Studies on Adaptive and Learning Agents on Production System

生产系统自适应学习Agent研究

• 批准号: 13650141
• 负责人: FURUKAWA Masashi
• 金额: $ 1.79万
• 依托单位: Asahikawa National College of Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2001
• 资助国家: 日本
• 起止时间: 2001 至 2003
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-13650141/
• 关键词: Autonomous agent; Learning agent; Autonomous Decentralized System; Production system; AGV; Path planning; Self-organization; マルチエージェントシステム; 機械学習; Q学習; 適応システム

In order to realize an agent system with adaptive and learning functions on a production system, it is practically requested to develop the agent system with a low level intelligence rather than a high level intelligence. I have developed the agent system with adaptive and learning function from a viewpoint of the high level intelligence for the last two years. However, a learning method I have adopted needs a large capacity of memory and highly computing speed. The agent system with the low level intelligence means that (1) the agents concern his/her local circumstances, (2) they communicate with other agents within the local circumstances, (3) they make their decision what to do, and (4) the whole system attains its purpose. To develop such an agent system, a self-organizing maps (SOM) concept is introduced. SOM consists of neurons and their synapses. Its neurons proceed to organize themselves toward the arranged system by only updating their local synapses. When we regard the neuron … More s and synapses as production agents and their associated information, respectively, it becomes possible to construct the agent system with the adaptable low-level intelligence. This concept is applied to a vehicle path-planning problem (VPM) and a vehicle delivery-planning problem (VDPP) in a virtual factory.On VDP and VDPP, vehicles are regarded as the agents. SOM requests some topology relation between the agents. On VDP a straight-line topology is adopted for this purpose. When a start and goal locations are given to the agents, many agents are located in the factory at random and they have the straight-line topology relation. It is recognized that SOM makes intersection paths around the start and goal point locations. Then, multi-knot concept, which is used in the B-spline interpolation method, is employed to overcome this defect. Numerical experiments verify that the agents only exchange their information and finally generates a near optimum vehicle path. As for VDPP, the agents are located in the factory at random and multiple loops are set as their topology among them. Several agents are located and fixed at the delivery center location on each loop just as a multi-knot. Numerical experiments verify that the agents construct nearly equal-length loops as the vehicle paths. These results are presented in JSME and JSPE annual conference in Japan. Less

为了在产生式系统上实现具有自适应和学习功能的智能体系统，现实要求开发具有低智能性而不是高智能性的智能体系统。在过去的两年里，我从高水平智能的角度开发了具有自适应和学习功能的代理系统。然而，我采用的一种学习方法需要大容量的内存和很高的计算速度。低水平智能的智能体系统是指(1)智能体关注自己的当地情况，(2)在当地环境中与其他智能体进行交流，(3)他们做出自己的决定，(4)整个系统达到目的。为了开发这样的代理系统，引入了自组织映射(SOM)的概念。SOM由神经元及其突触组成。它的神经元只通过更新它们的局部突触来朝着排列的系统进行自我组织。当我们考虑到神经元…更多的S和突触分别作为生产智能体及其关联信息，使得构建具有适应性的低级智能的智能体系统成为可能。将这一概念应用于虚拟工厂中的车辆路径规划问题(VPM)和车辆交付规划问题(VDPP)，在VDP和VDPP中，车辆被视为代理人。SOM要求代理之间存在某种拓扑关系。在VDP上，为此采用的是直线拓扑。当智能体的起始位置和目标位置给定时，许多智能体随机分布在工厂中，它们之间具有直线拓扑关系。人们认识到，SOM在起点和目标点位置周围建立相交路径。然后，利用B-Spline插值法中的多节点概念来克服这一缺陷。数值实验证明，多个智能体之间只交换信息，最终生成一条接近最优的车辆路径。对于VDPP，代理随机分布在工厂中，并在它们之间设置多个环路作为它们的拓扑。几个代理被定位并固定在每个环路上的交付中心位置，就像一个多结点。数值实验证明，这些智能体构建了与车辆路径几乎相同长度的环路。这些成果在日本的JSME和JSPE年会上公布。较少

项目成果

木下正博, 渡辺美知子, 川上敬, 古川正志, 嘉数侑昇: "複数ブロックエージェントの自律行動獲得に関する研究"精密工学会誌. 68巻10号. 1303-1308 (2002)

Masahiro Kinoshita、Michiko Watanabe、Takashi Kawakami、Masashi Furukawa、Yusuke Kakazu：“多块智能体的自主行为获取研究”日本精密工程学会杂志第 68 卷，第 1303-1308 期（2002 年）。

古川正志, 渡辺美知子, 池田将晴, 木下正博, 嘉数侑昇: "Q学習によるAGVの移動物体衝突回避"日本機械学会論文集第C編. 69. 215-220 (2003)

Masashi Furukawa、Michiko Watanabe、Masaharu Ikeda、Masahiro Kinoshita、Yusuke Kakazu：“使用 Q 学习避免 AGV 中移动物体的碰撞” 日本机械工程师学会会刊，C 卷，69. 215-220 (2003)

M.Furukawa, M.Watanabe, M.Kinoshita, Y.Kakazu: "A Mathematical Model for Learning Agents on a Multi-agent System"Computational Intelligence in Robotics and Automation (CIRA2003), ISBN:0-7803-7866-0. 1369-1374 (2003)

M.Furukawa、M.Watanabe、M.Kinoshita、Y.Kakazu：“多智能体系统上学习智能体的数学模型”机器人与自动化中的计算智能（CIRA2003），ISBN：0-7803-7866-0。

Masashi Furukawa, Michiko Watanabe, Masaharu Ikeda, Masahiro Kinoshita, Yukinori Kakazu: "Collision Avoidance for Moving Objects by Use of Q-Learning"J.of JSME. 69-680, Volume C. 215-220 (2003)

Masashi Furukawa、Michiko Watanabe、Masaharu Ikeda、Masahiro Kinoshita、Yukinori Kakazu：“使用 Q-Learning 来避免移动物体的碰撞”J.of JSME。

Masashi Furukawa, Michiko Watanabe, Masahiro Kinoshita, Yukinori Kakazu: "A Mathematical Model for Learning Agents on a Multi-agent System"Computational Intelligence in Robotics and Automation (CIRA2003), ISBN:0-7803-7866-0. 1369-1374 (2003)

Masashi Furukawa、Michiko Watanabe、Masahiro Kinoshita、Yukinori Kakazu：“多智能体系统上学习智能体的数学模型”机器人与自动化中的计算智能 (CIRA2003)，ISBN：0-7803-7866-0。