SymAware: 状況認識を備えた信頼性の高いマルチエージェントシステムのためのソフトウェア開発フレームワーク
SymAware: A Software Development Framework for Trustworthy Multi-Agent Systems with Situational Awareness
エージェント間の状況認識の計算・共有・制御を支援するマルチエージェントシミュレーション用ソフトウェアフレームワークを提案し、3つのケーススタディで有効性と効率性を検証した。
著者: Ernesto Casablanca, Zengjie Zhang, Gregorio Marchesini, Sofie Haesaert, Dimos V. Dimarogonas, Sadegh Soudjani
分類: cs.RO
原文アブストラクト
Developing trustworthy multi-agent systems for practical applications is challenging due to the complicated communication of situational awareness (SA) among agents. This paper showcases a novel efficient and easy-to-use software framework for multi-agent simulation, named SymAware which provides a rich set of predefined data structures to compute, store, and communicate SA for agents. It also provides an abstract interface for the agents to compute their control inputs taking into account the awareness of the situation, knowledge, and risk of surrounding agents. Besides, utilizing a cluster of specialized components, SymAware hides the heavy computation of physical rendering and communication interfacing of simulation engines behind the control threads, resulting in high implementation efficiency in bridging the gap between conceptual prototyping and practical applications. Three multi-agent case studies are used to validate the efficacy and efficiency of this software framework.
