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:20260202T100000
DTEND;TZID=America/New_York:20260202T113000
DTSTAMP:20260922T073948
CREATED:20260126T181831Z
LAST-MODIFIED:20260128T175209Z
UID:150186-1770026400-1770031800@www.ri.cmu.edu
SUMMARY:Structured Policies for Efficient Knowledge-Guided Learning from Humans
DESCRIPTION:Abstract: Imitation learning has achieved strong performance in sequential decision-making tasks\, but typically requires large numbers of expert demonstrations\, has limited generalization capability in unseen scenarios\, and is challenging for laypeople without technical backgrounds. This thesis introduces structured policies\, a framework that integrates human domain knowledge into imitation learning by using large language models (LLMs) to generate semantically meaningful policy structures from natural language instructions while learning continuous parameters from demonstrations. By explicitly encoding task-relevant latent variables and their dependencies\, structured policies focus on the essential causal structure of the expert policy\, improving sample efficiency\, robustness\, and interpretability. We first present Knowledge Informed Models (KIM) that integrate expert domain knowledge and demonstrations in a straightforward way\, and demonstrate its sample-efficient and robustness in continuous control domains such as Lunar Lander and Car Racing. We then present Interactive Policy Restructuring and Training (InterPReT)\, an interactive learning paradigm that allows end-users to iteratively provide instructions and demonstrations to refine the policy. And we show how it can learn dependable policies from laypeople through a user study. Together\, the two projects show that structured policy is a promising way to integrate symbolic knowledge and continuous demonstrations for learning from human teachers. \nCommittee: \nProf. Reid Simmons (co-advisor) \nProf. Jean Oh (co-advisor) \nProf. Yonatan Bisk \nBowen Li
URL:https://www.ri.cmu.edu/event/structured-policies-for-efficient-knowledge-guided-learning-from-humans/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:MSR Thesis Presentation,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260202T150000
DTEND;TZID=America/New_York:20260202T163000
DTSTAMP:20260922T073948
CREATED:20260128T142348Z
LAST-MODIFIED:20260128T142348Z
UID:150213-1770044400-1770049800@www.ri.cmu.edu
SUMMARY:GRAPPA: Generalizing and Adapting Robot Policies via Online Agentic Guidance
DESCRIPTION:Abstract: \nRobot learning approaches such as behavior cloning and reinforcement learning have shown great promise in synthesizing robot skills from human demonstrations in specific environments. However\, these approaches often struggle to generalize to unseen real-world settings because they rely on task-specific demonstrations or complex simulators. While foundation models (e.g.\, LLMs\, VLMs) offer rich semantic understanding from internet-scale data\, using this knowledge to enable robotic systems to understand the underlying dynamics of the world\,  generalize policies across different tasks\, and adapt policies to new environments remains an open challenge. To alleviate these limitations\, we propose an agentic framework for robot self-guidance and self-improvement that comprises a set of role-specialized conversational agents\, including a high-level advisor\, a grounding agent\, a monitoring agent\, and a robotic agent. Our framework iteratively grounds a base robot policy on relevant objects in the environment and uses visuomotor cues to shift the policy’s action distribution toward more desirable states online\, while remaining agnostic to the subjective configuration of a given robot hardware platform.  We demonstrate that our approach can effectively guide manipulation policies to achieve significantly higher success rates\, both in simulation and in real-world experiments\, without the need for additional human demonstrations or extensive exploration. \nCode and videos are available at: https://project-grappa.github.io/ \nCommittee: \nJean Oh (advisor)\nGuanya Shi\nAndrea Bajcsy
URL:https://www.ri.cmu.edu/event/grappa-generalizing-and-adapting-robot-policies-via-online-agentic-guidance/
LOCATION:GHC 4405
CATEGORIES:MSR Thesis Presentation,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260203T123000
DTEND;TZID=America/New_York:20260203T140000
DTSTAMP:20260922T073948
CREATED:20260121T003941Z
LAST-MODIFIED:20260121T003941Z
UID:150148-1770121800-1770127200@www.ri.cmu.edu
SUMMARY:Dynamic Route Guidance in Vehicle Networks by Simulating Future Traffic Patterns
DESCRIPTION:Abstract:\n\nRoadway congestion leads to wasted time and money and environmental damage. One possible solution is adding more roadway capacity\, but this can be impractical especially in urban environments and still may not make up for a poorly-calibrated traffic signal schedule. As such\, it is becoming increasingly important to use existing road networks more efficiently. Recent research has focused on developing more efficient traffic signal control algorithms. To further reduce delays\, in this work\, we consider the synergistic idea of dynamic routing\, or changing vehicles’ routes through the network to minimize the current delay. We generate new routes by simulating the current traffic state forward at each vehicle decision point\, based on knowledge of the current routes of other vehicles and the control algorithms governing the traffic signals\, and returning the fastest routes according to this forward simulation. \nWe evaluated our algorithm using the SUMO microscopic traffic simulator on different road networks (both synthetic and real-world examples) using different traffic signal control algorithms (fixed-timing plans and schedule-driven intersection control). Experiments carried out on combinations of networks and traffic signal control algorithms show that our rerouting protocol generally reduces delay for both vehicles participating in route guidance (adopters) and those that do not (non-adopters) and that the reduction in delay increases as the proportion of adopters does. In addition\, we are able to achieve real-time performance on the (relatively small) road networks we tested on by learning a neural net approximation of expensive signal control algorithms and extending our basic routing algorithm into an anytime version compatible with early stopping. In the future\, our routing could even potentially be interleaved with a traditional graph-search-based routing algorithm\, combining the speed and scale of traditional routing with detailed small-scale optimizations generated by simulating ahead.\n\n \nThesis Committee Members:\n\n\n\n\nStephen Smith (chair)\nZachary Rubinstein\nJeff Schneider\nHsu-Chieh Hu (Miovision\, Inc.)\n  \n\n\n\n\n\n\nA draft of the thesis is available here.
URL:https://www.ri.cmu.edu/event/dynamic-route-guidance-in-vehicle-networks-by-simulating-future-traffic-patterns-3/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:PhD Thesis Defense,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260205T170000
DTEND;TZID=America/New_York:20260205T183000
DTSTAMP:20260922T073948
CREATED:20260130T000503Z
LAST-MODIFIED:20260130T000503Z
UID:150235-1770310800-1770316200@www.ri.cmu.edu
SUMMARY:Correspondence-Preserving Transformers for Scalable 3D Lifting
DESCRIPTION:Abstract: \nTakeo Kanade’s famous quip – to infer geometry or motion from images\, you must first know what in one image corresponds to what in another\, has guided geometric vision for three decades. \nDeep learning seemed to bypass this: methods in 2017-2019 lifted 2D to 3D using only reprojection loss\, exploiting an implicit bias toward smooth solutions. But these methods didn’t scale – each category needed its own architecture. Transformers promised scalability\, yet with 2D-only supervision\, naively scaling transformers often fails. The field concluded that scalable 3D learning requires massive 3D supervision (VGGT\, Depth Anything). \nThis thesis asks: what went wrong\, and can we recover 2D-only learning in the transformer era? \nThe answer: preserving correspondence\, not adding supervision is what unlocks scale. Transformers scale through selective attention\, but 3D lifting requires preserving every correspondence – these goals can conflict under standard architectures. We resolve this with an architectural principle that preserves correspondence throughout the network\, achieving 12x improvement and matching full supervision with zero 3D labels. The result is 2D-LFM (2D Lifting Foundation model): a single model lifting 45+ categories to 3D using only 2D observations. The framework extends to template-free dense reconstruction (RAT4D).\n\nThis thesis shows that Kanade’s classical insights remain crucial in the modern foundation model era\, and that understanding why correspondence matters unlocks a different path: 3D foundation models trained on the widely available 2D observations the world already provides. \nThesis Committee Members:\nSimon Lucey and László A. Jeni\, Co-chairs\nKaterina Fragkiadaki\nJason Saragih\, Meta \nLink to thesis draft
URL:https://www.ri.cmu.edu/event/correspondence-preserving-transformers-for-scalable-3d-lifting/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:PhD Thesis Defense,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260206T083000
DTEND;TZID=America/New_York:20260206T100000
DTSTAMP:20260922T073948
CREATED:20260121T162246Z
LAST-MODIFIED:20260129T191639Z
UID:150154-1770366600-1770372000@www.ri.cmu.edu
SUMMARY:Empirically Grounded LLM-based Virtual Patients for Psychotherapy Training: Design\, Modeling\, and Evaluation
DESCRIPTION:Abstract:\n\n\nThe need for mental health care continues to outpace the supply of trained psychotherapists\, while psychotherapy training remains constrained by limited supervision time and scarce opportunities for repeated\, feedback-rich practice in realistic scenarios. Simulation-based training can mitigate these constraints\, but actor-based standardized patients are costly and difficult to scale\, and many clinically challenging moments are ethically and logistically hard to practice with real clients. Large language models (LLMs) make interactive virtual patients increasingly feasible as a complement to conventional training; however\, early systems are often prompt-driven rather than empirically grounded\, exhibit limited psychologically meaningful state and longitudinal change\, and predominantly focus on one-on-one sessions—leaving multi-party modalities such as couples therapy under-supported. \nThis thesis advances an empirical and design-oriented framework for building more realistic and pedagogically effective virtual patients grounded in psychotherapy process theory and real clinical data. Chapter 2 develops scalable\, LLM-based measurement of therapist behaviors and client responses from large psychotherapy transcript corpora and uses structural equation modeling to estimate process-level dynamics linking therapist micro-skills and relational factors to subsequent client disclosure and emotional expression. Chapter 3 translates these empirically informed requirements into a multimodal\, multi-agent couples therapy simulator that represents stage-structured sessions and recurrent interaction cycles such as demand–withdraw\, enabling trainees to practice timing- and wording-sensitive interventions in high-conflict moments; an evaluation with licensed therapists examines realism and training relevance. Chapter 4 proposes an adaptive virtual patient architecture in which an LLM agent maintains latent psychological states that update in real time according to SEM-derived interpersonal dynamics conditioned on detected therapist behaviors\, together with a plan for evaluating psychological fidelity. \nBy integrating theory-grounded measurement\, empirical causal modeling\, and interactive system design\, this work lays a pathway for scalable psychotherapy training tools that make the consequences of therapist choices visible\, support deliberate practice\, and responsibly expand access to high-quality skills development. \n\n \nThesis Committee:\n\n\n\n\n\nHaiyi Zhu (Chair)\, HCII\, CMU\nSherry Wu\, HCII & LTI\, CMU\nAaron Steinfeld\, RI\, CMU\nHolly Swartz\, Psychiatry\, UPMC\n\n\n\n\n\n\n\n\n \nA draft of the thesis proposal is available here.
URL:https://www.ri.cmu.edu/event/empirically-grounded-llm-based-virtual-patients-for-psychotherapy-training-design-modeling-and-evaluation/
LOCATION:Gates Hillman Center 6115
CATEGORIES:PhD Thesis Proposal,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260211T090000
DTEND;TZID=America/New_York:20260211T103000
DTSTAMP:20260922T073948
CREATED:20260202T194426Z
LAST-MODIFIED:20260202T194426Z
UID:150247-1770800400-1770805800@www.ri.cmu.edu
SUMMARY:Plan What You Can\, Learn What You Must: Interleaving Planning and Learning for Multi-Robot Manipulation
DESCRIPTION:Abstract:\nMulti-robot manipulation is becoming an inevitability of modern robotics. As hardware costs fall\, the barrier to deploying robot teams has shifted from economics to algorithmic capability. To fulfill their promise\, multi-robot systems must jointly reason about geometric coordination\, contact interactions\, task assignments\, and scene dynamics\, while adapting to variable team sizes and diverse robot embodiments. \nThe field has long pursued two parallel yet complementary approaches to robotic manipulation. Classical planning methods explicitly model system dynamics and interactions\, enabling scalability\, adaptability\, and strong formal guarantees—but confining applicability to well-understood systems. In contrast\, recent work abandons explicit modeling in favor of data-driven flexibility\, capturing interaction dynamics that are difficult to model but struggling to generalize when data is scarce or task distributions shift. Even though the strengths of one mirror the weaknesses of the other\, only few efforts have sought principled ways to combine them within a unified framework for multi-robot manipulation. \nThis thesis targets the boundary between explicit planning and learned policy synthesis\, developing algorithms that plan what can be modeled and learn what cannot. By exploiting structure and identifying where learning is tractable\, we develop methods for multi-robot manipulation that generalize across team sizes and robot embodiments while retaining the flexibility to learn hard-to-model components. \nWe begin at the structured end of the spectrum\, addressing scalable motion planning for multi-robot-arm systems. After introducing two algorithms for labeled settings–where each robot has an assigned goal–we turn to our first proposed work: an anonymous multi-arm motion planner that generates coordinated trajectories under interchangeable-goal formulations. This capability is essential when policies specify contact objectives without prescribing which robot should execute them. \nFrom this structured foundation\, we dive into the boundary between planning and learning.\nWe develop two methods that compose simple\, data-efficient policies through lightweight planning—one for coordination under implicit objectives and another for planar collaborative manipulation—and propose our second research body direction: extending these ideas to realistic 3D domains involving contact-rich manipulation of large rigid objects. This work determines when analytical models suffice\, when learning is necessary\, and seeks to invoke learned models where they perform well (i.e.\, are in-distribution)\, defining a systematic interface between explicit planning and learned interaction dynamics. \nTogether\, these contributions reveal how structure and learning can coexist: flexible and generalizable multi-robot manipulation emerges not from choosing between planning and learning\, but from combining them. \n\nThesis Committee:\n\n\nProf. Jiaoyang Li (co-chair)\nProf. Maxim Likhachev (co-chair)\nProf. Andrea Bajcsy\nProf. Yilun Du (Harvard University)\n\n\nThesis proposal document draft
URL:https://www.ri.cmu.edu/event/plan-what-you-can-learn-what-you-must-interleaving-planning-and-learning-for-multi-robot-manipulation/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:PhD Thesis Proposal,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260217T171500
DTEND;TZID=America/New_York:20260217T183000
DTSTAMP:20260922T073948
CREATED:20260210T174551Z
LAST-MODIFIED:20260210T174551Z
UID:150339-1771348500-1771353000@www.ri.cmu.edu
SUMMARY:A Layered Foundation for Reliable Trajectory Forecasting: Data\, Evaluation\, and Methods
DESCRIPTION:Abstract:\nReliable trajectory forecasting is a foundational requirement for autonomous robotic systems operating in environments with humans. Despite substantial progress in modeling techniques\, existing forecasting systems often fail under distribution shift\, exhibit socially implausible behaviors\, or report misleading performance due to limitations in data coverage and evaluation practices. This thesis argues that reliable trajectory forecasting does not depend on model architecture alone\, but instead requires a layered foundation: good data to train and evaluate on\, good benchmarking to measure progress faithfully\, and good methods that leverage the full richness of available sensor information\, each layer building on the ones below it. \nFirst\, this thesis investigates the role of data quality and coverage. We demonstrate how incomplete representation of rare but critical behaviors\, particularly those in the tails of the data distribution\, can significantly impair forecasting reliability. We then propose strategies for improving dataset coverage through targeted data collection in safety-critical scenarios\, and show how these interventions lead to more robust generalization on forecasting benchmarks. \nSecond\, we examine benchmarking and evaluation practices\, revealing that widely used metrics often obscure failure modes such as collisions or socially unlikely interactions. To address this\, we introduce and advocate for evaluation metrics that align with safety objectives and better reflect the conditions necessary for deployment on real-world robotic systems. These provide more faithful signals of model performance and enable more meaningful comparisons across forecasting approaches. \nFinally\, building upon improved data and evaluation foundations\, this thesis presents a forecasting method that makes effective use of the wealth of information present in sensor data. We introduce a forecasting approach that utilizes human body pose features as well as deep semantic environment features\, resulting in predictions that are more socially consistent and better obey environmental constraints without sacrificing accuracy. Our method benefits from the foundations of comprehensive data coverage and safety-oriented benchmarking\, demonstrating that advances in forecasting methods are most meaningful when built upon solid data and evaluation foundations. \nCollectively\, this work provides a unified framework for understanding and improving trajectory forecasting reliability. By addressing data\, evaluation\, and modeling together\, this thesis contributes insights and tools toward building forecasting systems that are better aligned with the requirements for real-world autonomous decision-making.\n \nThesis Committee Members:\nKris Kitani\, Co-chair\nDeva Ramanan\, Co-chair\nAaron Steinfeld\n \nHamid Rezatofighi\, Monash University\n\n \nA draft of the thesis proposal document is available here.
URL:https://www.ri.cmu.edu/event/a-layered-foundation-for-reliable-trajectory-forecasting-data-evaluation-and-methods/
LOCATION:GHC 4405
CATEGORIES:PhD Thesis Defense,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260218T100000
DTEND;TZID=America/New_York:20260218T113000
DTSTAMP:20260922T073948
CREATED:20260212T181825Z
LAST-MODIFIED:20260212T181825Z
UID:150366-1771408800-1771414200@www.ri.cmu.edu
SUMMARY:Toward Aligned Vision Models
DESCRIPTION:Abstract:\nModern vision and vision–language models (VLMs) achieve remarkable perceptual performance\, yet their internal representations often misalign with human-understandable concepts\, clinical reasoning\, or the causal structure of data. Such misalignment limits trust\, generalization\, and safety – particularly in high-stakes domains such as medical imaging. This thesis proposes a comprehensive framework for model alignment\, developing methods that bring model representations closer to clinically meaningful\, causally grounded\, and task-adaptive concepts across diverse visual tasks. \nFirst\, I introduce biomarker-grounded alignment for lung ultrasound (LUS)\, where domain-informed interpretable biomarkers serve as anchors to structure deep model representations. I develop methods that disentangle anatomical\, morphological\, and artifact-level biomarkers and demonstrate that these aligned representations improve interpretability while matching or exceeding fully supervised baselines across diagnostic and severity scoring tasks. \nSecond\, I propose a causal feature selection framework based on Markov blanket discovery to identify minimal yet causally relevant feature subsets across medical and non-medical datasets. By uncovering natural experiments embedded in observational data\, the method reveals features that are inherently robust\, reduces spurious correlations\, and provides theoretical and empirical evidence for improved generalization and interpretability. \nThird\, I explore prompt-tuning–based alignment for object detection\, showing that positive and negative few-shot exemplars can be leveraged for iterative prompt optimization. This strategy steers models toward task-relevant visual concepts\, improves detector robustness under domain shifts\, and reveals interpretable activation patterns associated with object-level reasoning.\n\nCollectively\, these contributions establish a cohesive strategy for aligning vision models with human-understandable\, causally grounded\, and task-relevant representations\, advancing the development of reliable\, interpretable\, and generalizable systems suitable for real-world clinical and broader perceptual deployment. \nFinally\, I outline two future research directions to further strengthen alignment and its evaluation. The first explores gradient-based soft prompt tuning\, which learns continuous prompt embeddings through backpropagation to enable more stable and scalable prompt optimization. The second develops saliency mapping for VLMs by evaluating region-proposal masks (e.g.\, from SAM) based on their impact on downstream performance\, measured through VQA-style scoring\, enabling quantitative assessment of visual explanation quality and faithfulness. \n \nThesis Committee Members:\nJohn Galeotti\, Co-chair\nDeva Ramanan\, Co-chair\nZachary Lipton\nTrevor Darrell\, University of California\, Berkeley\n \nA draft of the thesis proposal document is available here.
URL:https://www.ri.cmu.edu/event/toward-aligned-vision-models/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:PhD Thesis Proposal,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260219T183000
DTEND;TZID=America/New_York:20260219T200000
DTSTAMP:20260922T073948
CREATED:20260209T220741Z
LAST-MODIFIED:20260209T221052Z
UID:150335-1771525800-1771531200@www.ri.cmu.edu
SUMMARY:Learning Dynamic and Competitive Human Skills and Strategies for Animation and Robotics
DESCRIPTION:Abstract:\nHumanoid control in animation and robotics requires physically realistic motion as well as the ability to adapt\, coordinate actions over time\, and make decisions in response to changing environments and other agents. Human motion data provides a powerful source of prior knowledge for learning natural and stable movement\, but many existing approaches rely on reference motions in ways that are difficult to generalize beyond demonstrated scenarios. As a result\, it remains challenging for humanoid agents to reuse and compose skills over time\, limiting their ability to operate in interactive and competitive environments. \nThis thesis investigates how human motion references can be used more flexibly\, not as strict templates to be reproduced\, but as behavioral priors that shape how agents move while allowing adaptation to new tasks and conditions. Rather than focusing on the replication of specific motions\, the emphasis is placed on learning reusable structure from human behavior that supports robustness and generalization across diverse goals\, environments\, and interactions. Through this perspective\, humanoid agents can preserve natural movement while remaining responsive to novel objectives and disturbances. \nBuilding on this foundation\, the thesis extends beyond single-agent skill execution to study higher-level behavior in interactive and competitive settings. Domains such as sports highlight that strong motor skills alone are insufficient: successful performance also depends on selecting appropriate actions\, timing them effectively\, and coordinating behavior over longer time horizons in response to both the environment and other agents. Overall\, this work presents a unified view of humanoid control in which reference motion supports generalization rather than constraining behavior\, and enables adaptive and strategic interaction in both animation and robotics. \nThesis Committee:\nJessica Hodgins\, chair\nDeva Ramanan\nGuanya Shi\,\nXue Bin Peng\, Simon Fraser University\, NVIDIA\nTaku Komura\, The University of Hong Kong \nA draft of the thesis proposal document is available here.
URL:https://www.ri.cmu.edu/event/learning-dynamic-and-competitive-human-skills-and-strategies-for-animation-and-robotics/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:PhD Thesis Proposal,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260220T143000
DTEND;TZID=America/New_York:20260220T160000
DTSTAMP:20260922T073948
CREATED:20260210T173900Z
LAST-MODIFIED:20260210T173900Z
UID:150337-1771597800-1771603200@www.ri.cmu.edu
SUMMARY:Advancing Spacecraft Autonomy: Optimal GNC\, Vision-Based Estimation\, and Systems Integration for Small Spacecraft
DESCRIPTION:Abstract :\nSmall spacecraft are increasingly expected to perform complex missions despite strict constraints in mass\, power\, and onboard computation. Meeting these demands requires advances in autonomy that enable effective decision-making\, adaptive control\, and robust state estimation within resource-limited platforms. This thesis develops optimization- and machine-learning–based methods to improve spacecraft autonomy across guidance\, navigation\, and control (GNC)\, perception\, and onboard decision-making\, building on flight-relevant small spacecraft systems. \n\nAchieving onboard autonomy introduces challenges across multiple subsystems. Increased computational workloads raise thermal dissipation\, motivating new thermal management strategies for reliable operation in planetary and deep-space environments. For attitude and orbit control\, this work investigates propellant-free approaches based on magnetorquer Lyapunov control and differential-drag formation flying\, enabling precise maneuvering on constrained platforms. In navigation\, visual-inertial techniques are developed for GPS-denied environments by tightly integrating computer vision with inertial sensing\, while machine learning methods improve feature extraction and uncertainty-aware landmark detection for robust localization with limited prior information.\n\nThe thesis further presents near real-time georectification methods that directly register satellite imagery to planetary reference frames\, supporting onboard mapping and situational awareness. Together\, these contributions demonstrate how optimization and learning can enhance the autonomy\, reliability\, and scientific value of small satellite missions\, enabling more capable exploration and operations in dynamic and uncertain space environments.\n\nThesis Committee Members:\n \nZac Manchester (Chair)\nRed Whittaker\nBrandon Lucia\nKiruthika Devaraj (Planet Labs)\nAndrew Horchler (Astrobotic) \nLink to draft thesis document
URL:https://www.ri.cmu.edu/event/advancing-spacecraft-autonomy-optimal-gnc-vision-based-estimation-and-systems-integration-for-small-spacecraft-2/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:PhD Thesis Defense,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260225T093000
DTEND;TZID=America/New_York:20260225T110000
DTSTAMP:20260922T073948
CREATED:20260217T185857Z
LAST-MODIFIED:20260217T190000Z
UID:150422-1772011800-1772017200@www.ri.cmu.edu
SUMMARY:UFM: A Simple Path towards Unified Dense Correspondence with Flow
DESCRIPTION:Abstract: Dense image correspondence is central to many applications\, such as visual odometry\, 3D reconstruction\, object association\, and re-identification. Historically\, dense correspondence has been tackled separately for wide-baseline scenarios and optical flow estimation\, despite the common goal of matching content between two images. In this talk\, we develop a Unified Flow & Matching model (UFM)\, which is trained on unified data for pixels that are co-visible in both source and target images. UFM uses a simple\, generic transformer architecture that directly regresses the (u\, v) flow. It is easier to train and more accurate for large flows compared to the typical coarse-to-fine cost volumes in prior work. UFM is 28% more accurate than state-of-the-art flow methods (Unimatch)\, while also having 62% less error and 6.7x faster than dense wide-baseline matchers (RoMa). UFM is the first to demonstrate that unified training can outperform specialized approaches across both domains. This result enables fast\, general-purpose correspondence and opens new directions for multi-modal\, long-range\, and real-time correspondence tasks. \nCommittee: \nProf. Wenshan Wang (co-advisor)  \nProf. Sebastian Scherer (co-advisor)  \nProf. Deva Ramanan\n \nNikhil Keetha
URL:https://www.ri.cmu.edu/event/ufm-a-simple-path-towards-unified-dense-correspondence-with-flow/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:MSR Thesis Presentation,Student Talks
END:VEVENT
END:VCALENDAR