Browse by Subject "artificial intelligence"

  • Nath, Vishnu (2012-05)
    My research deals with incorporating Artificial Intelligence into a humanoid robot by making a cognitive model of the learning process. The goal is to “teach” a robot to fire a gun by allowing it to make small errors and ...
    untranslated PDF (2MB)Restricted to U of Illinois
  • Swarup, Samarth; Mahmud, M. M. Hassan; Lakkaraju, Kiran; Ray, Sylvian R. (2005-02)
    Cognitive architectures should be designed with learning performance as a central goal. A critical feature of intelligence is the ability to apply the knowledge learned in one context to a new context. A cognitive agent ...
    untranslated PDF (530KB)
  • Sarmiento, Alejandro (2004-12)
    This work addresses the problem of generating a motion strategy for solving a visibility-based task with a mobile robot equipped with sensors. In particular, the problem is to find a static object -- modeled with a probability ...
    untranslated PDF (2MB)
  • Wang, Felix (2011-05)
    In this work, I explore the behaviors and metrics relating to a nonlinear dynamical multi-scale model of associative memory developed by Alex Duda. The model utilizes an ab initio approach with the classic Hodgkin-Huxley ...
    untranslated PDF (2MB)Restricted to U of Illinois
  • Braz, Rodrigo de Salvo (2007-09)
    There has been a long standing division in AI between logical symbolic and probabilistic reasoning approaches. While probabilistic models can deal well with inherent uncertainty in many real-world domains, they operate on ...
    untranslated PDF (839KB)
  • Amir, Eyal; Russell, Stuart (2005-05)
    Filtering denotes any method whereby an agent updates its belief state - its knowledge of the state of the world - from a sequence of actions and observations. In logical filtering, the belief state is a logical formula ...
    untranslated PDF (325KB)
  • Agarwal, Shivani; Roth, Dan (2003-12)
    We develop an approach for automatically learning the optimal feature transformation for a given classification problem. The approach is based on extending the principle of risk minimization (RM), commonly used for learning ...
    untranslated PDF (243KB)
  • Law, Allan (2012-05)
    The aim of this thesis is to provide a simple visual closed loop control method to enable a humanoid robot to reach out towards an object in its visual field in 3D space. To achieve this task, the robot utilizes stereo ...
    untranslated PDF (3MB)Restricted to U of Illinois
  • Yu, Dan (2010-05)
    The iCub is a humanoid robot for the research of cognition. The vision system is one of the most important components of the iCub robot. It provides crucial information pertaining to the surroundings for the rest of its ...
    untranslated PDF (758KB)Restricted to U of Illinois