Logo: University of Southern California

Events Calendar



Select a calendar:



Filter April Events by Event Type:



Events for April 30, 2025

  • PhD Thesis Proposal - Kegan Strawn

    Wed, Apr 30, 2025 @ 11:00 AM - 12:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Title: Conformal Prediction for Safe Robot Planning in Dynamic Environments
     
    Date and Time: Wednesday, 04/30/25 - 11:00a - 12:00p
     
    Location: GCS 502C
     
    Committee Members: Lars Lindemann, Nora Ayanian, Jyotirmoy Vinay Deshmukh, Erdem Biyik, Ketan Savla
     
    Abstract: Safe robot navigation in dynamic environments around other uncontrolled agents is a central challenge for robotics. This thesis proposal explores statistical tools to quantify uncertainty in control and planning for collision avoidance applications in new and challenging problem settings. First, we introduce conformal predictive safety filters, which augment reinforcement learning policies with learned safety layers that avoid uncertainty regions around dynamic agents, providing probabilistic safety guarantees and reducing collisions without being overly conservative. We then extend this idea to multi-agent pathfinding (MAPF) with CP-Solver, a novel variant of Enhanced Conflict-Based Search that plans around uncontrollable agents. By incorporating uncertainty-aware predictions into planning, CP-Solver offers probabilistic safety guarantees while maintaining high throughput. We conclude with future work on online model selection to robustify and adapt safety filters in real-time, demonstrating safety and performance results through multi-robot drone simulations. Together, these contributions advance safety guarantees and performance in multi-agent systems by combining prediction, uncertainty quantification, and planning.

    Location: Ginsburg Hall (GCS) - 502C

    Audiences: Everyone Is Invited

    Contact: Kegan Strawn


    This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.

  • PhD Dissertation Defense - Sabyasachee Baruah

    Wed, Apr 30, 2025 @ 02:00 PM - 04:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Title: Character-centric Computational Narrative Understanding  
     
    Date and Time: April 30th, 2025: 2:00p - 4:00p  
     
    Location: RTH 320  
     
    Committee Members: Dr. Shrikanth Narayanan (chair), Dr. Maja Mataric, and Dr. Morteza Dehghani (outside member  
     
    Abstract: Narrative is a mechanism through which we try to understand the world. We use stories to communicate with each other, assign meaning to our actions, and create interpersonal bonds through similar experiences. It is important to study narratives to find the qualities of effective storytelling, understand how they enable human collaboration, and study the representation of people and ideas. However, even though substantial discourse on narrative understanding exists in the research community, it lacks a uniform and structured computational approach. Therefore, in this dissertation, I define narrativity and propose a modality-agnostic computational pipeline to study narratives. I identify the essential building blocks of narratives – characters, events, attributes, and relations – and define how their interaction creates narrativity. I focus on the character-centric tasks of the proposed pipeline to underscore the importance of narrative characters. I categorize the various character understanding tasks, and present my contributions towards the resolution and attribution tasks, building towards a holistic understanding of the narrative.
     
    Zoom Link: https://usc.zoom.us/j/95907531652?pwd=6eNMG5kHGUec6zICZKYaan3HebWvGS.1
     

    Location: Ronald Tutor Hall of Engineering (RTH) - 320

    Audiences: Everyone Is Invited

    Contact: Sabyasachee Baruah


    This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.