Intelligent automatic manoeuvring mechanism for computer generated forces using predictive multi-step fuzzy inference system

The purpose of this paper is to develop an intelligent automatic maneuvering mechanism for computer generated forces (CGF). The proposed CGF can take actions similar to a human pilot to gain an advantageous status over the enemy target using the intelligent automatic maneuvering mechanism. The mecha...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shang-Jeng Tsai, Tsung-Ying Sun, Shih-Hsiang Ting
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The purpose of this paper is to develop an intelligent automatic maneuvering mechanism for computer generated forces (CGF). The proposed CGF can take actions similar to a human pilot to gain an advantageous status over the enemy target using the intelligent automatic maneuvering mechanism. The mechanism will produce the best multi-step tactics combination (MSTC) for the CGF in an air combat environment. The MSTC is composed of CGF's decision space. In this paper, based on our previous work, we propose a predictive multi-step fuzzy inference system (PMSFIS) as the automatic maneuvering mechanism for CGF, which incorporates and mimics human thinking capability and the maximum capacity of CGF. Before PMSFIS executes the fuzzy inference system (FIS) process, it will generate a list of MSTC, and allows CGF to predict its future posture corresponding to the list of MSTC. This paper assumes that CGF can accurately predict an enemy target's future position, then PMSFIS applies the predicted data to generate the best MSTC. We verify the proposed algorithm with a set of fighter flying data that is used as the enemy target's flying trajectory. The simulation of the proposed algorithm shows that PMSFIS will enable CGF to obtain the best status in an air combat environment and improve the performance of our previous work.
ISSN:1062-922X
2577-1655
DOI:10.1109/ICSMC.2007.4413911