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.
Advisors: 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