PhD Thesis Defense

Event Location: GHC 4405Abstract: The typical approach to learning based vision has been that for each individual application, classifiers or detectors are learned anew from annotated training data for each specific task. However, the classifiers trained in this way tend to be brittle and highly specialized to the datasets from which they are derived, making [...]

Event Location: NSH 1507Abstract: This thesis tackles the problem of automatically discovering objects from a collection of images from the Activities of Daily Living (ADL) environment. We contribute, 1) a framework for discovering object instances under severe clutter, occlusion, changes of view point, heterogeneity of object appearance and imperfect segmentation; 2) a data-driven approach for [...]

Event Location: GHC 4405Abstract: Time-lapse live cell imaging has been increasingly employed by biological and biomedical researchers to understand the underlying mechanisms in cell physiology and development by investigating behavior of cells. This trend has led to a huge amount of image data, the analysis of which becomes a bottleneck in related research. Consequently, how [...]

Event Location: GHC 4405Abstract: Believability of characters is an objective in literature, theater, animation, film, and other media. Virtual characters, believable as sharing their ethnic background with users, improve their perception of the character and, sometimes, even their task performance. Social scientists refer to this phenomenon as homophily---humans tend to associate and bond with similar [...]

Event Location: GHC 8102Abstract: Planetary excavators face unique and extreme engineering constraints relative to terrestrial counterparts. In space missions mass is always at a premium because it is the main driver behind launch costs. Lightweight operation, due to low mass and reduced gravity, hinders excavation and mobility by reducing the forces a robot can effect [...]

Event Location: NSH 1305Abstract: This talk is about improving the process of designing controllers for humanoid robots. It describes tools we designed that enable us to iterate faster when experimenting with control systems that aggregate multiple model based sub-controllers. Many model based humanoid controllers can be considered approximations to a fully general, but computationally intractable, [...]

Event Location: NSH 1305Abstract: Sequential prediction problems arise commonly in many areas of robotics and information processing: e.g., predicting a sequence of actions over time to achieve a goal in a control task, interpreting an image through a sequence of local image patch classifications, or translating speech to text through an iterative decoding procedure. Learning [...]

Event Location: NSH 1305Abstract: Extracting a rich representation of an environment from visual sensor readings can benefit many tasks in robotics, e.g., path planning, mapping, and object manipulation. While important progress has been made, it remains a difficult problem to effectively parse entire scenes, i.e., to recognize semantic objects, man-made structures, and landforms. This process [...]

Event Location: NSH 1305Abstract: In this thesis, we study the topic of detecting object instances which lack discriminative features in scenes with severe clutter and occlusions. Our work focuses on the three key areas: (1) objects that have ambiguous features, (2) objects where discriminative point-based features cannot be reliably extracted, and (3) occlusions. Current approaches [...]

Event Location: NSH 1305Abstract: This thesis presents a series of planners and algorithms for manipulation in cluttered human environments. The focus is on using physics-based predictions, particularly for pushing operations, as an effective way to address the manipulation challenges posed by these environments.  We introduce push-grasping, a physics-based action to grasp an object first by pushing it and [...]