scholarly journals Automatic Generation of Agent Behavior Models from Raw Observational Data

2015 ◽  
pp. 121-132 ◽  
Author(s):  
Bridgette Parsons ◽  
José M. Vidal ◽  
Nathan Huynh ◽  
Rita Snyder
Keyword(s):  
Observational Data ◽  
Automatic Generation ◽  
Agent Behavior ◽  
Behavior Models

AUTOMATIC GENERATION OF GAZE AND GESTURES FOR DIALOGUES BETWEEN EMBODIED CONVERSATIONAL AGENTS

2008 ◽  
Vol 02 (01) ◽  
pp. 71-90 ◽  
Author(s):  
WERNER BREITFUSS ◽  
HELMUT PRENDINGER ◽  
MITSURU ISHIZUKA
Keyword(s):  
Verbal Behavior ◽  
Contextual Information ◽  
Eye Gaze ◽  
Automatic Generation ◽  
Gaze Behavior ◽  
Conversational Agents ◽  
Agent Behavior ◽  
Face To Face ◽  
Modal Behavior

In this paper we introduce a system that automatically adds different types of non-verbal behavior to a given dialogue script between two virtual embodied agents. It allows us to transform a dialogue in text format into an agent behavior script enriched by eye gaze and conversational gesture behavior. The agents' gaze behavior is informed by theories of human face-to-face gaze behavior. Gestures are generated based on the analysis of linguistic and contextual information of the input text. The resulting annotated dialogue script is then transformed into the Multimodal Presentation Markup Language for 3D agents (MPML3D), which controls the multi-modal behavior of animated life-like agents, including facial and body animation and synthetic speech. Using our system makes it very easy to add appropriate non-verbal behavior to a given dialogue text, a task that would otherwise be very cumbersome and time consuming. In order to test the quality of gaze generation, we conducted an empirical study. The results showed that by using our system, the naturalness of the agents' behavior was not increased when compared to randomly selected gaze behavior, but the quality of the communication between the two agents was perceived as significantly enhanced.

A Flexible System for Automatic Generation of Special Purpose Dichotomous Keys, and Its Application to Australian Grass Genera

1972 ◽  
Vol 20 (3) ◽  
pp. 331 ◽  
Author(s):  
L Watson ◽  
P Milne
Keyword(s):  
Data Base ◽  
Observational Data ◽  
Leaf Morphology ◽  
Automatic Generation ◽  
Taxonomic Group ◽  
Flexible System ◽  
World Level ◽  
Single Data ◽  
Fruit Structure

The key-generating program KEYGEN has been incorporated in a flexible system whereby special purpose dichotomous keys can be produced rapidly and cheaply from a single data base. The system is applicable to any taxonomic group for which suitable observational data are available. It is currently being applied to Australian grass genera, for which data are now available on 274 attributes representing 120 aspects of leaf morphology and anatomy, inflorescence form, spikelet, flower, and fruit structure. Grass genera are being recorded for variation at world level so that the data can be used (and if necessary extended) in order to make keys for other regions. Examples are given of early efforts at 'conventional' and 'vegetative-anatomical' special purpose keys, generated from the data via the system described here.

scholarly journals Trust and Normative Control in Multi-Agent Systems

2013 ◽  
Vol 1 (1) ◽  
pp. 43-52
Author(s):  
Joana Urbano ◽  
Henrique Lopes Cardoso ◽  
Ana Paula Rocha ◽  
Eugénio Oliveira
Keyword(s):  
Negotiation Process ◽  
Dyadic Relationships ◽  
Multi Agent Systems ◽  
Agent Behavior ◽  
Agent Systems ◽  
Economics Literature ◽  
Multi Agent ◽  
Behavior Models ◽  
Selection Of

Despite relevant insights from socio-economics, little research in multi-agent systems has addressed the interconnections between trust and normative notions such as contracts and sanctions. Focusing our attention on scenarios of betrayal, in this paper we combine the use of trust and sanctions in a negotiation process. We describe a scenario of dyadic relationships between truster agents, which make use of trust and/or sanctions, and trustee agents, characterized by their ability and integrity, which may influence their attitude toward betrayal. Both agent behavior models are inspired in socio-economics literature. Through simulation, we show the virtues and shortcomings of using trust, sanctions, and a combination of both in processes of selection of partners.

MODEL IDENTIFICATION OF A SERVO-TRACKING SYSTEM USING FUZZY CLUSTERING

1999 ◽  
Vol 07 (04) ◽  
pp. 337-346
Author(s):  
ERIC M. NGUYEN ◽  
NADIPURAM R. PRASAD
Keyword(s):  
Least Squares ◽  
Observational Data ◽  
Fuzzy Clustering ◽  
Least Squares Method ◽  
Tracking System ◽  
Model Identification ◽  
Automatic Generation ◽  
Non Linear ◽  
Servo Tracking ◽  
Takagi Sugeno

This paper investigates the use of Fuzzy Clustering as a means for model identification of a complex and highly non-linear servo-tracking system when only observational data is available. The use of Fuzzy Clustering facilities automatic generation of rules and its antecedent parameters. The consequent of the model is then formulated in the form of Takagi, Sugeno and Kang (TSK), and its parameters determined by the Least Squares Method (LSM).

Current status of special planetary and lunar theories and ephemerides

1966 ◽  
Vol 25 ◽  
pp. 266-267
Author(s):  
R. L. Duncombe
Keyword(s):  
Observational Data ◽  
Current Status ◽  
Numerical Errors

An examination of some specialized lunar and planetary ephemerides has revealed inconsistencies in the adopted planetary masses, the presence of non-gravitational terms, and some outright numerical errors. They should be considered of temporary usefulness only, subject to subsequent amendment as required for the interpretation of observational data.

July 11, 1991 Eclipse Corona Photometry by the Results of Electropolarimetric and CCD-Matrix Observations

1994 ◽  
Vol 144 ◽  
pp. 567-569
Author(s):  
V. Kulidzanishvili ◽  
D. Georgobiani
Keyword(s):  
Solar Corona ◽  
Observational Data ◽  
Solar Limb ◽  
Ccd Matrix

AbstractThe observational data of July 11, 1991 eclipse solar corona obtained by both electropolarimeter (EP) and CCD-matrix were processed. Using these data, the solar corona photometry was carried out. The results of EP data are compared with the ones of CCD data. It must be noted here that the CCD data give us only characteristics of the inner corona, while the EP data show the features of both the inner and middle corona up to 4R⊙. Standard flattening indexϵis evaluated from both data. The dependence of the flattening index on the distance from the solar limb is investigated. The isophotes in Na and Ca lines are plotted. Based on these data some ideas and conclusions on the type of the solar corona are presented.

On The Radii of Ap Stars

1976 ◽  
Vol 32 ◽  
pp. 49-55 ◽  
Author(s):  
F.A. Catalano ◽  
G. Strazzulla
Keyword(s):  
Observational Data ◽  
Line Width ◽  
Main Sequence ◽  
Main Sequence Stars ◽  
Ap Stars

SummaryFrom the analysis of the observational data of about 100 Ap stars, the radii have been computed under the assumption that Ap are main sequence stars. Radii range from 1.4 to 4.9 solar units. These values are all compatible with the Deutsch's period versus line-width relation.

Sign in / Sign up

Export Citation Format

Share Document