Select a calendar:
Filter November Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for November
-
CAIS Seminar: Itai Ashlagi (Stanford University) - Designing school choice for Diversity in San Francisco Unified School District
Tue, Nov 02, 2021 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Itai Ashlagi, Stanford University
Talk Title: Designing school choice for Diversity in San Francisco Unified School District
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: In December 2018, the Board of Education of San Francisco Unified School District (SFUSD) passed a resolution for developing a student assignment system for elementary schools, which seeks to improve diversity, transparency, and equal access to quality schools.
This follows an increasing trend towards segregation in the last two decades despite the diversity in the district. In this talk I will describe ongoing research, building on tools from Optimization and Economics, that supported SFUSD towards a new student assignment system to achieve these goals.
This is based on joint work with Max Allman, Irene Lo and Kaleigh Mentzer
Register in advance for this webinar at:
https://usc.zoom.us/webinar/register/WN_Fmg9g80OTcazDrCONyD4YA
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Itai Ashlagi is an Associate Professor at the Stanford University Management Science & Engineering Department. He is interested in market design. His work influenced the practice of kidney exchange, for which he has become a Franz Edelman Laureate.
Host: USC Center for Artificial Intelligence in Society (CAIS)
Webcast: https://usc.zoom.us/webinar/register/WN_Fmg9g80OTcazDrCONyD4YALocation: Online - Zoom Webinar
WebCast Link: https://usc.zoom.us/webinar/register/WN_Fmg9g80OTcazDrCONyD4YA
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Lisa Soros (Cross Labs) - Designing Open-Ended Algorithms via Artificial Life
Tue, Nov 02, 2021 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Lisa Soros, Cross Labs
Talk Title: Designing Open-Ended Algorithms via Artificial Life
Series: Computer Science Colloquium
Abstract: Most algorithms implemented in computers are designed to converge in a finite amount of time. Yet, some of the most powerful generative processes in the natural world (such as evolution) have been running for millions or billions of years. Is it possible to create algorithms that generate interesting and complex artifacts on the same scale as natural evolution? This talk will give an introduction to research on the synthesis and simulation of living systems, also known as Artificial Life. It will focus primarily on the challenge of open-ended evolutionary processes, which may pave the way for open-ended artificial intelligence.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Lisa Soros is a Postdoctoral Research Fellow at Cross Labs, which is a hybrid academic-industrial research institute based in Kyoto, Japan and dedicated to studying natural and artificial intelligence. Her research interests broadly include evolutionary computation, artificial life, and video game AI. She is a graduate of the Evolutionary Complexity Research Group at the University of Central Florida and completed her dissertation, "Necessary Conditions for Open-Ended Evolution" in 2018. Since then, she has been an Assistant Professor at Champlain College in Burlington, Vermont and a Postdoctoral Researcher at the Game Innovation Lab at New York University.
Host: Stefanos Nikolaidis
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Distinguished Lecture: Michael Bronstein (Imperial College London / Twitter) - Geometric Deep Learning: from Euclid to drug design
Tue, Nov 09, 2021 @ 11:00 AM - 12:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Michael Bronstein, Imperial College London / Twitter
Talk Title: Geometric Deep Learning: from Euclid to drug design
Series: Computer Science Distinguished Lecture Series
Abstract: For nearly two millennia, the word "geometry" was synonymous with Euclidean geometry, as no other types of geometry existed. Euclid's monopoly came to an end in the 19th century, where multiple examples of non-Euclidean geometries were shown. However, these studies quickly diverged into disparate fields, with mathematicians debating the relations between different geometries and what defines one. A way out of this pickle was shown by Felix Klein in his Erlangen Programme, which proposed approaching geometry as the study of invariants or symmetries using the language of group theory. In the 20th century, these ideas have been fundamental in developing modern physics, culminating in the Standard Model.
The current state of deep learning somewhat resembles the situation in the field of geometry in the 19h century: On the one hand, in the past decade, deep learning has brought a revolution in data science and made possible many tasks previously thought to be beyond reach -” including computer vision, playing Go, or protein folding. At the same time, we have a zoo of neural network architectures for various kinds of data, but few unifying principles. As in times past, it is difficult to understand the relations between different methods, inevitably resulting in the reinvention and re-branding of the same concepts.
Geometric Deep Learning aims to bring geometric unification to deep learning in the spirit of the Erlangen Programme. Such an endeavour serves a dual purpose: it provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers, and gives a constructive procedure to incorporate prior knowledge into neural networks and build future architectures in a principled way.
In this talk, I will overview the mathematical principles underlying Geometric Deep Learning on grids, graphs, and manifolds, and show some of the exciting and groundbreaking applications of these methods in the domains of computer vision, social science, biology, and drug design.
(based on joint work with J. Bruna, T. Cohen, P. VeliÄkoviÄ)
Register in advance for this webinar at:
https://usc.zoom.us/meeting/register/tJAodeitqTwjHNLVLccoIBCb3Ngtx0rHF1TR
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Michael Bronstein is a professor at Imperial College London, where he holds the Chair in Machine Learning and Pattern Recognition, and Head of Graph Learning Research at Twitter. Michael received his PhD from the Technion in 2007. He has held visiting appointments at Stanford, MIT, and Harvard, and has also been affiliated with three Institutes for Advanced Study (at TUM as a Rudolf Diesel Fellow (2017-2019), at Harvard as a Radcliffe fellow (2017-2018), and at Princeton as a short-time scholar (2020)). Michael is the recipient of the Royal Society Wolfson Research Merit Award, Royal Academy of Engineering Silver Medal, five ERC grants, two Google Faculty Research Awards, and two Amazon AWS ML Research Awards. He is a Member of the Academia Europaea, Fellow of IEEE, IAPR, BCS, and ELLIS, ACM Distinguished Speaker, and World Economic Forum Young Scientist. In addition to his academic career, Michael is a serial entrepreneur and founder of multiple startup companies, including Novafora, Invision (acquired by Intel in 2012), Videocites, and Fabula AI (acquired by Twitter in 2019).
Host: Mukund Raghothaman
Webcast: https://usc.zoom.us/meeting/register/tJAodeitqTwjHNLVLccoIBCb3Ngtx0rHF1TRLocation: Online - Zoom Webinar
WebCast Link: https://usc.zoom.us/meeting/register/tJAodeitqTwjHNLVLccoIBCb3Ngtx0rHF1TR
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Jerry Mendel (USC) - Explainable Ai (XAI) for Rule-Based Fuzzy Systems
Thu, Nov 11, 2021 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Jerry Mendel, Emeritus Professor of Electrical Engineering, University of Southern California
Talk Title: Explainable Ai (XAI) for Rule-Based Fuzzy Systems
Series: Computer Science Colloquium
Abstract: There is a sentiment in the fuzzy community that fuzzy rules would be of great value in XAI because such rules use words (which are modeled as fuzzy sets) and so they lend themselves naturally to XAI. This talk challenges that sentiment, in a constructive way. It explains why it is not valid to explain the output of Mamdani or TSK fuzzy systems using IF-THEN rules, but that it is valid to explain the output of such fuzzy systems as an association of the antecedents of a small subset of the original larger set of rules, using a phrase such as "These linguistic antecedents are symptomatic of this output". It also describes a novel multi-step approach to obtain such a small subset of rules for fuzzy systems, how Linguistic Approximation can be used to express the antecedent membership functions (the symptoms) linguistically, and a method for estimating the quality of linguistic explanations.
Register in advance for this webinar at:
https://usc.zoom.us/webinar/register/WN_IgXrJer8SMOaS5VdwMdRFQ
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Jerry Mendel received the Ph.D. degree in electrical engineering from the Polytechnic Institute of Brooklyn, Brooklyn, NY. Currently, he is (since Jan. 2018) Emeritus Professor of Electrical Engineering at the University of Southern California in Los Angeles. He has published close to 600 technical papers and is author and/or co-author of 12 books. He is a Life Fellow of the IEEE, a Distinguished Member of the IEEE Control Systems Society, and a Fellow of the International Fuzzy Systems Association. He was President of the IEEE Control Systems Society in 1986, a member of the Administrative Committee of the IEEE Computational Intelligence Society for nine years, and Chairman of its Fuzzy Systems Technical Committee and the Computing With Words Task Force of that Technical Committee. Among his awards are four IEEE Transactions best paper awards, a 1984 IEEE Centennial Medal, an IEEE Third Millenium Medal, and a Fuzzy Systems Pioneer Award from the IEEE Computational Intelligence Society. According to Google Scholar (as of Sept. 9, 2021) he has 58,428 citations, an h-index of 97 and an i10-index of 310. His present research interests include: type-2 fuzzy logic systems and XAI for rule-based systems.
Host: Mukund Raghothaman
Webcast: https://usc.zoom.us/webinar/register/WN_IgXrJer8SMOaS5VdwMdRFQLocation: Online Zoom Webinar
WebCast Link: https://usc.zoom.us/webinar/register/WN_IgXrJer8SMOaS5VdwMdRFQ
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CAIS Seminar: Erika Van Buren (First Place for Youth) - Leveraging Data Science to Individualize Extended Foster Care Services: the Youth Success Roadmap Tool
Tue, Nov 16, 2021 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Erika Van Buren, First Place for Youth
Talk Title: Leveraging Data Science to Individualize Extended Foster Care Services: the Youth Success Roadmap Tool
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: In service to a deep commitment to learning and impact, First Place for Youth -“ a service and advocacy organization dedicated to supporting transition age foster youth to achieve self-sufficiency and independence -“ leveraged several years of in-program administrative and follow-up data on youth served to conduct a precision analytics modeling process, and to develop The Youth Success Roadmap Tool (YRT). The YRT is a practitioner-centric, web-based decision-support tool that is used by direct service providers and managers to support high precision programming in the development of action plans, selection of interventions, and decisions about transition needs and timelines with individual youth, with the ultimate goal of helping all young people leave program with life sustaining, living wage employment. This seminar will discuss the findings from the original modeling, the methods utilized to generate the modeling and tool, showcase and describe how the YRT is currently being utilized to increase application of effective, individualized services and the achievement of equitable results with youth.
Register in advance for this webinar at:
https://usc.zoom.us/webinar/register/WN_sDAlPRaaSBCWQvZct9ZuyQ
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Dr. Erika Van Buren serves as the Chief Innovation Officer for First Place for Youth, where she leads evaluation, learning, and national expansion strategies for scaling First Place's influence and impact in service to older foster youth across the country. She crafts and implements the internal and external evaluation agenda for the agency, works closely with program leadership to innovate and roll-out best and evidence-supported strategies to improve practice, and conducts on-going sector building and system-capacity development activities in support of First Place's mission. With over 20 years of experience, she has cultivated expertise in the areas of community mental health and child welfare program development and evaluation, quality improvement and performance management practices and was most recently named as a member of the 11th class of Annie E. Casey Foundation Leadership Fellows.
Host: USC Center for Artificial Intelligence in Society (CAIS)
Webcast: https://usc.zoom.us/webinar/register/WN_sDAlPRaaSBCWQvZct9ZuyQLocation: Online Zoom Webinar
WebCast Link: https://usc.zoom.us/webinar/register/WN_sDAlPRaaSBCWQvZct9ZuyQ
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Laurel Riek (University of California, San Diego) - Robots in clinic and in the community: supporting wellbeing and health equity
Tue, Nov 16, 2021 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Laurel Riek, University of California, San Diego
Talk Title: Robots in clinic and in the community: supporting wellbeing and health equity
Series: Computer Science Colloquium
Abstract: The pandemic exacerbated inequities faced by people with disabilities and healthcare workers -” both are at high risk of adverse physical and mental health outcomes. Robots alone are not going to fix these major societal problems; however, our work explores how we can design technology to lessen the burden of systemic ableism and healthcare system stress. I will discuss several of our recent projects in acute care and community health contexts. In acute care, we are building hospital-based robots to support the clinical workforce, to support item delivery, telemedicine, and decision support. In community health, we are creating interactive and adaptive systems that aim to extend the reach of cognitive neurorehabilitative therapies, provide respite to overburdened caregivers, and explore how technology might serve as a means for mediating positive interactions during hardship. We focus on building robots that can adaptively team with and longitudinally learn from people, and personalize and tailor their behavior.
Register in advance for this webinar at:
https://usc.zoom.us/webinar/register/WN_BxKfSOStS--ZoudxSavY7w
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Dr. Laurel Riek is a professor in Computer Science and Engineering at the University of California, San Diego, with a joint appointments in the Department of Emergency Medicine, and affiliated with the Contextual Robotics Institute and Design Lab. Dr. Riek directs the Healthcare Robotics Lab and leads research in human-robot teaming and health informatics, with a focus on autonomous robots that work proximately with people. Riek's current research interests include long term learning, robot perception, and personalization; with applications in acute care, neurorehabilitation, and home health. Dr. Riek received a Ph.D. in Computer Science from the University of Cambridge, and B.S. in Logic and Computation from Carnegie Mellon. Riek served as a Senior Artificial Intelligence Engineer and Roboticist at The MITRE Corporation from 2000-2008, working on learning and vision systems for robots, and held the Clare Boothe Luce chair in Computer Science and Engineering at the University of Notre Dame from 2011-2016. Dr. Riek has received the NSF CAREER Award, AFOSR Young Investigator Award, Qualcomm Research Award, and was named one of ASEE's 20 Faculty Under 40. Dr. Riek is the HRI 2023 General Co-Chair and served as the Program Co-Chair for HRI 2020, and serves on the editorial boards of T-RO and THRI.
Host: Stefanos Nikolaidis
Webcast: https://usc.zoom.us/webinar/register/WN_BxKfSOStS--ZoudxSavY7wLocation: Online - Zoom Webinar
WebCast Link: https://usc.zoom.us/webinar/register/WN_BxKfSOStS--ZoudxSavY7w
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
Jian Pei (Simon Fraser University) - Exact, Concise, and Consistent Data Driven Interpretation
Tue, Nov 16, 2021 @ 03:30 PM - 04:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Jian Pei, Simon Fraser University
Talk Title: Exact, Concise, and Consistent Data Driven Interpretation
Abstract: Interpretability and explainability are at the core in our pursuit of new knowledge. At the same time, interpretation in data analytics and data mining is challenging in many ways, such as the complexity of models to be interpreted, the difficulty in knowledge elicitation, the expectation of embodying interpretation, and the need of many kinds of knowledge. In this talk, I will present our systematic research on exact, concise, and consistent data driven interpretation for database and data mining tasks. I will illustrate our principles and techniques using various application examples, including skyline queries (aka pareto optima) in databases, semantic OLAP in business intelligence, piece-wise linear neural networks in classification, and KS-tests in statistics. I will also discuss the promises and challenges of data driven interpretation for future work.
Biography: Jian Pei is a Professor in the School of Computing Science at Simon Fraser University. His research focuses on data science, big data, data mining, database systems, and information retrieval. His expertise is in developing effective and efficient data analysis techniques for novel data intensive applications, and transferring his research results to industry products and business practice. He is recognized as a Fellow of the Royal Society of Canada (Canada's national academy), the Canadian Academy of Engineering, ACM, and IEEE. Since 2000, he has published one textbook, two monographs and over 300 research papers in refereed journals and conferences, which have been cited extensively by others. He was the editor-in-chief of the IEEE Transactions of Knowledge and Data Engineering (TKDE) in 2013-16, the chair of ACM SIGKDD in 2017-2021. He received a few prestigious awards, including the 2017 ACM SIGKDD Innovation Award, the 2015 ACM SIGKDD Service Award, the 2014 IEEE ICDM Research Contributions Award, the British Columbia Innovation Council 2005 Young Innovator Award, an IBM Faculty Award, a KDD Best Application Paper Award, and an ICDE Influential Paper Award.
Host: Ellis Horowitz
Location: Ronald Tutor Hall of Engineering (RTH) - 105
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Jian Pei (Simon Fraser University) - Defining One Unified CS through Many Diversified Paths
Wed, Nov 17, 2021 @ 09:00 AM - 09:45 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Jian Pei, Simon Fraser University
Talk Title: Defining One Unified CS through Many Diversified Paths
Abstract: Computer science broadly construed becomes a new dimension disruptive in higher education and research. Computer science departments face grand opportunities and challenges. Most importantly, a responsible computer science department should obligatorily take the lead to establish a university-wise unified computer science identity, including strategies, workforces, culture, and impact, and leverage and extend the rich leadership, advantages, and resources of the university. We need to ensure that the unified CS identity best contributes to building an academic learning and research environment of inclusiveness, diversity, and equity. Defining one unified CS as a new dimension in educational programs and research initiatives has to embrace many diversified paths and inclusively collaborate with many units and resources on campus and beyond. In this talk, I will share my ideas about the strategies, organization, student experience, outreach, community building, recruitment and retention, and working plan to evolve from an established leading CS department today into a powerful engine of new CS era tomorrow.
Biography: Jian Pei is a Professor in the School of Computing Science at Simon Fraser University. His research focuses on data science, big data, data mining, database systems, and information retrieval. His expertise is in developing effective and efficient data analysis techniques for novel data intensive applications, and transferring his research results to industry products and business practice. He is recognized as a Fellow of the Royal Society of Canada (Canada's national academy), the Canadian Academy of Engineering, ACM, and IEEE. Since 2000, he has published one textbook, two monographs and over 300 research papers in refereed journals and conferences, which have been cited extensively by others. He was the editor-in-chief of the IEEE Transactions of Knowledge and Data Engineering (TKDE) in 2013-16, the chair of ACM SIGKDD in 2017-2021. He received a few prestigious awards, including the 2017 ACM SIGKDD Innovation Award, the 2015 ACM SIGKDD Service Award, the 2014 IEEE ICDM Research Contributions Award, the British Columbia Innovation Council 2005 Young Innovator Award, an IBM Faculty Award, a KDD Best Application Paper Award, and an ICDE Influential Paper Award.
Host: Ellis Horowitz
Location: Ronald Tutor Hall of Engineering (RTH) - 105
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Luis Garcia (USC ISI) - Use What You Know: Leveraging Semantics to Trust Learning-enabled Cyber-physical Systems
Thu, Nov 18, 2021 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Luis Garcia, USC
Talk Title: Use What You Know: Leveraging Semantics to Trust Learning-enabled Cyber-physical Systems
Abstract: The integration of autonomous cyber-physical systems (CPS) in society that interface with humans necessitates assurances for safety, security, and privacy. Traditional CPS research thrusts in this space have typically focused on closed-loop, deterministic models with relatively low-dimensional physics. With the artificial intelligence renaissance, deep learning models have enabled the utility of large amounts of data stemming from heterogeneous, distributed, and cyber-physical Internet-of-Things (IoT) networks. We are witnessing the emergence of performant cyber-physical systems whose interactions are poorly understood and rapidly evolving despite widespread adoption. My recent research explores how a semantic understanding of a deep learning model's environment can be leveraged to not only provide guarantees but also to enhance the reasoning power of a deep learning model. Neural-symbolic approaches that combine human logic with deep learning lie at the frontier of human-machine teaming in distributed and heterogenous IoT environments. My research aims to answer the following questions: 1) How can we design neural-symbolic frameworks that are semantically conscious of their subsuming cyber-physical systems? 2) In distributed and heterogeneous IoT environments enabled with such neural-symbolic frameworks, what are the correct programming abstractions that need to be exposed to developers? 3) How can we defend against collateral safety, security, and privacy threats that will subsequently be exposed by semantically aware, sensor-rich, adaptive, and distributed heterogeneous IoT environments? This talk will provide an overview of my research with an emphasis on the latter question of safety, security, and privacy threats in this space.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Join Zoom Meeting
https://usc.zoom.us/j/99126118128?pwd=YytHUzJzSWxObVdpOFphdG9KVDVvZz09
Meeting ID: 991 2611 8128
Biography: Luis Garcia joined USC ISI's Networking and Cybersecurity Division as a Research Computer Scientists in June 2020. He was previously a Postdoctoral Scholar in the Networked and Embedded Systems Laboratory (NESL) in the University of California, Los Angeles (UCLA) Electrical and Computer Engineering Department since 2018. His research interests include the safety and security of learning-enabled cyber-physical systems, malware analysis and reverse engineering, industrial control system security and verification, as well as broad interests in novel applications of machine learning. He obtained his Ph.D. in Computer Engineering with a Cyber Security track working on the safety and security of cyber-physical industrial control systems at Rutgers University in 2018.
Host: Greg Ver Steeg
Audiences: Everyone Is Invited
Contact: Cherie Carter
-
CS Colloquium: Tapomayukh Bhattacharjee (Cornell University) - Leveraging Physical Interactions to Enable Robotic Assistive Care
Tue, Nov 23, 2021 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Tapomayukh Bhattacharjee, Cornell University
Talk Title: Leveraging Physical Interactions to Enable Robotic Assistive Care
Series: Computer Science Colloquium
Abstract: How do we build robots that can assist people with mobility limitations with activities of daily living? To successfully perform these activities, a robot needs to be able to physically interact with humans and objects in unstructured human environments. In the first part of my talk, I will show how a robot can use multimodal sense of touch such as force and thermal sensing to infer properties of these physical interactions using data-driven methods and physics-based models. In the second part of the talk, I will show how a robot can leverage these properties to perform one such activity of daily living- feeding. Successful robot-assisted feeding depends on reliable bite acquisition of hard-to-model deformable food items and easy bite transfer. Using insights from human studies, I will showcase algorithms and technologies that leverage multiple sensing modalities to perceive varied food item properties and determine successful strategies for bite acquisition and transfer. Using feedback from all the stakeholders, I will show how we built an autonomous robot-assisted feeding system that uses these algorithms and technologies and deployed it in the real world that fed real users with mobility limitations.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Tapomayukh "Tapo" Bhattacharjee is an Assistant Professor in the Department of Computer Science at Cornell University where he directs the EmPRISE Lab (https://emprise.cs.cornell.edu/). He completed his Ph. D. in Robotics from Georgia Institute of Technology and was an NIH Ruth L. Kirschstein NRSA postdoctoral research associate in Computer Science & Engineering at the University of Washington. He wants to enable robots to assist people with mobility limitations with tasks for daily living and he believes that allowing efficient and safe physical interactions between robots and their immediate environments is the key. His work spans the fields of human-robot interaction, haptic perception, and robot manipulation.
Host: Stefanos Nikolaidis
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Konstantinos Karydis (University of California, Riverside) - Online mobile robot motion planning under uncertainty in unknown environments
Tue, Nov 30, 2021 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Konstantinos Karydis, University of California, Riverside
Talk Title: Online mobile robot motion planning under uncertainty in unknown environments
Series: Computer Science Colloquium
Abstract: Mobile robot motion planning under uncertainty is a challenging yet rewarding foundational robotics research problem with extensive applications across domains including intelligence, surveillance and reconnaissance (ISR), remote sensing, and precision agriculture. One important challenge is operation in unknown environments where planning decisions need to be made at run-time. In this talk we discuss recent results to address online motion planning in unknown environments. We consider two specific cases: 1) How to achieve resolution-complete field coverage considering the non-holonomic mobility constraints in commonly-used vehicles (e.g., wheeled robots) without prior information about the environment? 2) How to develop resilient, risk-aware and collision-inclusive planning algorithms to enable (collision-resilient) mobile robots to deliberately choose when to collide with locally-sensed obstacles to improve some motion planning metrics (e.g., total time to reach a goal).
To this end, we have proposed a hierarchical, hex-decomposition-based coverage planning algorithm for unknown, obstacle-cluttered environments. The proposed approach ensures resolution-complete coverage, can be tuned to achieve fast exploration, and plans smooth paths for Dubins vehicles to follow at constant velocity in real-time. Our approach can successfully trade-off between coverage and exploration speed, and can outperform existing online coverage algorithms in terms of total covered area or exploration speed according to how it is tuned. Further, we have introduced new sampling- and search-based online collision-inclusive motion planning algorithms for impact-resilient robots, that can explicitly handle the risk of colliding with the environment and can switch between collision avoidance and collision exploitation. Central to the planners' capabilities is a novel joint optimization function that evaluates the effect of possible collisions using a reflection model.
This way, the planner can make deliberate decisions to collide with the environment if such collision is expected to help the robot make progress toward its goal. To make the algorithm online, we present state expansion pruning techniques that can significantly reduce the search space while ensuring completeness.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Dr. Karydis is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of California, Riverside (UCR). Before joining UCR, he worked as a Post-Doctoral Researcher in Robotics in GRASP Lab, which is part of the Department of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania (Penn). His work was supported by Dr. Vijay Kumar, Professor and Nemirovsky Family Dean of Penn Engineering. He completed his doctoral studies in the Department of Mechanical Engineering at the University of Delaware, under the guidance of Prof. Herbert Tanner and Prof.
Ioannis Poulakakis.
Host: Stefanos Nikolaidis
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
