BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
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:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
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
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240603T130000
DTEND;TZID=America/New_York:20240603T150000
DTSTAMP:20260403T174340
CREATED:20240531T131800Z
LAST-MODIFIED:20240531T131800Z
UID:10007976-1717419600-1717426800@seasevents.nmsdev7.com
SUMMARY:ESE PhD Thesis Defense: "Integrated Electronic-Photonic Solutions From Quantum Control Systems to Optical Transmitters"
DESCRIPTION:Silicon’s advanced fabrication processes have enabled the miniaturization of complex electronic systems\, enhancing performance and efficiency. Recent technological developments have further expanded silicon’s utility to integrate photonic systems\, merging electronic and photonic technologies on a single chip. This integration has opened new avenues for high-speed communication and computation\, attracting significant interest from both research and industry. In this thesis\, integrated electronic-photonic solutions ranging from quantum control systems to optical transmitters are presented. Firstly\, an integrated reconfigurable quantum control system is demonstrated. This system is used to determine electron-spin resonance frequency and perform Rabi\, Ramsey\, and Hahn-echo measurements for an NV center spin qubit in diamond. Secondly\, two monolithically integrated single-channel optical PAM-4 transmitters are implemented\, studied\, and compared. Lastly\, monolithically integrated 8- and 32-channel wavelength-division multiplexed optical transmitter systems are presented. These systems operate in the infrared optical C-band using custom-designed two-section PN-capacitive micro-ring modulators. The 8- and 32-channel systems support aggregate data rates up to 256 Gb/s and 1.024 Tb/s\, respectively\, and are highly integrated with a wavelength stabilization circuit\, test data generators\, and high-swing electrical drivers on the same CMOS silicon-on-insulator chip.
URL:https://seasevents.nmsdev7.com/event/ese-phd-thesis-defense-integrated-electronic-photonic-solutions-from-quantum-control-systems-to-optical-transmitters/
LOCATION:Towne 337
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:20240530T123000
DTEND;TZID=America/New_York:20240530T140000
DTSTAMP:20260403T174340
CREATED:20240530T143637Z
LAST-MODIFIED:20240530T143637Z
UID:10007974-1717072200-1717077600@seasevents.nmsdev7.com
SUMMARY:PRIML Seminar: "Matrix Completion and Algebraic Geometry" (Manolis Tsakiris)
DESCRIPTION:
URL:https://seasevents.nmsdev7.com/event/priml-seminar-matrix-completion-and-algebraic-geometry/
LOCATION:Levine 307\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240530T123000
DTEND;TZID=America/New_York:20240530T133000
DTSTAMP:20260403T174340
CREATED:20240530T151549Z
LAST-MODIFIED:20240530T151549Z
UID:10007975-1717072200-1717075800@seasevents.nmsdev7.com
SUMMARY:PRIML Seminar: "Matrix Completion and Algebraic Geometry"
DESCRIPTION:Low-rank matrix completion is a well-studied problem\, for which a rich theory exists\, mainly from the optimization and statistical points of view. However\, the majority of the theoretical analysis in the literature assumes random observation patterns. On the other hand\, the pattern of observed entries depends on the nature of each application\, and is usually not random. This leads to the following fundamental question: What are the uniquely completable patterns at a certain rank r? This is a natural question of algebraic geometry that we will undertake in this talk (no prior experience with algebraic geometry will be assumed).
URL:https://seasevents.nmsdev7.com/event/priml-seminar-matrix-completion-and-algebraic-geometry-2/
LOCATION:Towne 307\, 220 S. 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar,Colloquium
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240528T100000
DTEND;TZID=America/New_York:20240528T120000
DTSTAMP:20260403T174340
CREATED:20240508T135721Z
LAST-MODIFIED:20240508T135721Z
UID:10007967-1716890400-1716897600@seasevents.nmsdev7.com
SUMMARY:BE Doctoral Dissertation: "Biologic Delivery to Preserve Joint Health and Promote Tissue Repair" (Elisabeth Lemmon)
DESCRIPTION:The Department of Bioengineering at the University of Pennsylvania and Dr. Rob Mauck are pleased to announce the Doctoral Dissertation Defense of Elisabeth Lemmon.\n\nTitle: Biologic Delivery to Preserve Joint Health and Promote Tissue Repair\nDate: May 28\, 2024\nTime: 10:00 AM\nLocation: JMB Class of ’62 Auditorium\nZoom link – https://upenn.zoom.us/j/93923840583?pwd=Tjl5bE1rMEFESlJKRm9ROEYzSU1VZz09\n\n\nPlease email elemmon@vet.upenn.edu for the zoom password.\n\n\nThe public is welcome to attend.
URL:https://seasevents.nmsdev7.com/event/be-doctoral-dissertation-biologic-delivery-to-preserve-joint-health-and-promote-tissue-repair-elisabeth-lemmon/
LOCATION:JMB Reunion Auditorium\, 3620 Hamilton Walk\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Doctoral,Graduate,Student,Dissertation or Thesis Defense
ORGANIZER;CN="Bioengineering":MAILTO:be@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240524T130000
DTEND;TZID=America/New_York:20240524T140000
DTSTAMP:20260403T174340
CREATED:20240430T190822Z
LAST-MODIFIED:20240430T190822Z
UID:10007958-1716555600-1716559200@seasevents.nmsdev7.com
SUMMARY:GRASP Seminar: Yinghao Xu\, Stanford University\, "Large Reconstruction Model for Efficient 3D Reconstruction and Generation"
DESCRIPTION:*This seminar will be held in-person in Wu and Chen as well as virtually via Zoom.  \nABSTRACT\nOver the past year\, the large language model has achieved significant milestones\, approaching human-like intelligence across various domains. However\, there has been limited investigation into large-scale 3D reconstruction in the literature. In this talk\, I will primarily focus on our recent advancements in large-scale 3D reconstruction.\nI will start with an introduction to the basics of the Large-scale Reconstruction Model (LRM)\, aiming to develop a robust and highly generalizable 3D reconstruction system utilizing high-quality 3D data. I will also explain how LRM can be used to efficiently perform high-quality text-to-3D and image-to-3D generation tasks\, such as Instant3D and DMV3D.Finally\, I will highlight our recent work\, specifically our progress in large-scale 3D reconstruction using Gaussian Splatting (GRM). As a large-scale reconstructor\, GRM can reconstruct a 3D asset from sparse-view images in about 0.1 seconds. Moreover\, GRM shows promising potential in generative tasks\, such as text-to-3D and image-to-3D\, through its integration with existing multi-view diffusion models.
URL:https://seasevents.nmsdev7.com/event/grasp-seminar-yinghao-xu-stanford-university-large-reconstruction-model-for-efficient-3d-reconstruction-and-generation/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut 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:20240520T121500
DTEND;TZID=America/New_York:20240520T141500
DTSTAMP:20260403T174340
CREATED:20240507T204607Z
LAST-MODIFIED:20240507T204607Z
UID:10007966-1716207300-1716214500@seasevents.nmsdev7.com
SUMMARY:Penn Engineering 2024 Commencement Open House
DESCRIPTION:On Monday\, May 20\, 2024\, from 12:15-2:15 p.m.\, Penn Engineering will host an Open House for the School’s returning graduates and their families throughout the first floors of the main Engineering complex\, immediately following the University Ceremony. \nIncluded are photo booth opportunities\, a t-shirt giveaway (including a live t-shirt press!)\, and light refreshments. Please join us!
URL:https://seasevents.nmsdev7.com/event/penn-engineering-2024-commencement-open-house/
LOCATION:PA
CATEGORIES:Faculty,Doctoral,Graduate,Student,Master's,Commencement,Undergraduate,Staff
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240518T140000
DTEND;TZID=America/New_York:20240518T160000
DTSTAMP:20260403T174340
CREATED:20240503T170249Z
LAST-MODIFIED:20240503T170249Z
UID:10007961-1716040800-1716048000@seasevents.nmsdev7.com
SUMMARY:Penn Engineering Commencement 2024: Undergraduate Ceremony
DESCRIPTION:Celebrate the Penn Engineering Undergraduate Class of 2024. Additional information is available on the Penn Engineering Commencement website.
URL:https://seasevents.nmsdev7.com/event/penn-engineering-commencement-2024-undergraduate-ceremony/
LOCATION:Palestra\, 223 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240518T090000
DTEND;TZID=America/New_York:20240518T103000
DTSTAMP:20260403T174340
CREATED:20240502T165541Z
LAST-MODIFIED:20240502T165541Z
UID:10007960-1716022800-1716028200@seasevents.nmsdev7.com
SUMMARY:Celebrating Penn Engineers: Past\, Present and Future
DESCRIPTION:Penn Engineering invites all alumni\, family and friends to join us for the dedication of two new hallway installations that honor the past while inspiring the future. Join Dean Kumar to reconnect with classmates and hear remarks from notable alumni. Breakfast will be provided at 9:00am\, program begins at 9:45 a.m. Click to see the full schedule of events for Penn Alumni Weekend.
URL:https://seasevents.nmsdev7.com/event/celebrating-penn-engineers-past-present-and-future/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Alumni
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240517T140000
DTEND;TZID=America/New_York:20240517T163000
DTSTAMP:20260403T174340
CREATED:20240503T171127Z
LAST-MODIFIED:20240503T171127Z
UID:10007962-1715954400-1715963400@seasevents.nmsdev7.com
SUMMARY:Penn Engineering Commencement 2024: Master's Ceremony
DESCRIPTION:Celebrate the Penn Engineering 2024 Master’s Graduates. Additional information is available on the Penn Engineering Commencement website.
URL:https://seasevents.nmsdev7.com/event/penn-engineering-commencement-2024-masters-ceremony/
LOCATION:Palestra\, 223 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240516T160000
DTEND;TZID=America/New_York:20240516T171500
DTSTAMP:20260403T174340
CREATED:20240503T171340Z
LAST-MODIFIED:20240503T171340Z
UID:10007963-1715875200-1715879700@seasevents.nmsdev7.com
SUMMARY:Penn Engineering Commencement 2024: Doctoral Ceremony
DESCRIPTION:Celebrate Penn Engineering’s 2024 Doctoral Graduates. Additional information is available on the Penn Engineering Commencement website.
URL:https://seasevents.nmsdev7.com/event/penn-engineering-commencement-2024-doctoral-ceremony/
LOCATION:Irvine Auditorium\, 3401 Spruce Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240515T140000
DTEND;TZID=America/New_York:20240515T150000
DTSTAMP:20260403T174340
CREATED:20240501T190218Z
LAST-MODIFIED:20240501T190218Z
UID:10007959-1715781600-1715785200@seasevents.nmsdev7.com
SUMMARY:MEAM Seminar: "Computational FSI Modeling of the Cardiovascular System"
DESCRIPTION:Computational modeling and simulation has become a routine part of cardiovascular clinical research. These techniques leverage medical imaging to construct patient-specific models that can be used to study disease processes\, design and evaluate medical devices\, perform predictive surgery\, and aid in clinical decision-making. Modern cardiovascular simulations often require millions of elements and tens of thousands of time steps. Thus\, there is a need for accurate\, robust\, and efficient computational techniques to simulate complex pulsatile hemodynamics potentially coupled with deformable vessel walls or heart valves. In this talk\, I will discuss computational methods for simulating blood flow and for modeling fluid-structure interaction problems in the cardiovascular system. I will present improvements to existing finite element solver technologies\, including development of a block preconditioning technique for fully implicit time integration schemes coupled to reduced dimension models of the cardiovascular system (e.g. Windkessel model). Mass conservation properties of various techniques will be investigated in a patient-specific aorta model. Next\, I will show how these improved techniques can be leveraged to simulate fluid-structure interaction problems using the arbitrary Lagrangian-Eulerian method combined with a quasi-Newton solution procedure. Lastly\, I will present an immersed approach to computational modeling of fluid-structure interaction problems and demonstrate the potential of the method to simulate heart valves dynamics over the cardiac cycle using an idealized problem.
URL:https://seasevents.nmsdev7.com/event/meam-seminar-computational-fsi-modeling-of-the-cardiovascular-system/
LOCATION:Moore 212
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240514T100000
DTEND;TZID=America/New_York:20240514T113000
DTSTAMP:20260403T174340
CREATED:20240429T154117Z
LAST-MODIFIED:20240429T154117Z
UID:10007957-1715680800-1715686200@seasevents.nmsdev7.com
SUMMARY:MEAM Seminar: "The Mechanics of Animal Collective Behavior: From Insect Swarms to Fish Schools"
DESCRIPTION:An incredible diversity of organisms\, from bacteria and social insects to bird flocks and fish schools\, self-organize to achieve collective tasks. They have inspired the development of decentralized algorithms and robotic swarms. While numerous models have been proposed to understand the self-organization of animal groups\, the role of mechanics was rarely considered. In this talk\, I will demonstrate experiments and models of the collective behaviors of two insect species\, red imported fire ants (Solenopsis invicta) and black soldier fly larvae (Hermetia illucens)\, in both static and moving fluids. Particular attention will be paid to how their collective behaviors are affected by fluid forces. My results suggest a timescale associated with the limit of animal perception and locomotion. Collective phenomena shorter than such a timescale are driven by mechanical forces and random movements of the individuals. To conclude\, I will extend the framework to consider the hydrodynamics of fish schools and discuss how I use computer vision and biomimetic robots to seek insights into this complex system.
URL:https://seasevents.nmsdev7.com/event/meam-seminar-the-mechanics-of-animal-collective-behavior-from-insect-swarms-to-fish-schools/
LOCATION:David Rittenhouse Laboratory Building\, Room A5\, 209 S. 33rd 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:20240513T150000
DTEND;TZID=America/New_York:20240513T170000
DTSTAMP:20260403T174340
CREATED:20240510T130519Z
LAST-MODIFIED:20240510T130519Z
UID:10007968-1715612400-1715619600@seasevents.nmsdev7.com
SUMMARY:ESE PhD Thesis Defense: "Low Noise and Low Power Front-end Circuit Design for Bio-Signal Recordings"
DESCRIPTION:Bio-signals in living objects are the signals thatcarry physiological information from one part of the body to another. Studying bio-signals can extract data that maps health status or body activities for medical purposes. Implantable and wearable devices of small volume for measuring different bio-signals are desired for medical applications where the devices measure the signals with further processing to provide feedback for diagnosis and treatment. Bio-signals produced by the body usually have a small amplitude requiring low noise and low power analog front-end amplifiers and signal processing circuitry. \nThis talk will focus on low noise and low power readout circuits for magnetic sensing systems to acquire bio-magnetic fields. Compared to bio-electrical recordings\, bio-magnetic sensing is non-invasive and non-contact. PCB-based readout electronics for strain modulated multiferroic sensors with a bandwidth of 3.4 kHz and a magnetic noise floor at 1 kHz of 98.5 pT/√Hz is implemented for understanding the circuit and the sensor noise models for modulated multiferroic sensor-readout systems. To reduce the power consumption\, an ASIC readout circuit in 180 nm CMOS for the sensor is designed and implemented. By utilizing a demodulator first architecture\, measurements for the sensor-readout system demonstrate a 127 pT/√Hz magnetic noise floor at 1 kHz and a low power consumption of 5.9 mW. To further improve the noise performance at low frequencies\, readout circuit in BiCMOS and a differential structure are implemented to achieve a magnetic noise floor of 85 pT/√Hz at 1 kHz\, and 300 pT/√Hz at 10 Hz with a power consumption of 5.6 mW. In addition\, a low intermediate frequency (low-IF) demodulation readout circuit is implemented and measured to eliminate the 1/f flicker noise and realizes a noise floor of 722 pT√Hz at 1 Hz with the power consumption of 2.9 mW. The noise and power consumption that the magnetic sensing systems have achieved are significantly lower than alternative magnetic sensor systems of similar volume\, which outlines an excellent solution for low-power\, low-noise\, wearable\, on-body sensing in the future.
URL:https://seasevents.nmsdev7.com/event/ese-phd-thesis-defense-low-noise-and-low-power-front-end-circuit-design-for-bio-signal-recordings/
LOCATION:Room 221\, 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:20240508T153000
DTEND;TZID=America/New_York:20240508T163000
DTSTAMP:20260403T174340
CREATED:20240116T183826Z
LAST-MODIFIED:20240116T183826Z
UID:10007815-1715182200-1715185800@seasevents.nmsdev7.com
SUMMARY:CBE Seminar: "Chemical Synthesis Enabled by Information" (Tim Cernak\, University of Michigan)
DESCRIPTION:Abstract\nAdvancing the synthesis of small molecules is critical to the advent of new medicines\, materials\, and agrochemicals. Our lab has been exploring strategies in chemical synthesis — both in reaction method development and total synthesis — that leverage modern data science techniques and robotics. This presentation will share some recent results using informatics to target novel amine-acid coupling reactions\, and algorithms to streamline multistep synthesis. Chemical synthesis enabled by data science techniques and automation will be a consistent theme of the research\, aiming towards a future state where medicines are invented at a rapid pace.
URL:https://seasevents.nmsdev7.com/event/cbe-seminar-chemical-synthesis-enabled-by-information-tim-cernak-university-of-michigan/
LOCATION:Glandt Forum\, Singh Center for Nanotechnology\, 3205 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:20240507T100000
DTEND;TZID=America/New_York:20240507T120000
DTSTAMP:20260403T174340
CREATED:20240308T175024Z
LAST-MODIFIED:20240308T175024Z
UID:10007894-1715076000-1715083200@seasevents.nmsdev7.com
SUMMARY:IEEE Grace Hopper A-0 Milestone Celebration
DESCRIPTION:
URL:https://seasevents.nmsdev7.com/event/ieee-grace-hopper-milestone-celebration/
LOCATION:Greenberg Lounge (Room 114)\, Skirkanich Hall\, 210 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240507T093000
DTEND;TZID=America/New_York:20240507T140000
DTSTAMP:20260403T174340
CREATED:20240424T165620Z
LAST-MODIFIED:20240424T165620Z
UID:10007956-1715074200-1715090400@seasevents.nmsdev7.com
SUMMARY:Spring 2024 Robotics MSE Thesis Presentations
DESCRIPTION:This is a hybrid event with in-person attendance in the GRASP Treehouse and virtual attendance via Zoom. \nRSVPs required for in-person attendees. Please RSVP here. \n  \n9:30am – Welcome Remarks\nDr. Ani Hsieh – ROBO Program Chair \n9:35am – Beiming Li\nAdvised by: Dr. Vijay Kumar\n“Depth Completion of Glass Surfaces from a Single-View Polarization Image“ \n  \n  \n10:05am – Derek Cheng\nAdvised by: Dr. Vijay Kumar\n“Multimodal Neural Rendering using Agricultural Robotics Field Data” \n  \n  \n10:35am – Coffee Break \n10:50am – Daryl Hurwitz\nAdvised by: Dr. Flavia Vitale\n“Rapid Fabrication of Patient Specific High Density Microelectrode Arrays” \n  \n  \n11:20am – Sharanya Venkatesh\nAdvised by: Dr. Michael Posa\n“Approximating global MPC for Contact Rich Manipulation Using Local Feedback”\n \n  \n  \n11:50am – Jiaqi Lian\nAdvised by: Dr. Linh Thi Xuan Phan\n“Online Rotor Fault Detection and Isolation for Vertical Takeoff and Landing Vehicles” \n  \n  \n12:20pm – Lunch \n12:50pm – Yifan Wang\nAdvised by: Dr. Linh Thi Xuan Phan\n“FDIR Verification for Faults in eVTOL Vehicles: Dynamic Analysis and Control” \n  \n  \n1:20pm – James Springer\nAdvised by: Dr. Dinesh Jayaraman\n“Leveraging Privileged Information for Sample-Efficient Reinforcement Learning” \n  \n  \n1:50pm – End of Presentations
URL:https://seasevents.nmsdev7.com/event/spring-2024-robotics-mse-thesis-presentations/
LOCATION:GRASP Treehouse – Pennovation Complex; LAB Building (Bldg 250 – Suite 250)\, 3401 Grays Ferry\, Philadelphia\, 19146\, 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:20240502T100000
DTEND;TZID=America/New_York:20240502T153000
DTSTAMP:20260403T174340
CREATED:20240416T211540Z
LAST-MODIFIED:20240416T211540Z
UID:10007952-1714644000-1714663800@seasevents.nmsdev7.com
SUMMARY:Penn NRT Soft AE Annual Symposium: Exploring research & educational intersections of soft materials\, autonomous experimentation & science policy
DESCRIPTION:Please register at the event webpage\, where you will also find abstracts and bios for the speakers. \nInvited talks include: \nExploring Polymer Blend Directed Self-Assembly Using Autonomous X-Ray Scattering\nGreg Doerk\, PhD\, Brookhaven National Lab \nMachine-Learning-Guided Discovery of New Electrochemical Reactions\nAndrew Zahrt\, PhD\, University of Pennsylvania \nAsk an Expert about ChatGPT\nChris Callison-Burch\, PhD\, University of Pennsylvania \nEngineering’s Hardest Problem\nGwen Ottinger\, PhD\, Drexel University
URL:https://seasevents.nmsdev7.com/event/penn-nrt-soft-ae-annual-symposium-exploring-research-educational-intersections-of-soft-materials-autonomous-experimentation-science-policy/
LOCATION:Glandt Forum\, Singh Center for Nanotechnology\, 3205 Walnut Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240501T120000
DTEND;TZID=America/New_York:20240501T133000
DTSTAMP:20260403T174340
CREATED:20240419T172144Z
LAST-MODIFIED:20240419T172144Z
UID:10007954-1714564800-1714570200@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: "Lifelong Learning for Autonomous Systems: Progress and Challenges" (Eric Eaton\, University of Pennsylvania)
DESCRIPTION:ABSTRACT: \nResearch in lifelong or continual machine learning has advanced rapidly over the past few years\, primarily focusing on enabling learned models to acquire new tasks over time while avoiding catastrophic forgetting of previous tasks. However\, autonomous systems still lack the ability to rapidly learn new generalizable skills by building upon and continually refining their learned knowledge—a hallmark of lifelong learning in humans and animals. In this talk\, I will examine our progress toward lifelong machine learning and its application to autonomous systems\, exploring recent work in compositional representations and self-supervision. We’ll then discuss how far we have come and the open problems that remain toward learning generalizable skills in lifelong settings. \n  \nZOOM LINK (if unable to attend in-person): https://upenn.zoom.us/j/94522983788
URL:https://seasevents.nmsdev7.com/event/asset-seminar-lifelong-learning-for-autonomous-systems-progress-and-challenges-eric-eaton-university-of-pennsylvania/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240430T130000
DTEND;TZID=America/New_York:20240430T140000
DTSTAMP:20260403T174340
CREATED:20240405T164610Z
LAST-MODIFIED:20240405T164610Z
UID:10007934-1714482000-1714485600@seasevents.nmsdev7.com
SUMMARY:AI Month: Closing Keynote Address
DESCRIPTION:AI Month at Penn concludes with closing remarks by Vijay Kumar\, Nemirovsky Family Dean\, Penn Engineering. This will be followed by a panel discussion moderated by Susan Davidson\, Weiss Professor\, Computer and Information Science (CIS). Panel guests include: Zachary Ives\, Adani President’s Distinguished Professor\, CIS;\nGeorge Pappas\, UPS Foundation Professor of Transportation\, Electrical and Systems Engineering; and Chris Callison-Burch\, Associate Professor\, CIS. \nPanel: 1:00-2:00 p.m.\nGlandt Forum\, Singh Center \nA reception will follow.
URL:https://seasevents.nmsdev7.com/event/ai-month-closing-keynote-address/
LOCATION:Singh Center for Nanotechnology\, 3205 Walnut Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240430T100000
DTEND;TZID=America/New_York:20240430T113000
DTSTAMP:20260403T174340
CREATED:20240411T160343Z
LAST-MODIFIED:20240411T160343Z
UID:10007945-1714471200-1714476600@seasevents.nmsdev7.com
SUMMARY:MEAM Seminar: "Collective Transitions in Beating Cilia and Swimming Fish"
DESCRIPTION:I will discuss the collective modes that spontaneously emerge in ciliary carpets and fish schools. In both systems\, the fluid medium couples the motion of individuals in the group. Flow coupling is dominated by viscous forces in cilia and by inertial interactions in fish. I will show\, numerically and analytically in the continuum limit\, that the waves that emerge in ciliary carpets are robust to morphological and kinematic perturbations of the ciliated tissues. In fish schools\, I will show intermittent collective behavior with back-and-forth switching between schooling and milling\, and I will analyze the bifurcations underlying phase transitions by lifting the stochastic dynamics of individual fish onto a Fokker-Planck equation that governs the group dynamics. These problems highlight how structure\, activity\, and environment interconnect to produce emergent biological function; our work provides a framework for establishing structure-to-function maps across multiple length scales to help understand\, probe\, and engineer emergent phenomena in biological and biomedical systems.
URL:https://seasevents.nmsdev7.com/event/meam-seminar-collective-transitions-in-beating-cilia-and-swimming-fish/
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:20240429T140000
DTEND;TZID=America/New_York:20240429T150000
DTSTAMP:20260403T174340
CREATED:20240415T220135Z
LAST-MODIFIED:20240415T220135Z
UID:10007951-1714399200-1714402800@seasevents.nmsdev7.com
SUMMARY:MEAM Master's Thesis Defense: "Modeling Off-Grid Photovoltaics Integrated with Micro-Cogeneration and Electrical Energy Storage"
DESCRIPTION:Due to the elevated expenditure of fossil fuels and their adverse impacts on climate change resulting from greenhouse gas emissions\, it is imperative to integrate clean energy sources alongside fossil fuels. This study presents the design\, simulation\, and optimization of an integrated system comprising solar photovoltaics\, micro-cogeneration\, and electrical energy storage to achieve energy self-sufficiency independently from external energy sources. Moreover\, the study determines the maximum cost of the converter that can be economically added to the heating system\, enabling it to generate both heat and electricity simultaneously. It also calculates the unit electricity cost for each combination. The modeled system is capable of meeting all required electricity and heat demands. Yet\, the model presents a range of alternatives for configuring the capacity required for PV panels\, batteries\, and converter\, each resulting in varied overall costs. It has been determined that when conversion efficiency increases\, the costs associated with PV panels and batteries decrease\, as do the overall cost. However\, the maximum cost of the converter necessary for achieving cost-effectiveness is not constant\, but rather changes according to its efficiency. Ultimately\, the unit electricity cost varies\, decreasing with increasing converter rated power until a certain value\, then increasing.
URL:https://seasevents.nmsdev7.com/event/meam-masters-thesis-defense-modeling-off-grid-photovoltaics-integrated-with-micro-cogeneration-and-electrical-energy-storage/
LOCATION:Room 2C6\, David Rittenhouse Laboratory Building\, 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:20240426T140000
DTEND;TZID=America/New_York:20240426T160000
DTSTAMP:20260403T174340
CREATED:20240411T185142Z
LAST-MODIFIED:20240411T185142Z
UID:10007946-1714140000-1714147200@seasevents.nmsdev7.com
SUMMARY:Entrepreneurship Seminar Series: Pathways to Impact
DESCRIPTION:Entrepreneurship Seminar Series: Pathways to Impact \nThis session brings together a panel of current and former faculty and PhDs that have brought their technology to market and have worked in both academia and commerce. Panelists will discuss the opportunities and approaches they took to create companies\, leverage experience in academia\, and drive research into commercial success. \nRefreshments will be provided. \nWho: Faculty\, Post-Docs\, & PhD students \nWhere: Towne 327 \nWhen: 2-4:00 pm\, Friday April 26\, 2024 \nAdd to calendar: Apple  Google  Office 365  Outlook  Outlook.com  Yahoo \nRSVP Here (Not required)
URL:https://seasevents.nmsdev7.com/event/entrepreneurship-seminar-series-pathways-to-impact/
LOCATION:Towne 327
CATEGORIES:Faculty,Doctoral,Graduate,Panel Discussion,Postdoctoral
ORGANIZER;CN="Penn Engineering Entrepreneurship":MAILTO:sevile@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240426T140000
DTEND;TZID=America/New_York:20240426T150000
DTSTAMP:20260403T174340
CREATED:20240401T175825Z
LAST-MODIFIED:20240401T175825Z
UID:10007926-1714140000-1714143600@seasevents.nmsdev7.com
SUMMARY:PICS Colloquium: "Representations Learnt from Synthetic Volumes Enable Training-free Medical Image Analysis"
DESCRIPTION:Current medical image analysis projects involve months to years of data annotation and custom technical development. This talk introduces methods to train networks that generalize out-of-the-box to new modalities\, anatomies\, and datasets all without retraining for the specific use case. Our key contributions include (A) generative models driven by biomedical shape priors that synthesize wildly variable training data\, and (B) a multi-scale dense representation learning algorithm that leverages the synthetic data to learn contrast-invariant representations. We will show that a single U-Net pretrained in this manner can then extract features that enable state-of-the-art 3D multimodality image registration and can also serve as a general-purpose foundation model for few-shot segmentation across arbitrary biomedical datasets. We will also briefly demonstrate translational applications of the proposed methods to ongoing studies of disordered pregnancies in fetal and maternal MRI.
URL:https://seasevents.nmsdev7.com/event/pics-colloquium-representations-learnt-from-synthetic-volumes-enable-training-free-medical-image-analysis/
LOCATION:PICS Conference Room 534 – A Wing \, 5th Floor\, 3401 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Colloquium
ORGANIZER;CN="Penn Institute for Computational Science (PICS)":MAILTO:dkparks@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240426T120000
DTEND;TZID=America/New_York:20240426T130000
DTSTAMP:20260403T174340
CREATED:20240404T171111Z
LAST-MODIFIED:20240404T171111Z
UID:10007929-1714132800-1714136400@seasevents.nmsdev7.com
SUMMARY:MEAM Master's Thesis Defense: "The Rheology and Microphysics of Monodisperse Synthetic Mucin"
DESCRIPTION:Mucus\, a complex fluid produced by every living organism\, has multiple essential functions including acting as an effective barrier layer in various bodily processes\, many of which involve important rheological (flow) and tribological (adhesive\, lubricative) functions. The primary component of mucuses are mucins – highly glycosylated\, linear polypeptides. Understanding how the structure and properties of mucins control the overall behavior of mucus is thus of substantial interest. However\, natural mucus is often contaminated with non-mucin constituents that affect the rheological response\, and purifying mucus without damaging the mucins themselves is difficult. Here\, fully synthetic\, monodisperse mucins have been prepared by a collaborator. Aqueous solutions of these mucins have been studied for comparison to the rheological response shown by natural mucin solutions. The purity and structural control of these synthetic mucins provide a model system where the mechanistic sources of the mucus’ rheological response can be isolated and identified. Experimental bulk rheometry demonstrates a shear-thinning behavior with a yield-stress fluid response. This behavior is attributed to associations between mucin molecules localized to the liquid-air interface\, which contradicts previous literature on natural mucins. This conclusion is supported by interfacial rheology measurements and by a mathematical model encapsulating the dynamics of a thin mucin layer under shear. This work furthers the understanding of the dynamics of mucin solutions and the qualitative microphysics surrounding their dynamics.
URL:https://seasevents.nmsdev7.com/event/meam-masters-thesis-defense-the-rheology-and-microphysics-of-monodisperse-synthetic-mucin/
LOCATION:Room 2C8\, David Rittenhouse Laboratory Building\, 209 South 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:20240426T103000
DTEND;TZID=America/New_York:20240426T114500
DTSTAMP:20260403T174340
CREATED:20240329T152051Z
LAST-MODIFIED:20240329T152051Z
UID:10007911-1714127400-1714131900@seasevents.nmsdev7.com
SUMMARY:Spring 2024 GRASP on Robotics: Marco Pavone\, Stanford University & NVIDIA\, "Rethinking AV Development with AV Foundation Models"
DESCRIPTION:This is a hybrid event with in-person attendance in Wu and Chen and virtual attendance on Zoom. \nABSTRACT\nFoundation models\, trained on vast and diverse data encompassing the human experience\, are at the heart of the ongoing AI revolution influencing the way we create\, problem solve\, and work. These models\, and the lessons learned from their construction\, can also be applied to the way we develop a similarly transformative technology\, autonomous vehicles. In this talk\, I will highlight recent research efforts towards rethinking elements of an AV program both in the vehicle and in the data center\, with an emphasis on (1) composing ingredients for universal and controllable end-to-end simulation\, (2) architecting autonomy stacks that leverage foundation models to generalize to long-tail events\, and (3) ensuring safety with foundation models in the loop.
URL:https://seasevents.nmsdev7.com/event/spring-2024-grasp-on-robotics-marco-pavone-stanford-university-nvidia-rethinking-av-development-with-av-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:20240425T140000
DTEND;TZID=America/New_York:20240425T150000
DTSTAMP:20260403T174340
CREATED:20240417T181645Z
LAST-MODIFIED:20240417T181645Z
UID:10007953-1714053600-1714057200@seasevents.nmsdev7.com
SUMMARY:PRECISE Seminar: Optical Coherence Tomography - From Conception to Current Frontiers
DESCRIPTION:Optical coherence tomography (OCT) is a technology invented in 1991 to image small critical tissue structures throughout the body with micrometer resolution. It is widely used in the management of eye and coronary heart diseases. In 2023\, OCT received broad attention when its inventors received the prestigious Lasker-DeBakey Clinic Medical Research Award and the National Medal of Technology and Innovation from President Biden. For me\, it was the culmination of 3 decades of work as an engineer\, clinician\, and translational researcher\, as well as an even longer journey as an immigrant who tapped into the potential of America’s great research universities. \nI will present OCT from an inventor’s perspective. The physical principles will be explained with illustrations on measuring the time-of-flight of light with interferometry. I will tell the story of the aha moment when the idea of OCT came to my mind\, as well as the rapid pace of development that made OCT a clinical reality. The biggest applications of OCT in the management of eye diseases will be shown. Recent advances made at OHSU that enable OCT to advance beyond the imaging of tissue structure to the detection of blood flow and photoreceptor function will be described. \nOCT is still a rapidly developing technology. The technical capabilities have improved in many aspects\, but the most astounding has been the continual improvement in imaging speed\, which has doubled approximately every 2.5 years over the past 3 decades. The technological advances have made more and more clinical applications feasible. I will present a vision for the broader applications of OCT\, which includes imaging the eye to assess brain and cardiovascular diseases\, as well as direct OCT imaging of other target organs such as the skin\, digestive tract\, brain\, inner/middle ear\, and teeth.
URL:https://seasevents.nmsdev7.com/event/precise-seminar-optical-coherence-tomography-from-conception-to-current-frontiers/
LOCATION:Room 307\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
ORGANIZER;CN="PRECISE":MAILTO:wng@cis.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240425T103000
DTEND;TZID=America/New_York:20240425T120000
DTSTAMP:20260403T174340
CREATED:20240421T211723Z
LAST-MODIFIED:20240421T211723Z
UID:10007955-1714041000-1714046400@seasevents.nmsdev7.com
SUMMARY:MSE Seminar: "Probabilistic Digital Twins for Structure Preserving Simulation and Scientific Discovery"
DESCRIPTION:Despite the recent flurry of work employing machine learning to develop surrogate models to accelerate scientific computation\, the “black-box” underpinnings of current techniques fail to provide the verification and validation guarantees provided by modern finite element methods. In this talk we present a data-driven finite element exterior calculus for building accelerated reduced-order models of multiphysics systems when the governing equations are either unknown or require closure. Key to the framework is a fully differentiable partition of unity which provides a machine learnable alternative to a traditional computational mesh\, upon which we simultaneously learn physical relevant control volumes alongside corresponding integral balance laws. We demonstrate that resulting models may realize speedup of over 1000x over traditional finite element simulations\, while guaranteeing the exact treatment of physical constraints and numerical stability. We then briefly summarize recent work developing Bayesian underpinnings for these models\, providing characterization of epistemic uncertainty which may be used to drive active learning tasks. \nWith tools for building probabilistic digital twins in hand\, we then turn to our work integrating physical models into high-throughput material discovery experiments to characterize process-structure-property relationships. In material science\, datasets are comparatively small relative to the combinatorially massive space of potential designs. We combat this by fusing information spanning multimodal characterization (e.g. XRD\,TEM\,SEM\,EBSD) of differing fidelity and throughput and incorporating data-driven models. We end by summarizing some campaigns conducted at Sandia National Laboratories applying these tools to physical vapor deposition\, metal additive manufacturing\, and electrodeposition.
URL:https://seasevents.nmsdev7.com/event/mse-seminar-probabilistic-digital-twins-for-structure-preserving-simulation-and-scientific-discovery/
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:20240424T180000
DTEND;TZID=America/New_York:20240424T200000
DTSTAMP:20260403T174340
CREATED:20240405T155605Z
LAST-MODIFIED:20240405T155605Z
UID:10007932-1713981600-1713988800@seasevents.nmsdev7.com
SUMMARY:Tech Talks: Bridging Academia and Innovation in Philadelphia's Tech Hub
DESCRIPTION:Join us at the University of Pennsylvania for an event co-organized by the Mack Institute for Innovation Management and the City of Philadelphia Department of Commerce. This event is set to explore and expand collaboration opportunities that are remaking Philadelphia’s tech industry into a diverse and dynamic hub of innovation. Hear from city and commonwealth officials about their take on Philadelphia’s tech ecosystem and how the University of Pennsylvania can help solidify the city’s future as a leader in innovation. We’ll also hear from Penn entrepreneurs about their contribution to the local ecosystem and the benefits of starting their venture in Philadelphia. \nConfirmed Panelists: \n\nTempest Carter\, Director of Strategic Tech Initiatives at the City of Philadelphia\nJohn Swartley\, Chief Innovation Officer\, University of Pennsylvania\nJen Gilburg\, Deputy Secretary for Technology and Entrepreneurship for the Commonwealth of PA\, Department of\nCommunity and Economic Development\, Commonwealth of PA\nSteven Nichtberger\, MD; CEO\, Cabaletta Bio; Adjunct Professor\, Healthcare Management; Senior Fellow\, Vagelos LSM Program\, University of Pennsylvania\n\nModerator: \n\nDr. Valery Yakubovich\, Executive Director\, Mack Institute of Innovation Management\n\nAbout the Organizers:\nDepartment of Commerce for the City of Philadelphia champions the innovation economy\, with the Philadelphia Most Diverse Tech Hub (MDTH) initiative leading the charge in making the city a top\, inclusive tech destination. Launched by the Department in August 2023\, Tech Talks offer a platform to share resources\, discuss innovative ideas\, and foster community connections. \nMack Institute for Innovation Management at the Wharton School is a premier hub for innovation research and practice\, driving forward the integration of academic insights with real-world application. \nREGISTER HERE \n 
URL:https://seasevents.nmsdev7.com/event/tech-talks-bridging-academia-and-innovation-in-philadelphias-tech-hub/
LOCATION:Jon M. Huntsman Hall\, 3730 Walnut Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240424T153000
DTEND;TZID=America/New_York:20240424T163000
DTSTAMP:20260403T174340
CREATED:20240116T183524Z
LAST-MODIFIED:20240116T183524Z
UID:10007814-1713972600-1713976200@seasevents.nmsdev7.com
SUMMARY:John A. Quinn Distinguished Lecture in Chemical Engineering: "Exploring the Physics\, Materials Science\, and Biological Implications of Polyelectrolyte Complexation" (Matthew Tirrell\, University of Chicago)
DESCRIPTION:Abstract\nThe richness of liquid-liquid phase separation behavior in mixtures of oppositely-charged polyelectrolyte has been greatly illuminated recently in the polymer physics literature. Precise determinations of phase diagrams\, measurements of interfacial tension\, scattering measurements of chain configurations\, and increasingly insightful theory are all producing a clearer understanding of these phenomena. In parallel\, physics is also being brought to bear on manifestations of these behaviors in biology. Diverse biological examples related to liquid0liquid phase separation of polyelectrolyte complexes include membraneless organelles\, biological condensates that enhance transcription or protect from stress shock\, and other biological functions. This talk will spell out current understanding of the various contributions to the phase behavior\, including the role of various entropic contributions\, as well as the effects of charge density of the macromolecules. New\nresults on asymmetric mixtures will be presented\, which are more the norm in nature than the perfectly symmetrical mixtures in polymer physics studies.
URL:https://seasevents.nmsdev7.com/event/john-a-quinn-distinguished-lecture-in-chemical-engineering-exploring-the-physics-materials-science-and-biological-implications-of-polyelectrolyte-complexation-matthew-tirrell-university-of-c/
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:20240424T150000
DTEND;TZID=America/New_York:20240424T160000
DTSTAMP:20260403T174340
CREATED:20240408T195558Z
LAST-MODIFIED:20240408T195558Z
UID:10007940-1713970800-1713974400@seasevents.nmsdev7.com
SUMMARY:Spring 2024 GRASP SFI: Harish Ravichandar\, Georgia Institute of Technology\, "New Wine in an Old Bottle: A Structured Approach to Democratize Robot Learning"
DESCRIPTION:This will be a hybrid event with in-person attendance in Levine 307 and virtual attendance on Zoom. \nABSTRACT\nDecades of rigorous research in dynamical systems and control helped us integrate robots into a wide variety of domains\, ranging from factory floors to the moon. Today\, it would appear that deep learning has taken over the torch and will bring robots to our homes\, freeing us all from banal chores. In this utopian vision\, learning-based approaches tend to replace analytical methods. Moving away from handcrafted bespoke solutions to generalist robots that can operate in unstructured environments. But one can instead view learning-based and analytical approaches as two ends of a broad spectrum\, with one end optimizing for reliability (at the cost of human effort) and the other for emergent intelligence (at the cost of data and computation). In this talk\, I will argue why it is better for robots to be in the middle of this broad spectrum. Using manipulation as a case study\, I will discuss how our lab combines ideas from dynamical systems and machine learning to overcome three often-overlooked issues with contemporary methods: i) high barrier to entry due to demands for expensive computational resources and annotated data\, ii) inability to handle new tasks without relying on significant user expertise (e.g.\, for reward or controller design\, hyperparameter tuning\, data collection and curation)\, and iii) unreliable behaviors due to inscrutable and unpredictable learned policies. Addressing these issues will enable robot learning to escape the confines of well-resourced research labs and positively impact the larger society.
URL:https://seasevents.nmsdev7.com/event/spring-2024-grasp-sfi-harish-ravichandar/
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