基于隐马尔可夫模型的机器人足球赛场态势评估  

HMM Based Situation Assessment for Robot Soccer

作　　者：李长江[1] 李孝安[1] 

机构地区：[1]西北工业大学计算机学院,西安710129

出　　处：《科学技术与工程》2012年第4期789-793,共5页Science Technology and Engineering

摘　　要：针对机器人足球赛场态势评估问题,提出一种基于隐马尔可夫模型(HMM)的机器人足球赛场态势评估模型。通过对赛场信息进行提取和量化,抽象出7个相关态势因素,作为HMM模型的输入数据。通过采用改进的Bauw-Welch算法优化HMM的参数,从而获得赛场态势评估结果。实验结果表明,所提出的方法能较好地满足赛场实时性和准确性的要求,可以为球场上对应策略的变更提供及时、可靠的依据。For robot soccer stadium situation assessment problem,a novel model of robot soccer stadium situation assessment based on the Hidden Markov Model(HMM) is proposed.First,seven key factors through the characteristics of game environment as the inputs of HMM are abstracted.And then the parameters of HMM using the improved Bauw-Welch algorithm based on the existing experimental database are optimized.Finally,the result of the model is got.The experiment result shows model can satisfy real-time and accuracy demands and provide timely and reliable references for the change of the corresponding strategy for current soccer situation.

关 键 词：机器人足球 态势评估 隐马尔可夫模型 Bauw-Welch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] TP311[自动化与计算机技术—控制科学与工程]