Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: artificial agent

Sortuj według:

Ogranicz wyniki do:

Matching Observed with Empirical Reality - What you see is what you get?

100%

Kurbalija V. , Ivanović M. , von Bernstorff C. , Nachtwei J. , Burkhard H.-D.

Fundamenta Informaticae

2014

tom Vol. 129, nr 1/2

133--147

This paper outlines the primary steps to investigate if artificial agents can be considered as true substitutes of humans. Based on a Socially augmented microworld (SAM) human tracking behavior was analyzed using time series. SAM involves a team of navigators jointly steering a driving object along different virtual tracks containing obstacles and forks. Speed and deviances from track are logged, producing high-resolution time series of individual (training) and cooperative tracking behavior. In the current study 52 time series of individual tracking behavior on training tracks were clustered according to different similarity measures. Resulting clusters were used to predict cooperative tracking behavior in fork situations. Results showed that prediction was well for tracking behavior shown at the first and, moderately well at the third fork of the cooperative track: navigators switched from their trained to a different tracking style and then back to their trained behavior. This matches with earlier identified navigator types, which were identified on visual examination. Our findings on navigator types will serve as a basis for the development of artificial agents, which can be compared later to behavior of human navigators.

Cooperating agents approach to task execution planning

63%

Madejski J.

Journal of Achievements in Materials and Manufacturing Engineering

2009

tom Vol. 37, nr 1

52-56

Purpose: The aim of the paper is to investigate the behaviour of the cooperating agents having to agree task execution. Design/methodology/approach: A heuristic method is proposed for scheduling tasks that should be carried out by a group of agents. An important issue is that the agents have to complete their negotiations to commit to the task and carry out it in real time. This task was solved by splitting the problem solving into two layers which make it possible to obtain the rough solutions first and further improve them next as much as possible. Findings: The first layer proposed refers to tasks assigned static priorities and its goal is to meet the real time requirements. Next, the agents can proceed to obtain the optimized solution, provided there is time to do it before the task execution has to begin. Research limitations/implications: Analysis of the negotiations procedure was done and model examples were worked out to develop a planning system based on these design requirements. Practical implications: Implementing the real time task execution planning in artificial agents brings them closer to the job shop floor real life requirements, making it possible to develop software entities mimicking reactions of humans and capable of joint task execution planned on the fly as needed. Originality/value: Analysis of the real time task planning and execution of groups of agents.