PhD Thesis Proposal
Rosen Diankov
Carnegie Mellon University

Robotics Framework for Automated Construction of Autonomous Manipulation Programs

Event Location: Newell Simon Hall 3305Abstract: Society is becoming more automated with robots beginning to perform most tasks in factories and starting to help out in home and office environments. Arguably, one of the most important functions of robots is the ability to manipulate their environment to accomplish basic tasks. However, the space of possible [...]

PhD Thesis Proposal
Mark Palatucci
Carnegie Mellon University

Learning Methods for Thought Recognition

Event Location: NSH 3305Abstract: This thesis proposal considers the problem of training machine learning classifiers in domains where data are very high dimensional and training examples are extremely limited or impossible to collect for all classes of interest. As a case study, we focus on the application of thought recognition, where the objective is to [...]

PhD Thesis Proposal
Hanns W. Tappeiner
Carnegie Mellon University

Improving Teleoperation of Mobile Robots and Manipulators in Large Workspaces via Haptic Feedback

Event Location: GHC 6501Abstract: Many applications today involving mobile robots require human control because the task to solve or the environment to move in is too complicated for existing fully autonomous systems. While computers today are already better than humans at controlling machines at a low level and can provide operators with a higher level [...]

PhD Thesis Proposal
Benjamin Stephens
Carnegie Mellon University

Control of Full-Body Humanoid Push Recovery Using Simple Models

Event Location: GHC 8115Abstract: Humanoid robots represent the state of the art in complex robot systems, but the design of controllers can be challenging and tedious. High performance controllers that can handle unknown perturbations will be required if complex robots are to one day interact safely with people in everyday environments. The high degree of [...]

PhD Thesis Proposal
Ethan Tira-Thompson
Carnegie Mellon University

Ambulatory Manipulation

Event Location: GHC 6115Abstract: Robots with legs have a number of advantages over those with wheels, such as greater ability to navigate through rough terrain, more flexible manipulation of objects, and fully holonomic control of the body. However, leveraging these advantages on a multi-legged system is computationally intensive and often relegates leg usage exclusively to [...]

PhD Thesis Proposal
Young-Woo Seo
Carnegie Mellon University

A Self-Supervised Machine Learning Framework for Augmenting Cartographic Resources

Event Location: NSH 1109Abstract: Maps are important for both human and robot navigation. Given a route, driving assistance systems brief maps to guide human drivers to their destinations. Similarly, topological maps of road network provide a robotic vehicle with information about where it can drive and what driving behaviors it should use. Maps simplify both [...]

PhD Thesis Proposal
Peter Barnum
Carnegie Mellon University

Illuminating Water Drops

Event Location: NSH 1305Abstract: Water drops are present throughout our daily lives. Microscopic droplets create fog and mist, and large drops fall as rain. Because of their shape and refractive properties, water drops exhibit a wide variety of visual effects. If not directly illuminated by a light source, then they are difficult to see. But [...]

PhD Thesis Proposal
Mihail N. Pivtoraiko
Carnegie Mellon University

Principled Search Space Design

Event Location: Newell Simon Hall 1507Abstract: Motion planning and navigation of outdoor mobile robots has received a lot of attention in the last thirty years, yet today it still remains a challenging problem. Among the many reasons, three stand out. First, most physical mobility systems feature differential constraints that render the coupling between the control [...]

PhD Thesis Proposal
Ross A. Knepper
Carnegie Mellon University

Realtime Contextual Trajectory Set Generation for Local Area Motion Planning

Event Location: NSH 3305Abstract: Robotic motion planning is known to be an NP Hard problem. Many real-world applications employ hierarchical planning to decompose a complex problem into a set of sub-problems, each addressed by a sub-planner that makes different trade-offs and assumptions. To achieve scalability, long-range planners such as D* simplify the robot’s motion model, [...]

PhD Thesis Proposal
Tomasz Malisiewicz
Carnegie Mellon University

Data-driven Scene Parsing With the Visual Memex

Event Location: NSH 3305Abstract: This proposal is concerned with the problem of image understanding. Given a single static image, the goal is to explain the entire image by recognizing all of the objects depicted in the image. We formulate the problem of image understanding as image parsing -- breaking up the image into semantically meaningful [...]