PhD Thesis Proposal

Abstract:  Soft robot hands offer compelling advantages for manipulation tasks, including inherent safety through material compliance, robust adaptation to uncertain object geometries, and the ability to conform to complex shapes passively. However, these same properties create significant challenges for conventional sensing and control approaches. This talk presents approaches to bridging advances in geometric learning and [...]

Abstract: As autonomous robots are increasingly expected to operate in dynamic, human-centered environments, it is crucial to develop robot policies that ensure safe and seamless interactions with humans, all while allowing robots to complete their intended tasks efficiently. To achieve this, robots must be capable of making informed decisions that account for human preferences, ensuring [...]

Abstract: Teams of multiple robots working together can achieve challenging tasks like warehouse automation, search and rescue, and cooperative construction. However, finding efficient collision-free motions for all agents is extremely challenging as the complexity of the multi-agent motion planning (MAMP) problem grows exponentially with the number of agents. Multi-Agent Path Finding (MAPF) is a subset [...]

Abstract: Building a generalist robot capable of performing diverse tasks in unstructured environments remains a longstanding challenge. A recent trend in robot learning aims to address this by scaling up demonstration datasets for imitation learning. However, most large-scale robotics datasets are collected in the real-world, often via manual teleoperation. This process is labor-intensive, slow, hardware-dependent, [...]

Abstract: Optimization and machine learning-based methods are increasingly critical in enhancing the autonomy, efficiency, and overall return on investment (ROI) of small, resource-constrained spacecraft. By enabling more effective decision-making, adaptive control, and robust state estimation, these techniques expand mission capabilities while operating within strict mass, power, and computational limitations. This thesis builds on previous contributions [...]

Abstract: Robots operating in the real world can leverage intentional contacts with objects to understand and manipulate them effectively—especially in cluttered, partially observable environments where vision alone is insufficient. This thesis explores how intentional physical interactions, combined with haptic sensing, can provide rich spatial, temporal, and physical cues that enhance a robot’s perception and decision-making. [...]

Abstract: Robots, and autonomous systems in general, are becoming increasingly more advanced beyond traditional functions. This can potentially widen the mismatch between human expectations of system behaviors during interaction, especially when the systems behave unexpectedly. Unexpected system behaviors could induce negative emotional responses in humans, which not all systems have the capability of recognizing and [...]

Abstract: Bayesian Experimental Design (BED) provides a principled framework for sequential data-collection under uncertainty, and is used in a wide set of domains such as clinical trials, ecological monitoring, and hyperparameter optimization. Despite its wide applicability, BED methods remain challenging to deploy in practice due to their significant computational demands. This thesis addresses these computational [...]

Abstract: How can we enable robots to perceive, adapt, and understand their surroundings like humans—in real-time and under uncertainty? Just as humans rely on vision to navigate complex environments, robots need robust and intelligent perception systems—“eyes” that can endure sensor degradation, adapt to changing conditions, and recover from failure. However, today’s visual systems are fragile—easily [...]

Abstract: Modern AI won’t achieve physical intelligence until it can extract rich, semantic spatial knowledge from the wild ocean of internet video—not just curated motion-capture datasets or expensive 3D scans. This thesis proposes a self-bootstrapping pipeline for converting raw pixels into large-scale 3D and 4D spatial understanding. It begins with multi-view bootstrapping: using just two [...]