摘要
自主机器人车辆具有智能性和快速反应的特点，而在精确推理和实时性之间寻求最佳折衷是体系结构的关键．文中提出基于分布式多Ａｇｅｎｔ系统的自组织体系结构ＩＲＡＳＯ，Ａｇｅｎｔ之间动态组合以适应环境变化，公告板系统评估环境势态和指导Ａｇｅｎｔ组织，同时设计了Ａｇｅｎｔ协调工作的空间和时间模型．基于ＴＣＰ／ＩＰ的计算联通域为异质分布式多Ａｇｅｎｔ的协作运行提供支持．仿真结果表明该结构在智能性和实时性达到了期望特性．
Intelligence and responsiveness are the two issues in architectures of autonomous robot vehicles. The key is how to make good tradeoff between deliberative reasoning and fast reaction. This paper explores a type of architecture, which is based on a distributed multi agent system. Agents can be dynamically reorganized to suit the various environments. A bulletin board system plays the role of assessing the surrounding situation and organization of the agents. Several models are designed to coordinate agents both in temporal and spatial.The computing coherent field based on TCP/IP supports agents to work together. The simulation shows that the architecture is desirable both in intelligence and responsibility.
出处
《计算机研究与发展》
EI
CSCD
北大核心
1999年第7期776-782,共7页
Journal of Computer Research and Development
基金
国防科工委"九五"攻关项目基金
关键词
自主机器人
人工智能
自组织结构
IRASO
仿真
autonomous robot vehicle, multi agent system, distributed artificial intelligence, bulletin board system, situation assessment
