BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Robotics Institute Carnegie Mellon University - ECPv6.15.12.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Robotics Institute Carnegie Mellon University
X-ORIGINAL-URL:https://www.ri.cmu.edu
X-WR-CALDESC:Events for Robotics Institute Carnegie Mellon University
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:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20270314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20271107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260918T100000
DTEND;TZID=America/New_York:20260918T113000
DTSTAMP:20261007T041328
CREATED:20260908T155758Z
LAST-MODIFIED:20260908T155947Z
UID:153494-1789725600-1789731000@www.ri.cmu.edu
SUMMARY:RI PhD Thesis Defense - Ingrid Navarro Anaya
DESCRIPTION:Date: September 18th\, 2026 \nTime: 10:00 AM (ET) \nZoom: link \nLocation: NSH 4305 \nType: PhD Thesis Defense \nWho: Ingrid Navarro Anaya \n  \nTitle: Towards Generalizable Motion Prediction under Distribution Shifts \n  \nAbstract: \nAutonomous robots are increasingly expected to operate in dynamic\, human-centered environments. To do so safely and efficiently\, they must reason about how people move and interact. In domains like driving\, social navigation\, and aviation\, a common approach is to learn models of human motion directly from recorded data and use the resulting priors to inform downstream systems like simulators and planning stacks. \n  \nDespite the growing availability of datasets\, benchmarks\, and modeling techniques\, state-of-the-art methods remain unreliable for real-world deployment\, often generalizing poorly to novel environments and rare events. Much of this stems from recorded datasets covering few environments and few safety-relevant events relative to what a deployed system will ultimately encounter. Broadly\, the field has addressed this in four main ways: validating autonomy stacks on the road\, collecting more data\, synthesizing relevant scenarios\, and adapting at test time. These are all valuable and necessary strategies\, but each is bounded by risk\, cost\, the sim-to-real gap\, or the difficulty of reliably detecting and adapting to a shift\, respectively. \n  \nThese strategies share the premise that the data we hold is insufficient. This dissertation argues that such data is also underexploited and thus pursues a complementary direction\, asking how much actionable signal existing datasets already contain but current practice overlooks. We do so through a recurring paradigm we call scenario characterization: describing a scenario in terms of a property of interest and acting on that description downstream. We use this paradigm in three ways. The first is for guidance and abstraction\, shaping what a model trains or optimizes. The second is for mining and benchmarking\, determining what a model trains on and what is withheld to test it. The third is for analysis\, fixing the basis on which results are studied. We apply these uses across two settings: in-distribution generalization\, which draws mainly on guidance and abstraction\, and generalization under distribution shift\, which draws on all three and is where the main contributions concentrate. \n  \nWe further argue that evidence for generalization is typically gathered only within a single domain\, so a claim that holds there is rarely challenged elsewhere. This is largely because\, outside autonomous driving\, no motion domain offers comparable infrastructure and scale. This dissertation therefore contributes aviation as a testbed\, introducing a large-scale framework and dataset for airport surface movement forecasting. \n  \nThrough this framework and our experimental settings\, we expose generalization failures that would otherwise have remained hidden in aggregate metrics. We also enable reading aviation and driving on a common basis\, hinting at what transfers and what does not. Finally\, we also provide early evidence that the signal recovered through our framework may help systems gain the risk awareness needed to handle real-world critical events. \n  \nThesis Committee: \nJean Oh (co-chair) \nJonathan Francis (co-chair) \nSebastian Scherer \nAndrea Bajcsy \nAlexandre Alahi (EPFL)
URL:https://www.ri.cmu.edu/event/ri-phd-thesis-defense-ingrid-navarro-anaya/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:PhD Thesis Defense,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260923T141500
DTEND;TZID=America/New_York:20260923T163000
DTSTAMP:20261007T041328
CREATED:20260921T143237Z
LAST-MODIFIED:20260923T173509Z
UID:153762-1790172900-1790181000@www.ri.cmu.edu
SUMMARY:RI PhD Thesis Defense - Bardienus Duisterhof
DESCRIPTION:Date: 9/23/2026 \nTime: 2:00 PM – 4:00 PM \nZoom: https://cmu.zoom.us/j/98474543738?pwd=PVQo6JfRsWvuB9eWLqbatVivVv7CTj.1 \nLocation: NSH 4305 \nType: PhD Thesis Defense \nWho: Bardienus Pieter Duisterhof \nTitle: Spatiotemporal World Models for Robot Manipulation \nAbstract: \nRobot manipulation aims to automate tasks that are too dull\, dirty\, or dangerous for humans. This future requires remarkable resource efficiency: robots must adapt to new tasks with limited data and compute while meeting stringent performance requirements. Current systems can succeed at dexterous tasks but require substantial resources to meet industrial standards. One possible explanation for this inefficiency is that frontier models learn directly from RGB images\, which are typically dominated by content irrelevant to robots. Previous work has addressed this problem through task-specific feature engineering\, improving efficiency by focusing on task-relevant information. Can we construct similarly focused representations that remain scalable and broadly applicable? This thesis explores spatiotemporal representations—representations of 3D geometry and motion over time—focusing on their reconstruction\, generation\, and robot applications. \nThe first part of this thesis addresses unconstrained spatiotemporal reconstruction. Robots may benefit from representations that place past observations in a precise spatial and temporal context. We contribute methods that improve 3D reconstruction and calibration from arbitrary image sets and lens configurations. We show that calibrated multi-camera setups and neural rendering yield precise reconstruction in dynamic scenes\, including highly deformable objects such as cloth. \nIn the second part of this thesis\, we investigate learning spatiotemporal generative priors for robot manipulation. Humans can infer plausible geometry and dynamics from a single observation. Can we instill similar priors into robots? We contribute methods that can infer depth maps\, complete object geometry\, and predict object dynamics. With Modality Forcing\, we investigate text-to-image pre-training as a way to learn geometric priors. With PointZero\, we use 3D point track completion to learn spatiotemporal priors without any robot data. \nThe final part of this thesis considers spatiotemporal world models applied to robot manipulation. First\, we show that PointZero improves performance in robot manipulation tasks\, including imitation learning and action-conditioned dynamics prediction. Next\, we investigate how predicting future scene states can guide action generation in world-action models (WAMs). In 3PoinTr\, we show that 3D point tracks can serve as compact task plans that support transfer from human demonstrations to robot execution. In ModAR\, we autoregressively denoise multiple future modalities and robot actions\, achieving the best performance among the WAM formulations tested. We systematically study which modalities contribute most to manipulation performance and find that predicting RGB images provides no consistent additional benefit at the scale studied. \nTogether\, these works connect reconstruction\, learned geometric and dynamics priors\, and action generation to study how spatiotemporal representations can support efficient\, scalable robot learning. \nCommittee:  \nJeffrey Ichnowski (Chair)\nDeva Ramanan\nShubham Tulsiani\nAbhishek Gupta (University of Washington)
URL:https://www.ri.cmu.edu/event/ri-phd-thesis-defense-bardienus-duisterhof-2/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:PhD Thesis Defense,Student Talks
END:VEVENT
END:VCALENDAR