Crowd-sourcing is a recent framework in which human intelligence tasks are outsourced to a crowd of unknown people (”workers”) as an open call (e.g., on Amazon’s Mechanical Turk). Crowd-sourcing has become immensely popular with hoards of employers (”requesters”), who use it to solve a wide variety of jobs, such as dictation transcription, content screening, etc. In order to achieve quality results, requesters often subdivide a large task into a chain of bite-sized sub-tasks that are combined into a complex, iterative workflow in which workers check and improve each other’s results.
The goal of this project is to integrate Gaussian process prediction and observation models into Bayes filters. These GP-BayesFilters are more accurate than standard Bayes filters using parametric models. In addition, GP models naturally supply the process and observation noise necessary for Bayesian filters.
The lab's research focuses on understanding the brain using computational models and simulations and applying this knowledge to the task of building intelligent robotic systems and brain-computer interfaces (BCIs). The lab utilizes data and techniques from a variety of fields, ranging from neuroscience and psychology to machine learning and statistics.
Probabilistic planning problems are often modeled as Markov decision
processes (MDPs), which assume that a single action is executed per decision
epoch and that actions take unit time. However, in the real world it is
common to execute several actions in parallel, and the durations of these
actions may differ. We are developing extensions to MDPs that incorporate
these features. In particular, we propose the model of Concurrent MDPs,
which allows simultaneous execution of multiple unit-duration actions at a
time point. We extend this to handle concurrent durative actions with
Being PSPACE-complete, even MDPs that describe relatively simple planning problems often defeat modern solvers by forcing them to run out of physical memory or take unreasonably long to produce a solution. Increasing scalability of techniques for solving MDPs is thus a central research topic in planning under uncertainty, and we address it in multiple ways.
SUPPLE is an application and device-independent system, developed at University of Washington, that automatically generates user interfaces for a wide variety of display devices. SUPPLE uses decision-theoretic optimization to render an interface from an abstract functional specification and an interchangeable device model.
What makes a temporal planning problem challenging? When can these problems be solved by classical planners, and when do they require special processing?
Our study attempts to answer these questions and investigate other fundamental properties of temporal planning. For example, we have divided the temporal planning domains and problems into two categories, temporally simple and temporally expressive, and identified automatic ways to test the temporal expressiveness of a domain.