Logo: University of Southern California

Events Calendar



Select a calendar:



Filter August Events by Event Type:



University Calendar
Events for August

  • PHD Defense - Weiwei Duan

    Fri, Aug 04, 2023 @ 01:00 PM - 02:30 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Dissertation Title:
    Efficient and Accurate Object Extraction from Scanned Maps by Leveraging External Data and Learning Representative Context

    Venue: Zoom meeting link: https://usc.zoom.us/j/2332986718

    Time: 1 pm - 2:30 pm (PT), August 4th

    Abstract:
    Scanned historical maps contain valuable information about environmental changes and human development over time. For instance, comparing historical waterline locations can reveal patterns of climate change. Extracting geographic objects in map images involves two main steps: 1. obtaining a substantial amount of labeled data to train extraction models, and 2. training extraction models to extract desired geographic objects. However, the extraction process has two difficulties. One difficulty is generating a large amount of labeled data with minimal human effort, as manual labeling is expensive and time-consuming. The other difficulty is ensuring that the extraction model learns representative and sufficient knowledge for the accurate extraction of geographic objects. The success of subsequent analyses, like calculating the shortest paths after extracting railroads, heavily depends on the accuracy of the extractions.

    To generate labeled data with minimal human efforts, this thesis presents semi- and fully automatic approaches to generate labeled desired geographic objects by leveraging external data. The semi-automatic approach requires one or a few manually labeled desired objects to collect all desired objects from candidates provided by the external data. In contrast, existing methods require more than a few manually labeled desired objects to achieve the same goal. On the other hand, the proposed automatic approach aims to label the desired objects in close proximity to external data. Using the location and shape information fully from the external data, the proposed automatic approach can accurately label the desired objects on the maps. On the contrary, existing methods that do not utilize shape information may lead to false labels. The novel approaches introduced in this thesis significantly reduce the need for manual labeling while ensuring accurate results.

    Extracting accurate geographic objects is the other difficulty due to the ambiguous appearances of objects and the overlapping objects in maps. The extraction model presented in this thesis captures cartographic symbols to differentiate desired objects from other objects with similar appearances. When the desired objects overlap with other objects on maps, the extracted results could be broken. The proposed extraction model captures sufficient spatial context to reduce broken extraction. For example, the proposed extractor learns the long and continuous structure of linear objects to reduce the gaps in the extracted lines. On the contrary, existing extractors lack the ability to learn sufficient spatial context, resulting in the broken extraction of linear objects. In summary, the proposed extractor learns representative cartographic symbols and sufficient spatial context to accurately extract desired objects.

    The results of the experiment demonstrate the superiority of both the labeling and extraction approaches compared to the existing methods. Accurately labeled data generated by the proposed methods significantly improve the quality of training data for extraction models. The extraction results from the proposed extractor have much less false extraction and better continuity than state-of-the-art baselines. The combination of precise labeling and accurate extraction allows us to extract geographic objects in scanned historical maps. Therefore, we can analyze and interpret historical map data effectively.

    Committee: Craig A. Knoblock Chair), Yao-Yi Chinag, Ram Nevatia, and John Wilson

    Location: https://usc.zoom.us/j/2332986718

    Audiences: Everyone Is Invited

    Contact: Asiroh Cham

    Event Link: https://usc.zoom.us/j/2332986718

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Defense - Aaron Ferber

    Fri, Aug 11, 2023 @ 09:30 AM - 11:30 AM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Defense - Aaron Ferber

    Committee Members: Bistra Dilkina (Chair), Yan Liu, and Phebe Vayanos

    Title: Artificial Decision Intelligence: Integrating Deep Learning and Combinatorial Optimization

    Abstract: Artificial Intelligence (AI) has the potential to impact many facets of our society largely due to its ability to quickly make high quality data driven decisions at scale. We consider Artificial Decision Intelligence (ADI) to be a paradigm for building artificial intelligence methods geared explicitly toward automatic decision making. In the rapidly evolving paradigms of machine learning (ML) and combinatorial optimization (CO), remarkable progress has been made in different directions, revolutionizing how we synthesize insights from data as well as how to best act on those insights. Machine learning, specifically deep learning, with its ability to learn intricate patterns from seemingly unstructured data, has seen profound success across diverse applications. Simultaneously, combinatorial optimization has made significant strides, efficiently performing industrial scale decision-making by searching for optimal solutions from combinatorially large and highly structured search spaces. This thesis explores different perspectives on the tight integration of these two paradigms: machine learning and combinatorial optimization, developing new tools that demonstrate the strengths of both approaches for solving complex tasks. Taking different perspectives on machine learning, combinatorial optimization, and how they can be combined in a cohesive and complementary manner, we propose new methodologies that enable end to end data driven decision making, deep predictive models that respect combinatorial constraints, methods that solve complex problems by learning to formulate simpler surrogate optimization problems, and optimization algorithms that learn from historical data to improve solver performance. The proposed methodologies contribute to the advancement of our capability in handling new and complex real world problems. Specifically, we demonstrate the impact of our methodologies in several domains, such as identifying wildlife trafficking routes, designing photonic devices, large scale recommendation systems, financial portfolio optimization, generating game levels, and smart energy grid scheduling. Thus, this thesis serves as a step forward in artificial decision intelligence by solving complex tasks and providing decision support tools that leverage machine learning and combinatorial optimization.

    Location: Henry Salvatori Computer Science Center (SAL) - 213

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/my/aaron.ferber

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • Repeating EventSix Sigma Green Belt for Process Improvement

    Tue, Aug 15, 2023 @ 09:00 AM - 05:00 PM

    Executive Education

    University Calendar


    USC Viterbi School of Engineering's Six Sigma Green Belt for Process Improvement, offered in partnership with the Institute of Industrial and Systems Engineers, allows professionals to learn how to integrate principles of business, statistics, and engineering to achieve tangible results.

    Master the use of Six Sigma to quantify the critical quality issues in your company. Once the issues have been quantified, statistics can be applied to provide probabilities of success and failure. Six Sigma methods increase productivity and enhance quality. As a USC Six Sigma Green Belt, you will be equipped to support and champion a Six Sigma implementation in your organization.

    To earn the USC Six Sigma Green Belt Certificate, you will be required to pass the Institute of Industrial and Systems Engineer's green belt exam.

    Location: Olin Hall of Engineering (OHE) -

    Audiences: Registered Participants

    View All Dates

    Contact: Karen Escobar

    Event Link: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Defense - Basileal Yoseph Imana

    Tue, Aug 15, 2023 @ 11:00 AM - 01:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Defense - Basileal Yoseph Imana

    Committee Members: John Heidemann (Chair), Aleksandra Korolova, Bistra Dilkina, Phebe Vayanos

    Title: Platform Supported And Privacy Preserving Auditing of Social Media Algorithms For Public Interest

    Abstract:
    Social media platforms are entering a new era of increasing scrutiny by public interest groups and regulators. One reason for the increased scrutiny is platform induced bias in how they deliver ads for life opportunities with legal protections against discrimination. Platforms use relevance estimator algorithms to optimize the delivery of ads. Such algorithms are proprietary and therefore opaque to outside evaluation, and early evidence suggests these algorithms may be biased or discriminatory. In response to such risks, the U.S. and the E.U. have proposed policies to allow researchers to audit platforms while protecting users privacy and platforms proprietary information. Currently, no technical solution exists for implementing such audits with rigorous privacy protections and without putting significant constraints on researchers. In this work, our thesis is that relevance estimator algorithms bias the delivery of opportunity ads, but new auditing methods can detect that bias while preserving privacy.

    We support our thesis statement through three studies. In the first study, we propose a black box method for measuring gender bias in the delivery of job ads with a novel control for differences in job qualification, as well as other confounding factors that influence ad delivery. Controlling for qualification is necessary since qualification is a legally acceptable factor to target ads with, and we must separate it from bias introduced by platforms algorithms. We apply our method to Meta and LinkedIn, and demonstrate that Metas relevance estimators result in discriminatory delivery of job ads by gender. In our second study, we design a black box methodology that is the first to propose a means to draw out potential racial bias in the delivery of education ads. Our method employs a pair of ads that are seemingly identical education opportunities but one is of inferior quality tied with a historical societal disparity that ad delivery algorithms may propagate. We also develop a method for auditing ad delivery using inferred race that handles uncertainty in inference. Using inferred race is useful to address the lack of access to race attributes that is a growing challenge for auditing racial bias in ad delivery. We evaluate Metas delivery of education ads with both known and inferred race. When race is known, we demonstrate Metas relevance estimators racially bias the delivery of education ads. We then show, when race is inferred, inference error makes the test for bias in ad delivery less sensitive to small amounts of bias. Going beyond the domain specific and black box methods we used in our first two studies, our final study proposes a novel platform supported framework to allow researchers to audit relevance estimators that is generalizable to studying various categories of ads, demographic attributes and target platforms. The framework allows auditors to get privileged query access to platforms relevance estimators to audit for bias in the algorithms while preserving the privacy interests of users and platforms. Overall, our first two studies show relevance estimator algorithms bias the delivery of job and education ads, and thus motivate making these algorithms the target of platform supported auditing in our third study. Our work demonstrates a platform supported means to audit these algorithms is the key to increasing public oversight over ad platforms while rigorously protecting privacy

    Location: Henry Salvatori Computer Science Center (SAL) - 213

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/93768511444?pwd=dDZTVjdyM0trSE1Qc2dqQ2hMcWNxUT09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • Repeating EventSix Sigma Green Belt for Process Improvement

    Wed, Aug 16, 2023 @ 09:00 AM - 05:00 PM

    Executive Education

    University Calendar


    USC Viterbi School of Engineering's Six Sigma Green Belt for Process Improvement, offered in partnership with the Institute of Industrial and Systems Engineers, allows professionals to learn how to integrate principles of business, statistics, and engineering to achieve tangible results.

    Master the use of Six Sigma to quantify the critical quality issues in your company. Once the issues have been quantified, statistics can be applied to provide probabilities of success and failure. Six Sigma methods increase productivity and enhance quality. As a USC Six Sigma Green Belt, you will be equipped to support and champion a Six Sigma implementation in your organization.

    To earn the USC Six Sigma Green Belt Certificate, you will be required to pass the Institute of Industrial and Systems Engineer's green belt exam.

    Location: Olin Hall of Engineering (OHE) -

    Audiences: Registered Participants

    View All Dates

    Contact: Karen Escobar

    Event Link: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Defense - Guillermo Baltra

    Wed, Aug 16, 2023 @ 09:00 AM - 11:00 AM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Defense - Guillermo Baltra

    Committee Members: John Heidemann (Chair), Ramesh Govindan, Antonio Ortega


    Title: Improving network reliability using a formal definition of the Internet core

    Abstract: After 50 years, the Internet is still defined as a collection of interconnected networks. Yet seamless, universal connectivity is challenged in several ways. Political pressure threatens fragmentation due to de peering, architectural changes such as carrier grade NAT, the cloud makes connectivity indirect, firewalls impede connectivity, and operational problems and commercial disputes all challenge the idea of a single set of interconnected networks. We propose that a new, conceptual definition of the Internet core helps disambiguate questions in analysis of network reliability and address space usage.
    We prove this statement through three studies. First, we improve coverage of outage detection by dealing with sparse sections of the Internet, increasing from a nominal 67 percent responsive 24 blocks coverage to 96 percent of the responsive Internet. Second, we provide a new definition of the Internet core, and use it to resolve partial reachability ambiguities. We show that the Internet today has peninsulas of persistent, partial connectivity, and that some outages cause islands where the Internet at the site is up, but partitioned from the main Internet. Finally, we use our definition to identify ISP trends, with applications to policy and improving outage detection accuracy. We show how these studies together thoroughly prove our thesis statement. We provide a new conceptual definition of the Internet core in our second study about partial reachability. We use our definition in our first and second studies to disambiguate questions about network reliability and in our third study, to ISP address space usage dynamics.

    Location: Charles Lee Powell Hall (PHE) - 325

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/93940091161?pwd=S0tzNms2OW5EWTgzWFhtd3lSUlNudz09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Proposal - Nicolaas Weideman

    Wed, Aug 16, 2023 @ 10:00 AM - 11:30 AM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Proposal - Nicolaas Weideman

    Committee Members: Jelena Mirkovic (chair), Christophe Hauser, William Halfond, Mukund Raghothaman, Srivatsan Ravi, Peter Beerel

    Title: Improving the Security of Modern Software Systems through Binary Program Analysis with Semantic Understanding, Automated Vulnerability Discovery and Non-disruptive Patching


    Abstract: With the ever increasing reliance of the modern world on software systems, the frequency and impact of cyberattacks have greatly increased as well. Software must be analyzed thoroughly to evaluate its security, as vulnerabilities in software can have devastating consequences such as compromised privacy of users, shutdown of infrastructure and significant business losses, and even pose threat to human life. In this thesis we introduce our contributions toward addressing the challenges existing in software security evaluation. It is widely accepted that when evaluating the security of software, analyzing the source code is insufficient. We leverage and extend the field of binary program analysis in three key domains crucial for software security. These domains are semantic understanding, automated vulnerability discovery and nondisruptive patching. Jointly our contributions improve the field of binary program analysis in a threefold manner. We enable analysts to gain a deeper understanding of the program under analysis through extracting high level semantics. We design and implement a new approach for automated and precise vulnerability discovery. We automate vulnerability patching to secure software. Each of these directions independently pushes the boundaries of what is possible in defending modern software, leading to a more secure digital environment

    Location: Henry Salvatori Computer Science Center (SAL) - 322

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/91332871311?pwd=TmhuUyttWEJqMWQ5NTd1cGlpZVk1QT09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • Repeating EventSix Sigma Green Belt for Process Improvement

    Thu, Aug 17, 2023 @ 09:00 AM - 05:00 PM

    Executive Education

    University Calendar


    USC Viterbi School of Engineering's Six Sigma Green Belt for Process Improvement, offered in partnership with the Institute of Industrial and Systems Engineers, allows professionals to learn how to integrate principles of business, statistics, and engineering to achieve tangible results.

    Master the use of Six Sigma to quantify the critical quality issues in your company. Once the issues have been quantified, statistics can be applied to provide probabilities of success and failure. Six Sigma methods increase productivity and enhance quality. As a USC Six Sigma Green Belt, you will be equipped to support and champion a Six Sigma implementation in your organization.

    To earn the USC Six Sigma Green Belt Certificate, you will be required to pass the Institute of Industrial and Systems Engineer's green belt exam.

    Location: Olin Hall of Engineering (OHE) -

    Audiences: Registered Participants

    View All Dates

    Contact: Karen Escobar

    Event Link: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Defense - Zunchen Huang

    Mon, Aug 21, 2023 @ 02:00 PM - 04:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Defense - Zunchen Huang

    Committee Members: Chao Wang (chair), Srivatsan Ravi, and Pierluigi Nuzzo

    Title: Constraint Based Analysis for Persistent Memory Programs

    Abstract: Emerging persistent memory technologies are beginning to bridge the gap between volatile memory and nonvolatile storage in computer systems, by allowing high speed memory access, byte addressability, and persistency at the same time. However, PM programming remains a challenging and error prone task due to reliance on ordinary developers to write correct and efficient PM software code. In this dissertation, I propose a framework to detect and repair PM bugs automatically using a set of new symbolic analysis techniques. Unlike existing techniques that rely on patterns and heuristics to detect and repair a small subset of PM bugs, the proposed techniques can handle a wide range of PM bugs. This is achieved by first encoding the program semantics, correctness properties, and PM requirements as a set of logical constraints, and then solving these constraints using off the shelf SMT solvers. By reasoning about these logical constraints symbolically, the proposed techniques can detect, diagnose, and repair PM bugs efficiently. Furthermore, I propose a new method to automatically infer PM requirements using a combination of static and dynamic analysis techniques. Finally, I demonstrate the feasibility of applying the proposed techniques to programs that rely on both PM and multi threading, by reasoning about persistency and concurrency simultaneously.

    Location: Henry Salvatori Computer Science Center (SAL) - 213

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/4326990557

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Defense - Umang Gupta

    Tue, Aug 22, 2023 @ 10:00 AM - 12:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Defense - Umang Gupta

    Committee Members: Greg Ver Steeg (Chair), Paul Thompson, Bistra Dilkina, Fred Morstatter

    Title: Controlling Information in Neural Networks for Fairness and Privacy

    Abstract: As machine learning becomes more prevalent in mission critical domains, the harms of unintended information captured by these models are becoming more apparent. These models can inadvertently introduce biases and memorize training data, leading to potential unfairness, inequitable outcomes, or risking privacy. These phenomena are especially alarming in applications where data privacy needs to be upheld, such as medical imaging, or where unfairness can lead to disparate outcomes, such as hiring decisions. This thesis examines ways to control and limit information in deep learning models, focusing on fairness and privacy. Specifically, we discuss ways to ensure fairness in decision making by learning fair data representations and preventing unfair language generation by correctly modulating information in neural networks. Concerning privacy, we demonstrate that releasing neuroimaging models may reveal private information about the individuals participating in the training set and discuss ways to mitigate these privacy leakages. Among these methods, differential private training is promising as it protects against all possible privacy attacks. However, differential private training can drastically hurt utility since the magnitude of noise in the outputs scales with the model parameters. To this end, we explore techniques to reduce effective model parameters during training.

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/7354464916

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Defense - Sarik Ghazarian

    Wed, Aug 23, 2023 @ 04:00 PM - 06:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Defense - Sarik Ghazarian

    Committee Members:Aram Galstyan, Nanyun Peng, Kallirroi Georgila, Gaurav Sukhatme, Morteza Dehghani

    Title: Automatic Evaluation of Open Domain Dialogue Systems

    Abstract: With the rapid development of open domain dialogue systems in recent years, it is imperative to have precise evaluation metrics that correctly assess the quality of these systems. To this end, many researchers resort primarily to human evaluation which is time consuming, expensive and it does not facilitate the model comparisons across research papers. Therefore, the existence of accurate automatic evaluation metrics that can accelerate the development cycle by assisting the process of architecture search and hyperparameter tuning is necessary. Reference based metrics such because BLEU or ROUGE fail to correlate well with human judgment in open domain settings as there can be potentially many plausible generations that do not overlap significantly with the limited set of given references. This failure leads the research towards learning based evaluation metrics that are more sophisticated and reliable.
    Automatic evaluation of open domain dialogue systems has a multifaceted nature with many fine grained quality aspects. This dissertation explores both turn level and conversation level facets of open-domain dialogue evaluation. We train models that automatically assess the relevance, engagement, coherence, and commonsense aspects of the responses generated by dialogue models. We formulate the evaluation as a classification task to identify the quality of the responses. To this end, we focus on training data and model architecture of these metrics as two main components that metrics quality strongly relies on them. We start with heuristic text level manipulations such as random swapping of utterances to create negative samples for training evaluation metrics. Then, we show that such manipulations are insufficient to appropriately reflect the issues that occur in interactions between advanced dialogue models and human. To tackle this issue, we move forward toward proposing advanced semantic level perturbations of human written responses to generate challenging negative responses that are more likely to be generated by state of the art dialogue models. Next, we complete our investigation on dialogue evaluation by concentrating on the model architecture of these metrics by incorporating knowledge from knowledge bases and leveraging prompt based generative models in a low resource setting. Finally, in addition to dialogue assessment, the main goal of automatic evaluation metrics, we leverage them as influential control factors to guide dialogue models and generate higher quality responses.

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/97105095544?pwd=Q05tWTdLSFdhNS9EY2JRMklWbHRkUT09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Defense - Jingbo Wang

    Thu, Aug 24, 2023 @ 10:00 AM - 12:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Defense - Jingbo Wang

    Committee Members: Prof. Chao Wang (chair), Prof. Nenad Medvidovic, Prof. Jyotirmoy Deshmukh, Prof. Mukund Raghothaman, and Prof. Pierluigi Nuzzo

    Title: Side channel Security Enabled by Program Analysis and Synthesis

    Abstract: The objective of my dissertation research is to develop rigorous methods and analysis tools for improving the security of software systems. I focus on a class of emerging security threats called side channel attacks. During a side channel attack, the adversary relies on exploiting statistical dependencies between the secret data e.g. passwords or encryption keys and seemingly unrelated non functional properties e.g. power consumption or execution time of the computer. In particular, power side channel leaks are caused by statistical dependencies instead of syntactic or semantic dependencies between sources and sinks. Thus, existing techniques that focus primarily on information flow security e.g. taint analysis would not work. To detect and then automatically remove these statistical dependencies in software code, I have developed a set of type inference rules to capture and quantify the leaks, and then a set of transformation based methods to mitigate the leaks. To adapt these type inference rules to constantly evolving program characteristics, I have also proposed a data driven method for learning provably sound side channel analysis rules from annotated programs. To ensure the correctness of the mitigation, I have developed new methods to help prove the equivalence of the original and mitigated programs. All of these methods aim to identify and then eliminate the side channel related statistical dependencies, which in turn leads to more secure software for critical applications.

    Location: Henry Salvatori Computer Science Center (SAL) - 213

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Proposal - Kushal Chawla

    Wed, Aug 30, 2023 @ 02:00 PM - 03:30 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Proposal - Kushal Chawla

    Committee Members: Gale Lucas (Chair), Jonathan Gratch, Jonathan May, Peter Kim, Maja Mataric

    Title: Computational Foundations for Mixed Motive Human Machine Dialogue

    Abstract: Success in a mixed motive interaction demands a balance between self serving and other serving behaviors. For instance, in a typical negotiation, a player must balance maximizing their own goals with the goals of their partner so as to come to an agreement. If the player asks for too much, this can push the partner to walk away without an agreement, hence, hurting the outcomes for all the parties involved. Such interactions are ubiquitous in everyday life, from deciding who performs household chores to customer support and high stake business deals. Consequently, AI tools capable of comprehending and participating in such mixed motive or other social influence interactions such as argumentation or therapy find broad applications in pedagogy and conversational AI.

    In this thesis, we present our foundational work for enabling mixed motive human machine dialogue. I will discuss our progress in three key areas. 1.The design of a novel task and dataset of grounded human human negotiations that has fueled our investigations into the impact of emotion expression and linguistic strategies, 2.Techniques for end to end dialogue systems for mixed motive interactions that learn to strike a balance between self and partner interests, and 3.Promoting a research community for dedicated efforts and discussion in this area

    Location: Henry Salvatori Computer Science Center (SAL) - 213

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/98290954709?pwd=NndMZ0VlbkJ4L25lVllLYTZZbWgvQT09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Dissertation Defense - Baskin B. Senbaslar

    Thu, Aug 31, 2023 @ 11:00 AM - 01:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Dissertation Defense - Baskin B. Senbaslar

    Committee Members: Gaurav S. Sukhatme (Chair), Sven Koenig, Satish Kumar Thittamaranahalli, Mihailo R. Jovanovic

    Title: Decentralized Real Time Trajectory Planning For Multi Robot Navigation in Cluttered Environments

    Abstract: Multi robot collision free and deadlock free navigation in cluttered environments with static and dynamic obstacles is a fundamental problem for many real world applications. Dynamic obstacles can additionally be interactive, i.e., changing their behaviors depending on the behaviors of other objects. We focus on decision making algorithms, with a particular emphasis on decentralized real time trajectory planning, to enable multi robot navigation in such environments.
    Practicality of the developed approaches is a central focus of ours, such that we design our systems and algorithms under assumptions that can be realized in the real world. Central concerns of our treatment are embracing on board compute, memory, and storage limitations of robotic systems, not relying on communication for safe operation, and explicitly account for communication imperfections, allowing navigation with imperfect a priori knowledge, embracing controller trajectory tracking errors and accounting for them, working with minimal sensing and estimation capabilities, and achieving highly reactive collision avoidance behavior.

    We introduce i. two decentralized real time multi robot trajectory planning algorithms to allow static obstacle, interactive dynamic obstacle, and teammate avoidance, ii. a constraint generation, overconstraining, and constraint discarding scheme to ensure inter robot collision avoidance under asynchronous planning that is inherent in decentralized systems, which we use within one of the proposed planners, and iii. a multi robot aware planning and control stack that allows collision free and deadlock free navigation in diverse types of environments, which combines three qualitatively different decision making approaches in a hierarchical manner.

    Location: Ronald Tutor Hall of Engineering (RTH) - 406

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/94985203072?pwd=Y3h6OTJIY244RU1LYlhlR0JFa3dMZz09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File