Browsing by Subject "artificial intelligence"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item A framework for knowledge-based team training(2009-06-02) Miller, Michael ScottTeamwork is crucial to many disciplines, from activities such as organized sports to economic and military organizations. Team training is difficult and as yet there are few automated tools to assist in the training task. As with the training of individuals, effective training depends upon practice and proper training protocols. In this research, we defined a team training framework for constructing team training systems in domains involving command and control teams. This team training framework provides an underlying model of teamwork and programming interfaces to provide services that ease the construction of team training systems. Also, the framework enables experimentation with training protocols and coaching to be conducted more readily, as team training systems incorporating new protocols or coaching capabilities can be more easily built. For this framework (called CAST-ITT) we developed an underlying intelligent agent architecture known as CAST (Collaborative Agents Simulating Teamwork). CAST provides the underlying model of teamwork and agents to simulate virtual team members. CAST-ITT (Intelligent Team Trainer) uses CAST to also monitor trainees, and support performance assessment and coaching for the purposes of evaluating the performance of a trainee as a member of a team. CAST includes a language for describing teamwork called MALLET (Multi-Agent Logic Language for Encoding Teamwork). MALLET allows us to codify the behaviors of team members (both as virtual agents and as trainees) for use by CAST. In demonstrating CAST-ITT through an implemented team training system called TWP-DDD we have shown that a team training system can be built that uses the framework (CAST-ITT) and has good performance and can be used for achieving real world training objectives.Item Cybernetic automata: An approach for the realization of economical cognition for multi-robot systems(2009-05-15) Mathai, Nebu JohnThe multi-agent robotics paradigm has attracted much attention due to the variety of pertinent applications that are well-served by the use of a multiplicity of agents (including space robotics, search and rescue, and mobile sensor networks). The use of this paradigm for most applications, however, demands economical, lightweight agent designs for reasons of longer operational life, lower economic cost, faster and easily-verified designs, etc. An important contributing factor to an agent?s cost is its control architecture. Due to the emergence of novel implementation technologies carrying the promise of economical implementation, we consider the development of a technology-independent specification for computational machinery. To that end, the use of cybernetics toolsets (control and dynamical systems theory) is appropriate, enabling a principled specifi- cation of robotic control architectures in mathematical terms that could be mapped directly to diverse implementation substrates. This dissertation, hence, addresses the problem of developing a technologyindependent specification for lightweight control architectures to enable robotic agents to serve in a multi-agent scheme. We present the principled design of static and dynamical regulators that elicit useful behaviors, and integrate these within an overall architecture for both single and multi-agent control. Since the use of control theory can be limited in unstructured environments, a major focus of the work is on the engineering of emergent behavior. The proposed scheme is highly decentralized, requiring only local sensing and no inter-agent communication. Beyond several simulation-based studies, we provide experimental results for a two-agent system, based on a custom implementation employing field-programmable gate arrays.Item Visualization of Ant Pheromone Based Path Following(2010-07-14) Sutherland, Benjamin T.This thesis develops a simulation and visualization of a path finding algorithm based on ant pheromone paths created in 3D space. The simulation is useful as a demonstration of a heuristic approach to NP-complete problems and as an educational tool for demonstrating how ant colonies gather food. An interactive real time 3D visualization is built on top of the simulation. A graphical user interface layer allows user interaction with the simulation and visualization.