-10 with a sub-picomolar detection limit. Finally, the thesis presents a drift- and noise-compensated ISFET/REFET readout chip in a 180 nm CMOS process that combines analog current subtraction, in-pixel chopping, and a current-starved ring-oscillator counter with an I²C interface. Subtraction rejects common-mode drift and temperature while chopping suppresses 1/f noise, lowering the achievable detection limit beyond what either technique provides alone. Together, these contributions deliver a validated, calibrated platform for rapid, bedside biomarker detection, with applications in monitoring cytokine release syndrome and sepsis and in real-time profiling of apoptotic and inflammatory pathways. http://www.ece.umd.edu/events/index.php?mode=4&id=20742 http://www.ece.umd.edu/events/index.php?mode=4&id=20742 Friday, September 25, 2026 10:30 PM, A.V. Williams Courtyard, The Department of Electrical and Computer Engineering invites ECE Terps and their families for our annual Family Weekend open house on Friday, September 25th from 5:30 to 7:30 p.m. Please join us for an early evening networking event where you will meet our ECE Chair, the Associate Chair for Undergraduate Studies, and the Director of Undergraduate Studies.  There will be lab tours and demonstrations of the exciting research being conducted by ECE faculty and students. We recognize that the families of our students are vital to their success. Please take this opportunity to discover more about the educational journey they embark on in Electrical or Computer Engineering and learn about ways to remain engaged throughout their academic career. RSVP: https://go.umd.edu/2026-ECE-FamilyNight If you have any questions, please contact Darcy Long, External Relations Coordinator, in ECE's Office of External Relations: (301) 405-3114 or dlong123@umd.edu http://www.ece.umd.edu/events/index.php?mode=4&id=20717 http://www.ece.umd.edu/events/index.php?mode=4&id=20717 Monday, August 10, 2026 4:00 PM, AVW1146, ANNOUNCEMENT: Ph.D. Dissertation Defense Name: Mohamed ElnoorCommittee:Professor Dinesh Manocha, Chair/Advisor Professor Pratap TokekarProfessor Kaiqing ZhangProfessor Sanghamitra Dutta Professor Michael Otte, Dean's Representative Date/time: Monday, August 10 at 11:00 AMLocation: AVW 1146  Zoom Link: umd.zoom.us/my/dmanochaTitle: Proprioception-based Perception and Physically Grounded Vision-Language Reasoning for Autonomous NavigationAbstract:Autonomous mobile robots increasingly operate in complex outdoor environments where navigation requires reasoning about terrain geometry, physical properties, environmental conditions, and semantic context. Existing perception systems rely primarily on vision-based sensors, which often fail when terrain appearance does not accurately reflect traversability or when sensing conditions deteriorate.In this dissertation, we present several novel algorithms built on two complementary ideas. The first, proprioception-based perception, uses measurements of the robot’s own body, including joint positions, forces, motor currents, and platform state, to estimate terrain traversability, stability, and other physical properties that may not be reliably inferred from visual appearance alone. The second, physically grounded vision-language reasoning, uses Vision-Language Models (VLMs) for high-level scene understanding while incorporating measured physical information, such as the robot’s interaction with the environment or its current state, into the reasoning and navigation process. Building on these ideas, our algorithms estimate terrain traversability from proprioceptive signals, adaptively combine vision and proprioception under variable sensing conditions, ground VLM predictions in physical feedback, distill VLM reasoning into lightweight on-board models, and apply state-conditioned vision-language reasoning to safety-critical two-wheeled platforms. We implement and evaluate the proposed navigation methods on real legged and wheeled robots and on a simulated motorcycle, demonstrating improvements in navigation success rate, energy consumption, and stability over state-of-the-art baselines.The first part develops proprioception-based perception for legged robots. We propose ProNav, which uses proprioceptive signals from joint encoders, force, and current sensors for traversability estimation, gait selection, and preemptive crash prediction, showing up to 40% improvement in success rate and up to 15.1% reduction in energy consumption over exteroceptive-based methods. Building on this, AMCO adaptively couples vision and proprioception through three cost maps weighted by the visual stream’s estimated reliability, observing 10.8%–34.9% reduction in stability metrics and up to 50% improvement in success rate over prior methods.In the second part, we integrate physically grounded vision-language reasoning through VLMs along two complementary directions. We present VLM-GroNav, which integrates VLMs with physical grounding using in-context learning to dynamically update traversability estimates from the robot’s real-time physical interactions and inform both local and global planners, observing up to 50% increase in success rate. Furthermore, ViLAM distills vision-language reasoning from large VLMs into spatial attention maps used as planning cost maps by a sampling-based local planner, demonstrating 14.2%–50% improvements in success rate over existing methods.The final part extends the vision-language reasoning framework to safety-critical two-wheeled platforms. We present an Advanced Rider Assistance System (ARAS) that leverages VLM chain-of-thought reasoning conditioned on the vehicle’s speed and lean angle to produce a dense per-pixel risk map, and drives a local planner adapted to motorcycle dynamics, improving success rate and hazard-clearance distance over baselines in the CARLA simulator.Together, these contributions establish a unified approach for proprioception-based perception and physically grounded vision-language reasoning that combines physical interaction, adaptive sensor fusion, and semantic reasoning to enable reliable autonomous navigation across diverse robotic platforms. http://www.ece.umd.edu/events/index.php?mode=4&id=20749 http://www.ece.umd.edu/events/index.php?mode=4&id=20749 Friday, October 30, 2026 5:00 PM, Kim Engineering Building Rotunda, Companies will be looking for undergraduate and graduate students for internships and full-time positions. Information available HERE Student Registration Link http://www.ece.umd.edu/events/index.php?mode=4&id=20727 http://www.ece.umd.edu/events/index.php?mode=4&id=20727 Monday, August 31, 2026 2:30 PM, J. M. Patterson Building (JMP) 2217, Applications of AI in Reliability: Prognostics and Systems Health Management (Fall 2026 Graduate Course) Prof. Michael G. Pecht301-405-5323pecht@umd.edu Dr. Michael H. Azarian301-405-7555mazarian@umd.edu Prof. Jay Lee301-405-5255leejay@umd.edu Class Timings: Mondays, 9:30 AM to 12:10 PM US Eastern Time at J. M. Patterson Building (JMP) 2217 Find the Syllabus Here Read more about the course here. Prognostics and health management (PHM) is an enabling discipline consisting of technologies and methods to assess the reliability of a product in its actual life cycle conditions to determine the advent of failure and mitigate system risk. In recent years, PHM has emerged as a key technology that provides an early warning of failure, forecasts maintenance, and assesses the potential for life extensions. In the future, PHM will equip systems with the capability to assess their own real-time performance (self-cognizant health management and diagnostics) under actual usage conditions and adaptively enhance life cycle sustainment with risk-mitigation actions that virtually eliminate unplanned failures.  The application areas of PHM include aerospace structures and avionics, automobiles, civil structures, consumer and industrial products, defense infrastructure and medical equipment, and machine tools. This is an interdisciplinary course, and students in many areas, including aerospace, civil, electrical, and mechanical engineering, and engineering management, are welcome. Students will get the opportunity to learn the basic scientific foundations that enable PHM and work on its implementation for real-life applications through projects. Experts from industry, government, and academia will teach guest lectures in this course. Some of the topics covered in this course include: Fundamentals of Prognostics and Health Management (PHM). Internet of Things, Big Data, and Sensors for PHM. Data Pre-processing (Data Cleansing, Feature Extraction, Feature Selection, Feature Learning). Machine Learning and Artificial Intelligence for Anomaly Detection, Diagnostics, and Prognostics. PHM Cost and Return on Investment. Valuation and Optimization of PHM-enabled Maintenance Decisions. Software Tools for PHM. Predictive Maintenance. PHM Applications in Industry. For more information, contact Prof. Michael Pecht, Dr. Michael H. Azarian, and Prof. Jay Lee. http://www.ece.umd.edu/events/index.php?mode=4&id=20733 http://www.ece.umd.edu/events/index.php?mode=4&id=20733 Tuesday, October 13, 2026 6:00 AM, College Park Marriott Hotel & Conference Center, This isn’t just a conference; it’s a high-level convergence of industry stakeholders, policymakers, financiers, and tech trailblazers. We’re bringing together the forward thinkers who are keeping tabs on the changing energy landscape, leveraging groundbreaking solutions to optimize our grid, accelerating decarbonization, and driving Maryland’s economic evolution. What to Expect:  Tuesday, Oct. 13: Kick off the summit with our Opening Luncheon, followed by dedicated networking sessions designed to spark collaborative breakthroughs.  Wednesday, Oct. 14: Dive into expert panels on AI-driven efficiency, grid modernization, and the future of climate tech.  Register here http://www.ece.umd.edu/events/index.php?mode=4&id=20743 http://www.ece.umd.edu/events/index.php?mode=4&id=20743 Friday, August 14, 2026 1:00 PM, Online registration, The National Science Foundation (NSF) I-Corps program delivers an immersive learning experience about how to successfully translate innovations into real-world impact. LEARN what it takes to commercialize your innovation, along with the barriers to adoption and how to overcome them. DETERMINE the real-world impacts of your research or technology. EXPAND your network with introductions to potential mentors, customers, and investors. INCREASE the commercial potential of your innovation. SAVE years and money by accelerating your understanding of your product, customer, and market. ESTABLISH credibility and a path to the NSF’s national I-Corps program, which provides grants of $50,000 for I-Corps, and subsequent opportunities for SBIR grants and other funding. To participate in the August Mid-Atlantic I-Corps Customer Discovery Workshops, you must complete the short I-Corps Prep by Wednesday, August 8. You may not apply to the program until you have completed I-Corps Prep. You can enroll in I-Corps Prep at any time here at this link This Hub-wide cohort is hosted by the University of Maryland, College Park. Anyone from around the Hub and Hub partners is welcome to apply. http://www.ece.umd.edu/events/index.php?mode=4&id=20744 http://www.ece.umd.edu/events/index.php?mode=4&id=20744