PhD Thesis Defense
Learning to Search: Structured Prediction Techniques for Imitation Learning
Event Location: Newell Simon Hall 1507Abstract: Modern robots successfully manipulate objects, navigate rugged terrain, drive in urban settings, and play world-class chess. Unfortunately, programming these robots is challenging, time-consuming and expensive; the parameters governing their behavior are often unintuitive, even when the desired behavior is clear and easily demonstrated. Inspired by successful end-to-end learning systems [...]
Spectral Graph Matching, Learning, and Inference for Computer Vision
Event Location: Newell Simon Hall 1305Abstract: Several important applications in computer vision, such as 2D and 3D object matching, object category and action recognition, object category discovery, and texture discovery and analysis, require the ability to match features efficiently in the presence of background clutter and occlusion. In order to improve matching robustness and accuracy [...]
Adaptive Model-Predictive Motion Planning for Navigation in Complex Environments
Event Location: Newell Simon Hall 1305Abstract: Outdoor mobile robot motion planning and navigation is a challenging problem in artificial intelligence. The search space density and dimensionality, system dynamics and environmental interaction complexity, and the perceptual horizon limitation all contribute to the difficultly of this problem. It is hard to generate a motion plan between arbitrary [...]
Modeling Illumination for Scene Recovery through the Motion, Occlusion and Strobing of Light-Sources
Event Location: Newell Simon Hall 1305Abstract: Recent display applications for entertainment and business have made available new types of illumination using LEDs, DMDs and LCDs, which are bright, energy efficient and cheap. Some of these devices are programmable and allow spatio-temporal control of the emitted light rays. With the advent of such digital light-sources, illumination [...]
Multi-robot Coordination in Domains with Intra-path Constraints
Event Location: Newell Simon Hall 1305Abstract: Many applications require teams of robots to cooperatively execute tasks. Among these domains are those in which successful coordination must respect intra-path constraints, which are constraints that occur on the paths of agents and affect route planning. One such domain is disaster response with intra-path constraints, a compelling application [...]
Learning in Modular Systems
Planning to Fail: Incorporating Reliability into Design and Mission Planning for Mobile Robots
Event Location: Newell Simon Hall 1305Abstract: Current mobile robots generally fall into one of two categories as far as reliability is concerned -- highly unreliable, or very expensive. Most fall into the first category, requiring teams of graduate students or staff engineers to coddle them in the days and hours before a brief demonstration. The [...]
Learning Latent Variable and Predictive Models of Dynamical Systems
Event Location: Newell Simon Hall 3305Abstract: A variety of learning problems in robotics, computer vision and other areas of artificial intelligence can be construed as problems of learning statistical models for dynamical systems from sequential observations. Good dynamical system models allow us to represent and predict observations in these systems, which in turn enables applications [...]