基于区域博弈的全局视觉2VS2策略改进  

Strategy Improvement of Global Visual 2VS2 Based on Regional Game Analysis

作　　者：王中伟[1] 沈志强[1] 王梅娟[1] Wang Zhongwei Shen Zhiqiang Wang Meijuan(College of Command Information Systems, PLA University of Science ＆ Technology, Nanjing 210007, China)

机构地区：[1]解放军理工大学指挥信息系统学院,南京210007

出　　处：《兵工自动化》2016年第12期89-92,共4页Ordnance Industry Automation

摘　　要：为寻找更加有效的制胜算法,寻求一种基于国际水中机器人大赛全局视觉2VS2项目的有效策略改进方案,笔者将建模思想引入策略实现。首先对赛场进行区域划分,并基于不同区域的威胁程度进行博弈分析,实现策略改进,编写了新的顶球算法策略。实践结果表明:在同等条件下,采用该算法能够更加灵活、有效地采取策略进攻或防守,提高对抗防御能力和进攻进球效率。In order to find a more efficient algorithm, this paper seeks an effective strategy to improve the global visual 2VS2 project based on the international water robot competition. Use model establishment theory into strategy application. First to the field of regional division, the game was analyzed based on the threat degree of different regions, and then the implementation strategy is improved and the new header in the algorithm has been written. Practice has proved that, by using algorithm, it can more flexible and more effectively adopt strategy to attack or defense, which effectively improve the combat capability of defense and offensive efficiency goals.

关 键 词：MURobotSys平台 策略 区域博弈 顶球算法 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]