PhD Thesis Defense
Somchaya Liemhetcharat
Carnegie Mellon University

Representation, Planning, and Learning of Dynamic Ad Hoc Robot Teams

Event Location: GHC 8102Abstract: Forming an effective multi-robot team to perform a task is a key problem in many domains. The performance of a multi-robot team depends on the robots the team is composed of, where each robot has different capabilities. Team performance has previously been modeled as the sum of single-robot capabilities, and these [...]

PhD Thesis Defense
Scott Satkin
Carnegie Mellon University

Data-Driven Geometric Scene Understanding

Event Location: NSH 1305Abstract: In this thesis, we describe a data-driven approach to leverage repositories of 3D models for scene understanding. Our ability to relate what we see in an image to a large collection of 3D models allows us to transfer information from these models, creating a rich understanding of the scene.  We develop [...]

PhD Thesis Defense
Alberto Rodriguez
Carnegie Mellon University

Shape for Contact

Event Location: NSH 1305Abstract: Given a desired function for an effector, what is its appropriate shape? This thesis addresses the problem of designing the shape of a rigid end effector to perform a given manipulation task. It presents three main contributions: First, it describes the kinematics of an effector as the combination of both its [...]

PhD Thesis Defense
Yuandong Tian
Carnegie Mellon University

Theory and Practice of Globally Optimal Deformation Estimation

Event Location: GHC 8102Abstract: Nonrigid deformation modeling and estimation from images is a technically challenging task due to its nonlinear, nonconvex and high-dimensional nature. Traditional optimization procedures often rely on good initializations and give locally optimal solutions. On the other hand, learning-based methods that directly model the relationship between deformed images and their parameters either [...]

PhD Thesis Defense
Eric C. Whitman
Carnegie Mellon University

Coordination of Multiple Dynamic Programming Policies for Control of Bipedal Walking

Event Location: NSH 3305Abstract: Walking is a core task for humanoid robots. Most existing walking controllers fall into one of two categories. One category plans ahead and walks precisely; they can place the feet in desired locations to avoid obstacles but react poorly to unexpected disturbances. The other category is more reactive; they can respond [...]

PhD Thesis Defense
Michael Dille
Carnegie Mellon University

Search and Pursuit with Unmanned Aerial Vehicles in Road Networks

Event Location: NSH 1305Abstract: Across many rescue, surveillance, and scientific applications, there exists a broad need to perform wide-area reconnaissance and terrain surveys, for which unmanned aerial vehicles (UAVs) are increasingly popular. This thesis considers the task of using one or more UAVs to locate an object of interest, provide continuous viewing, and rapidly re-acquire [...]

PhD Thesis Defense
Matthew Tesch
Carnegie Mellon University

Improving Robot Locomotion Through Learning Methods for Expensive Black-Box Systems

Event Location: NSH 3305Abstract: The modular snake robots in Carnegie Mellon’s Biorobotics lab provide an intriguing platform for research: they have already been shown to excel at a variety of locomotive tasks and have incredible potential for navigating complex terrains, but much of that potential remains untapped. Unfortunately, many techniques commonly used in robotics prove [...]

PhD Thesis Defense
Brian Coltin
Carnegie Mellon University

Multi-agent Pickup and Delivery Planning with Transfers

Event Location: GHC 2109Abstract: In Pickup and Delivery Problems (PDPs), mobile vehicles retrieve and deliver a set of items. The PDP is a well-studied, NP-hard problem. Examples of the PDP include mail and courier services, taxis, ridesharing services, and robots such as our own CoBots and CreBots, which retrieve and deliver items for the occupants [...]

PhD Thesis Defense
Jiyan Pan
Carnegie Mellon University

Coherent Scene Understanding with 3D Geometric Reasoning

Event Location: NSH 1305Abstract: When looking at a single 2D image of a scene, humans could effortlessly understand the 3D world behind the scene even though stereo and motion cues are not available. Due to this remarkable human capability, one of the ultimate goals of computer vision is to enable machines to automatically infer the [...]