Student Talks
Structured Policies for Efficient Knowledge-Guided Learning from Humans
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 [...]
GRAPPA: Generalizing and Adapting Robot Policies via Online Agentic Guidance
Abstract: Robot 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 [...]
Dynamic Route Guidance in Vehicle Networks by Simulating Future Traffic Patterns
Abstract: Roadway 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. [...]
Correspondence-Preserving Transformers for Scalable 3D Lifting
Abstract: Takeo 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. Deep learning seemed to bypass this: methods in 2017-2019 lifted 2D to 3D using only reprojection loss, exploiting an implicit bias toward smooth [...]
Empirically Grounded LLM-based Virtual Patients for Psychotherapy Training: Design, Modeling, and Evaluation
Abstract: The 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 [...]
Plan What You Can, Learn What You Must: Interleaving Planning and Learning for Multi-Robot Manipulation
Abstract: Multi-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 [...]
A Layered Foundation for Reliable Trajectory Forecasting: Data, Evaluation, and Methods
Abstract: Reliable 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 [...]
Toward Aligned Vision Models
Abstract: Modern 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 [...]
Learning Dynamic and Competitive Human Skills and Strategies for Animation and Robotics
Abstract: Humanoid 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 [...]
Advancing Spacecraft Autonomy: Optimal GNC, Vision-Based Estimation, and Systems Integration for Small Spacecraft
Abstract : Small 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 [...]