Student Talks
Distributed Planning for Large Teams
Event Location: NSH 1507Abstract: In many domains, teams of hundreds of agents must cooperatively plan to perform tasks in a complex, uncertain environment. Naively, this requires that each agent take into account every teammates' state, observation, and choice of action when making decisions about its own actions. This results in a huge joint policy space [...]
Object Instance Discovery and Modeling
Event Location: NSH 1109Abstract: This thesis tackles the problem of automatically discovering and modeling objects from a collection of images from the Activities of Daily Living (ADL) environment. I propose an approach that can discover object instances under severe clutter, occlusion, changes of view point, heterogeneity of object appearance and imperfect segmentation. The proposed approach [...]
Low-Altitude Operation of Unmanned Aerial Vehicles
Event Location: NSH 1109Abstract: Currently deployed unmanned aerial vehicles (UAVs) rely on preplanned missions or teleoperation and do not actively incorporate information about obstacles, landing sites, wind, position uncertainty, and other aerial vehicles during online trajectory planning. Prior work has successfully addressed some problems such as obstacle avoidance at slow speeds, or landing at known [...]
Soft Robots for Safe Physical Human Interaction
Event Location: NSH 1507Abstract: Robots that can operate in human environments in a safe and robust manner would be of tremendous benefit to society in general, due to their immense potential as assistance providers to humans. However, robots to this day have seen limited application outside of the industrial setting in environments such as homes [...]
Understanding and Recreating Visual Appearance Under Natural Illumination
Event Location: GHC 4405Abstract: The appearance of an outdoor scene is determined to a great extent by the prevailing illumination conditions. However, most practical computer vision applications treat illumination more as a nuisance rather than a source of signal. In this dissertation, we suggest that we should instead embrace illumination, even in the challenging, uncontrolled [...]
Exploring bounded optimal coordination for heterogeneous teams with cross-schedule dependencies
Event Location: GHC 6501Abstract: Many domains, such as emergency assistance, agriculture, construction, and planetary exploration, will increasingly require effective coordination of teams of robots and humans to accomplish a collection of spatially distributed heterogeneous tasks. Such coordination problems range from those that require loosely coordinated teams in which agents independently perform their assigned tasks, to [...]
Cross-cultural believability of robot characters
Event Location: NSH 1507Abstract: Believability of characters is an objective in literature, theater, animation, film, and other media. In human-computer interaction, believability of on-screen agents improves perceptual and behavioral responses to the character. Social scientists refer to this phenomenon as homophily---humans tend to associate and bond with similar others. In this thesis proposal, we first [...]
Fast, Dynamic and Graceful Navigation for Balancing Mobile Robots
Event Location: GHC 4405Abstract: Personal mobile robots will soon be operating and closely interacting with us in human environments. They will offer a variety of assistive technologies that will augment our capabilities and enhance our lives. Dynamically stable mobile robots that actively balance can be effective personal mobile robots as they can be tall enough [...]
Visual Subcategories
Event Location: NSH 1305Abstract: This thesis introduces the concept of visual subcategories. Many image understanding tasks such as object detection and image classification are formulated as binary classification problems, where the positive examples are instances (bounding boxes or images) of a specific object or scene category, and negative examples are background patches or images. Due [...]
Thought Recognition: Predicting and Decoding Brain Activity Using the Zero-Shot Learning Model
Event Location: GHC 8102Abstract: Machine learning algorithms have been successfully applied to learning classifiers in many domains such as computer vision, fraud detection, and brain image analysis. Typically, classifiers are trained to predict a class value given a set of labeled training data that includes all possible class values, and sometimes additional unlabeled training data. [...]