LDRD project final report : hybrid AI/cognitive tactical behavior framework for LVC. Page: 24 of 35
35 p.View a full description of this report.
Extracted Text
The following text was automatically extracted from the image on this page using optical character recognition software:
perception or reactive behaviors, would de-activate a memory element when the duration since
its most recent perception reaches a threshold. Behavior elements associated with specific
contexts might include models that should overrule this default. Even stronger models could
include estimation of data and uncertainty from the most recent perception and additional
knowledge.
The Flexibly Updatable Memory module provides an interface for inserting memory elements,
registering memory element updaters, retrieving active memory elements. Memory elements are
identified by a combination of an attribute identifier and a vector of entity identifiers. These
identifiers can be generated with or without associating them with a string (name). The basic
retrieval function gets all elements with a given attribute identifier and activation over a given
threshold. Each memory element has up to three versions of content: what was perceived, what
is proposed, and what is the current value that can be retrieved. The general part of content
includes activation, the time the content was updated, and the strength of the model that updated
the content. The Flexibly Updatable Memory's update function applies the registered updaters
to memory elements as appropriate. It applies a default decay model to memory elements that
the updaters miss. A memory element updater will not override proposed content set by a
stronger model at the current update time. The data part of memory element content is a
templated data structure, enabling different attributes to have different types. To enable further
generality, there is a simple value template parameter and an estimated value template parameter.
The latter, for example, could include statistical data. We assume that the behavior model
components that interface with the flexible working memory component will consistently
associate attribute identifiers with data types.24
Upcoming Pages
Here’s what’s next.
Search Inside
This report can be searched. Note: Results may vary based on the legibility of text within the document.
Tools / Downloads
Get a copy of this page or view the extracted text.
Citing and Sharing
Basic information for referencing this web page. We also provide extended guidance on usage rights, references, copying or embedding.
Reference the current page of this Report.
Djordjevich, Donna D.; Xavier, Patrick Gordon; Brannon, Nathan Gregory; Hart, Brian E.; Hart, Derek H.; Little, Charles Quentin et al. LDRD project final report : hybrid AI/cognitive tactical behavior framework for LVC., report, January 1, 2012; United States. (https://digital.library.unt.edu/ark:/67531/metadc839509/m1/24/: accessed July 16, 2024), University of North Texas Libraries, UNT Digital Library, https://digital.library.unt.edu; crediting UNT Libraries Government Documents Department.