ITS Berkeley Events

Syndicate content
Upcoming Events
Updated: 15 min 52 sec ago

Explore Urban Air Mobility (UAM) from every angle: Vehicles, Technology, Society, Oct 7-8

15 min 52 sec ago
Sustainable Aviation Symposium 2019 (SAS) asks critical questions about equity in the future of air transit, through a holistic examination of technology, platforms, urbanism and other emerging topics. SAS will explore the ideas that will shape UAM and the global transition to accessible, safe, electric aviation for all. Registration required.

CITRIS Research Exchange - Rama Akkiraju, Oct 9

15 min 52 sec ago
About the Talk:

There is renewed interest among companies these days to implement and deploy AI models in their business processes either to increase automation, or to improve human productivity. AI models are making their way as chat bots in customer support scenarios, as doctors' assistants in hospitals, as legal research assistants in legal domain, as marketing manager assistants in marketing, and as face detection applications in security domain, just to name a few use cases. Making AI work for enterprises requires a whole new and different set of concerns to be addressed than those for traditional software applications or for consumer-facing AI models such as targeted advertising and product recommendations. These new concerns include robustness (R), accuracy and adaptability (A), continuous learning (C), explainability (E), fairness (F), accountability (A), consistency (C) and transparency (T). In addition, building high quality and scalable AI models requires specific kind of discipline, methodology and tools. Data Scientists and practitioners need prescriptive guidance, tools, methods, and best practices on how to procure data, and build, improve and manage their AI models while addressing the concerns mentioned above. In this talk, I will present our best practices for making AI work for enterprises based on our first-hand experience of building scalable AI models for enterprises.

Speaker:

Rama Akkiraju is an IBM Fellow, Master Inventor and IBM Academy Member, and a Director, at IBM’s Watson Division where she leads the AI operations team with a mission to scale AI for Enterprises.
LinkedIn: https://www.linkedin.com/in/ramaakkiraju/

About CITRIS Research Exchange:

Launched in 2008, CITRIS Research Exchange delivers fresh perspectives on information technology and society from distinguished academic, industry, and civic leaders. CITRIS Research Exchange is free and open to the public. Each one-hour seminar starts at 12 pm and is hosted at the Banatao Auditorium in Sutardja Dai Hall on the UC Berkeley campus unless otherwise noted. Register by the Monday prior to the event to receive lunch.

-------

Live broadcast at https://www.youtube.com/user/citrisuc/live

All talks may be viewed on our YouTube channel: https://www.youtube.com/user/citrisuc/playlists

Sign up to receive the latest news and updates from CITRIS: http://bit.ly/SubscribeCITRIS

CITRIS Research Exchange - Yana Feldman, Oct 30

15 min 52 sec ago
"A Multimodal-Deep Learning System for Monitoring Nuclear Proliferation Activities Using Open Sources"


About the Talk:

As the amount of available data increases, the human ability to locate, process, and analyze it is strained and eventually overwhelmed. To address this challenge for nonproliferation analysts, we have been designing a large-scale multimodal retrieval system to help analysts triage and search open source science, technology, transaction, and news data for indicators of nuclear proliferation capabilities and activities. Our system relies on a set of deep neural networks (DNNs) trained to evaluate conceptual similarities across data modalities, e.g. text, image, video. These DNNs can be used to search and prioritize data, according to a nuclear fuel cycle (NFC) process template, that are conceptually closest to the seed query items regardless of data modality. We evaluate the system's ability to retrieve NFC related data that have been purposely hidden in collections of unrelated background data. Quantitative and qualitative results for text-to-image, image-to-image, and image-to-video retrievals are demonstrated.

Speaker:

Yana Feldman, Nonproliferation and International Safeguards Analyst, Lawrence Livermore National Laboratory
LinkedIn: https://www.linkedin.com/in/yana-feldman-44baa99/

About CITRIS Research Exchange:

Launched in 2008, CITRIS Research Exchange delivers fresh perspectives on information technology and society from distinguished academic, industry, and civic leaders. CITRIS Research Exchange is free and open to the public. Each one-hour seminar starts at 12 pm and is hosted at the Banatao Auditorium in Sutardja Dai Hall on the UC Berkeley campus unless otherwise noted. Register by the Monday prior to the event to receive lunch.

Human Mobility and Urban Resilience in America's Cities, Oct 11

15 min 52 sec ago
Northeastern University's Ryan Qi Wang will present Human Mobility and Urban Resilience in America's Cities at 4 p.m. Oct. 11 at the ITS Transportation Seminar in 290 Hearst Memorial Mining Building.

Modeling Human Distraction in the Car Due to Acoustic Annoyances, Oct 18

15 min 52 sec ago
UC Berkeley's Ruzena Bajcsy will present Modeling Human Distraction in the Car Due to Acoustic Annoyances at 4 p.m. Oct. 18 at the ITS Transportation Seminar in 290 Hearst Memorial Mining Building.

Strategic Initiatives for Inland Movement of Containerized Imports at San Pedro Bay, Oct 25

15 min 52 sec ago
UC Berkeley's Rob Leachman will presentStrategic Initiatives for Inland Movement of Containerized Imports at San Pedro Bay at 4 p.m. Oct. 25 at the ITS Transportation Seminar in 290 Hearst Memorial Mining Building.

Learning for Robust Control and Optimization: Efficiency and Safety of Autonomous Transportation Systems, Nov 1

15 min 52 sec ago
University of Connecticut's Fei Mao will present Learning for Robust Control and Optimization: Efficiency and Safety of Autonomous Transportation Systems at 4 p.m. Nov. 1 at the ITS Transportation Seminar in 290 Hearst Memorial Mining Building.

Temporal Instability and the Analysis of Highway Accident Data, Nov 15

15 min 52 sec ago
University of South Florida's Fred Mannering will present Temporal Instability and the Analysis of Highway Accident Data at 4 p.m. Nov. 15 at the ITS Transportation Seminar in 290 Hearst Memorial Mining Building.

Trustworthy Autonomy: Behavior Prediction and Validation, Nov 22

15 min 52 sec ago
University of Illinois' Katherine Driggs-Campbell will present Trustworthy Autonomy: Behavior Prediction and Validation at 4 p.m. Nov. 22 at the ITS Transportation Seminar in 290 Hearst Memorial Mining Building.

Reliably Accurate State Estimation for Connected and Autonomous Highway Vehicles, Sep 27

15 min 52 sec ago
UC Riverside's Jay Farrell will present Reliably Accurate State Estimation for Connected and Autonomous Highway Vehicles on Sept. 27, 2019 at 4 p.m. in 290 Hearst Memorial Mining Building at the ITS Transportation Seminar.

Abstract: Accurate and reliable awareness of world interactions is a key requirement for effective commercial deployment of autonomous and connected vehicles. Awareness arises from onboard sensors and ubiquitous communication between vehicles and infrastructure. Vehicle coordination and safety necessitate reliable “where-in-lane” knowledge of vehicle state. This presentation will address sensor fusion for high-bandwidth vehicle state estimation with a focus on high accuracy and reliability.
Advances is sensing and computation have dramatically altered the focus of related research. For example, computer vision and Global Navigation Satellite Systems each separately provide far more measurements than are necessary for observability. Such environments are signal-rich. The large number of measurements provides both opportunities (e.g., high accuracy) and challenges (e.g., large numbers of outliers). Standard state estimation approaches that decide irrevocably at each time which measurements are valid (e.g. EKF) are not sufficiently reliable at removing the effects of spurious measurements. When that decision is wrong, either measurement information is lost or the state and covariance estimates become corrupted, rendering all subsequent decisions suspect. Either situation can result in divergence of the state estimate, with potentially tragic consequences.
This presentation will consider moving horizon nonlinear state estimation by a novel risk-averse performance-specified (RAPS) approach. Moving horizon methods extract the Bayesian optimal trajectory using all sensor data over a temporal window (e.g. SLAM and RHE). RAPS modifies the optimization problem to select the least risky set of measurements that satisfies a user-defined performance constraint. RAPS is able to evaluate, and reconsider, outlier assumptions for all measurements within the temporal window. The presentation will include experimental results.

Bio:
Jay A. Farrell earned B.S. degrees in physics and electrical engineering from Iowa State University, and M.S. and Ph.D. degrees in electrical engineering from the University of Notre Dame. While in the Autonomous Vehicles Group at Draper Lab, he received the Engineering Vice President's Best Technical Publication Award in 1990, and Recognition Awards for Outstanding Performance and Achievement in 1991 and 1993. He is a Professor in the Department of Electrical and Computer Engineering at the University of California, Riverside. He has served the IEEE Control Systems Society (CSS) on the Board of Governors for two terms, as Vice President Finance and Vice President of Technical Activities, as General Chair of IEEE CDC 2012, and as President in 2014. He has served on the Board of the Electrical and Computer Engineering Department Heads Association, as IEEE Education Activity Board treasurer, as a member of the IEEE Financial Committee, and three terms on the IEEE Fellow Committee. He currently serves as Vice President of the American Automatic Control Council. He was named a GNSS Leader to Watch for 2009-2010 by GPS World Magazine in May 2009 and a winner of the Connected Vehicle Technology Challenge by the U.S. Department of Transportation`s (DOT`s) Research and Innovative Technology Administration in July 2011. He is author of over 250 technical publications and three books, a Distinguished Member of IEEE CSS, a Fellow of AAAS, and a Fellow of the IEEE.

Towards Robust Machine Learning for Transportation Systems, Oct 4

15 min 52 sec ago
Nanyeng Technological University's Justin Dauwels will present Towards Robust Machine Learning for Transportation Systems on Oct. 4, 2019 at 4 p.m. in 290 Hearst Memorial Mining Building at the ITS Transportation Seminar.

Introduction to Crowdsourcing in Research: Overview of Processes and Discussion on Benefits and Concerns, Sep 16

Mon, 2019-09-16 23:32
Crowdsourcing is a method increasingly used in qualitative, quantitative, and mixed-methods research. However, many researchers remain unclear about what this method is, when it may be appropriate to use, and how it could be implemented. Please join Kate Beck, Program Lead at UC Berkeley's Safe Transportation Research and Education Center (SafeTREC), to learn more about this research method.

In addition to providing a brief overview of both the method and the Street Story project for which SafeTREC is currently using crowdsourcing, Kate will help attendees understand potential benefits and discuss common concerns. A significant portion of the meeting will be dedicated to an open discussion so you can ask and learn about the specific topics that interest you the most.

Rethinking America's Highway Institutions, Sep 13

Fri, 2019-09-13 23:32
Reason Foundation's Robert Poole will present Rethinking America's Highway Institutions on Sept. 13, 2019 at 4 p.m. in 290 Hearst Memorial Mining Building at the ITS Transportation Seminar.

Abstract:
In this talk, Robert Poole will suggest that the 20th century institutions that govern how we design, construct, maintain, and fund major highways are broken and in need of major revision. The evidence is the persistence over many decades of serious and worsening problems, including chronic congestion, extensive deferred maintenance, and declining and unpopular funding sources. Drawing on practices from abroad, plus limited U.S. experience with new models, Poole suggests that highways are better conceived as network utilities that can be run as business operations—either by state entities (such as toll agencies) or as investor-owned companies operating under long-term franchises comparable to those of electric utilities. He will suggest as a possible first step toward this new model: toll-financed reconstruction and modernization of the aging Interstate highway system.

Bio:
Robert Poole is Director of Transportation Policy and the Searle Freedom Trust Transportation Fellow at the Reason Foundation. He has advised the U.S. DOT and half a dozen state DOTs on transportation policy. Over the past 20 years, he has helped introduce a number of policy ideas into U.S. transportation, including long-term toll concessions, HOT lanes, and truck-only toll lanes. A Reason policy paper Bob wrote in 1988 directly inspired the first state PPP law, enacted in California in 1989. That law led directly to the 91 Express Lanes—the first all-electronic toll road and the first U.S. long-term toll concession (P3) project.
Bob received his B.S. and M.S. in mechanical engineering at MIT and did graduate work in operations research at NYU. He’s a member of the
Transportation Research Board’s Managed Lanes Committee, and was a
member of TRB’s special committee on the long-term viability of fuel taxes for highway funding. In 2007 he was named “Private Sector Entrepreneur of the Year” by the Public-Private Partnerships division of ARTBA. In 2008 he was a member of the Texas Study Committee on Private Participation in Toll Projects. In 2010 he was a member of Washington State DOT’s Expert Review Panel on the I-405 corridor, and was also a member of the transportation transition team for Florida Gov. Rick Scott.
Bob produces Reason’s monthly e-newsletter, Surface Transportation
Innovations, and writes a monthly column on transportation policy for
Public Works Financing. His book, Rethinking America’s Highways: A 21 st Century Vision for Better Infrastructure, was published by the University of Chicago Press in July 2018.

Pricing Data Science for Uber Eats, Sep 6

Fri, 2019-09-06 23:34
Uber's Feras El Zarwi will present Pricing Data Science for Uber Eats on Sept. 6, 2019 at 4 p.m. in 290 Hearst Memorial Mining Building at the ITS Transportation Seminar.

Abstract
UberEats, the food delivery platform at Uber, is currently a USD $13 billion gross bookings business that is present in hundreds of markets all around the world. At UberEATS, pricing data science focuses on developing pricing models and algorithms for couriers and eaters. Our north star is to have a platform that ensures reliability, efficiency, growth and user engagement. In this talk, I will discuss and present how courier pricing is leveraging on data science methods and techniques to guide the evolution of our products at UberEATS. Specifically, I will focus on three levers that make our platform more efficient and reliable: (1) dispatch incentives; (2) dispatch screen redesign; and (3) experimentation.

Feras El Zarwi is currently a Senior Data Scientist at Uber. He has been at Uber for 2 years and has primarily focused on courier pricing (driver pricing) data science. Feras’s expertise is in behavioral modeling of decision-makers as well as demand forecasting. The techniques he uses entail a mixture of econometric models (specifically discrete choice analysis), machine learning methods, and statistical modeling. Feras received his Masters and PhD in Transportation Engineering from the University of California at Berkeley in 2017. He received his Bachelor’s degree in Civil and Environmental Engineering from the American University of Beirut. In addition to Uber, Feras has worked as a transportation engineering consultant at SETS International in the Middle East region for two years prior to his PhD.

Transportation Engineering Orientation, Aug 26

Mon, 2019-08-26 23:34
ITS Berkeley and the Transportation Library will help host the Transportation Engineering and dual degree TE/Master of City Planning orientation Monday Aug. 26, 2019 in the ITS Library, fourth floor McLaughlin.

TechTransfer Open House, Aug 21

Wed, 2019-08-21 23:37
The Institute of Transportation Studies morale committee and TechTransfer are hosting an open house for ITS and its centers community on Wednesday Aug. 21, 2019 in 240 Bechtel Engineering Building from 2-5 pm. This social gathering will also highlight some of the research and programs that TechTransfer runs, in addition to meeting the team! Light refreshments will be provided.