|本期目录/Table of Contents|

[1]吴 坤,刘 玮*,李 爽,等.一种动态环境下多Agent的协作方法[J].武汉工程大学学报,2017,39(02):186-192.[doi:10. 3969/j. issn. 1674?2869. 2017. 02. 015]
 WU Kun,LIU Wei*,LI Shuang,et al.A Multi-Agent Cooperation Method in Dynamic Environment[J].Journal of Wuhan Institute of Technology,2017,39(02):186-192.[doi:10. 3969/j. issn. 1674?2869. 2017. 02. 015]
点击复制

一种动态环境下多Agent的协作方法(/HTML)
分享到:

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
39
期数:
2017年02期
页码:
186-192
栏目:
机电与信息工程
出版日期:
2017-05-04

文章信息/Info

Title:
A Multi-Agent Cooperation Method in Dynamic Environment
作者:
吴 坤12刘 玮12*李 爽12王 晶12
1. 武汉工程大学计算机科学与工程学院,湖北 武汉 430205;2. 智能机器人湖北省重点实验室(武汉工程大学),湖北 武汉 430205
Author(s):
WU Kun12 LIU Wei12* LI Shuang12 WANG Jing12
1.School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China;2. Hubei Key Laboratory of Intelligent Robot (Wuhan Institute of Technology), Wuhan 430205,China
关键词:
动态环境MAS多Agent协作连续规划MA-PDDL
Keywords:
dynamic environment multi-agent system multi-agent cooperation continual planning MA-PDDL
分类号:
TP242
DOI:
10. 3969/j. issn. 1674?2869. 2017. 02. 015
文献标志码:
A
摘要:
对动态环境下多Agent系统中Agent的协作问题进行了研究,提出了一种基于连续规划的动态环境下多Agent协作方法. 首先,在MA-PDDL的语法上进行了改进,通过一个自定义的函数使其能够描述连续规划方法;然后,提出了一种基于扩展的MA-PDDL的连续规划算法,能够处理动态环境在系统中所造成的不确定性;最后,实现了扩展的MA-PDDL的解析方法,解析的结果能够用于模拟Agent执行任务的过程. 选取了医疗垃圾无人运输场景进行实验,成功模拟了整个实验场景的运行过程,验证了方法的可行性.
Abstract:
A multi-agent cooperation method was proposed based on multi-agent system continual planning in dynamic environment. First, the Multi-Agent Planning Domain Definition Language (MA-PDDL) was extended for describing the continual planning method by a user-defined function. Then, a continual planning algorithm based on extended MA-PDDL was proposed to deal with the uncertainty. Finally, a parsing method of the extended MA-PDDL was implemented, which simulated how agents execute tasks. The method successfully simulates the execution process of automated cart transportation in hospital, which validates its feasibility.

参考文献/References:

[1] SMITH R G. The contract net protocol: high-level communication and control in a distributed problem solver[J]. IEEE Transactions on Computers, 1980, 29(12):1104-1113. [2] JENNINGS N R. Commitments and conventions: the foundation of coordination in multi-agent systems[J]. Knowledge Engineering Review,1993,8(3):223-250.[3] NII P. The blackboard model of problem solving[J]. AI Magazine, 1986, 7(2):38-53. [4] 林琳, 刘锋. 基于改进合同网协议的多Agent协作模型[J]. 计算机技术与发展, 2010, 20(3):71-75. LIN L, LIU F. A multi-agent cooperation model based on improved contract net protocol[J]. Computer Technology and Development, 2010, 20(3):71-75. [5] 唐贤伦, 李亚楠, 樊峥. 未知环境中多Agent自主协作规划策略[J]. 系统工程与电子技术, 2013, 35(2):345-349. TANG X L, LI Y N, FAN Z. Multi-agent autonomous cooperation planning strategy in unknown environment[J]. System Engineering and Electronics, 2013, 35(2):345-349. [6] 宋泾舸, 查建中, 陆一平. 智能规划研究综述——一个面向应用的视角[J]. 智能系统学报, 2007, 2(2):18-25. SONG J G, CHA J Z, LU Y P. Survey on AI planning research——an application-oriented perspective[J]. CAAI Transactions on Intelligent Systems, 2007, 2(2):18-25. [7] CHIEN S,KNIGHT R,STECHERT A, et al. Integrated planning and execution for autonomous spacecraft[J]. IEEE Aerospace and Electronic Systems Magazine, 2009, 24(1):23-30. [8] IZZO D, PETTAZZI L. Autonomous and distributed motion planning for satellite swarm[J]. Journal of Guidance Control and Dynamics, 2015, 30(2):449-459.[9] 张彦铎, 李哲靖, 鲁统伟. 机器人世界杯足球锦标赛中多机器人对目标协同定位算法的改进[J]. 武汉工程大学学报, 2013, 35(2):69-73. ZHANG Y D, LI Z J, LU T W. Improvements of collaborative localization algorithm of multi-robot on target in ROBOCUP[J]. Journal of Wuhan Institute of Technology, 2013, 35(2):69-73. [10] 鲁统伟, 林芹, 李熹,等. 记忆运动方向的机器人避障算法[J]. 武汉工程大学学报, 2013, 35(4):66-71. LU T W, LIN Q, LI X, et al. Obstacle avoidance algorithm of robot based on recording move direction[J]. Journal of Wuhan Institute of Technology, 2013, 35(4):66-71. [11] 张彦铎, 葛林凤. 一种新的基于MMAS的机器人路径规划方法[J]. 武汉工程大学学报, 2009, 31(5):76-79. ZHANG Y D, GE L F. A novel method for robot’s path planning based on and max-min ant system[J]. Journal of Wuhan Institute of Technology, 2009, 31(5):76-79. [12] 林川. 基于PDDL的Web服务自动组合的描述[J]. 计算机应用与软件, 2008, 25(1):138-139. LIN C. Describition of automatic web services composition based on PDDL[J]. Computer Applications and Software, 2008, 25(1):138-139. [13] FIKES R E, NILSSON N J. Strips: a new approach to the application of theorem proving to problem solving[J]. Artificial intelligence, 1971, 2:608-620.[14] MALIK G, HOWE A, KNOBLOCK C, et al. PDDL-the planning domain definition language, Technical Report CVC TR-98-003/DCS TR-1165[R]. Connecticut:Yale Center for Computational Vision and Control, 1998.[15] KOVACS D L. A multi-agent extension of PDDL3.1[C]// The Association for the Advancement of Artificial Intelligence(AAAI). Workshop on the International Planning Competition, ICAPS-2012. Atibaia:AAAI Press, 2012:19-27.[16] BRENNER M, NEBEL B. Continual planning and acting in dynamic multiagent environments[J].Autonomous Agents and Multi-agent Systems, 2009, 19(3):297-331.[17] SAVANT AUTOMATION. Automated hospital cart transportation system[EB/OL].(2015-06-15)[2017-04-10].http://www.agvsystems.com/hospital- carts.

相似文献/References:

备注/Memo

备注/Memo:
-
更新日期/Last Update: 2017-04-25