An Architecture for Structured, Concurrent, Real-Time Action

Leon Rubin Barrett

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2010-58
May 11, 2010

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-58.pdf

I present a computational architecture designed to capture certain properties essential to actions, including compositionality, concurrency, quick reactions, and resilience in the face of unexpected events. It uses a structured internal state model and complex inference about the environment to inform decision-making. The properties above are achieved by combining interacting procedural and probabilistic representations, so that the structure of actions is captured by Petri Nets, which are informed by, and affect, a model of the world represented as a Probabilistic Relational Model. I give both a theoretical analysis of the architecture and a demonstration of its use in a simulated robotic environment.

Advisor: Jerome A. Feldman


BibTeX citation:

@phdthesis{Barrett:EECS-2010-58,
    Author = {Barrett, Leon Rubin},
    Title = {An Architecture for Structured, Concurrent, Real-Time Action},
    School = {EECS Department, University of California, Berkeley},
    Year = {2010},
    Month = {May},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-58.html},
    Number = {UCB/EECS-2010-58},
    Abstract = {I present a computational architecture designed to capture certain properties essential to actions, including compositionality, concurrency, quick reactions, and resilience in the face of unexpected events. It uses a structured internal state model and complex inference about the environment to inform decision-making. The properties above are achieved by combining interacting procedural and probabilistic representations, so that the structure of actions is captured by Petri Nets, which are informed by, and affect, a model of the world represented as a Probabilistic Relational Model. I give both a theoretical analysis of the architecture and a demonstration of its use in a simulated robotic environment.}
}

EndNote citation:

%0 Thesis
%A Barrett, Leon Rubin
%T An Architecture for Structured, Concurrent, Real-Time Action
%I EECS Department, University of California, Berkeley
%D 2010
%8 May 11
%@ UCB/EECS-2010-58
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-58.html
%F Barrett:EECS-2010-58