【摘要】 针对移动机器人探测静态未知环境时,利用不精确传感器(声纳)获取的数据信息不精确、不确定及高冲突性等问题,引入了一种信息融合方法Dezert-Smarandache证据理论(DSmT),并根据声纳的物理特性建立了混合DSm模型,构造了基本信度赋值函数.使用Pioneer 2-DXe机器人进行了地图构建实验,将由混合DSm模型构建出的静态环境地图与实际环境布局进行比较,实验结果充分验证了算法的有效性,为处理不精确信息提供了有力的理论依据.更多还原

【Abstract】 To solve the problem of mobile robot map building under entirely unknown environment,a few of general basic belief assignment functions and a hybrid DSm(Dezert-Smarandache) model of sonar are constructed to deal with the uncertain and imprecise information obtained by sonar sensors with the application of new information fusion method DSmT(DSm theory) in the system and consideration of characteristics of sonar sensors.At last,Pioneer II mobile robot are used to carry out experiment of map building.The comparison of created ichnography with the real map testified the validity of hybrid DSm model for fusing imprecise information and map building proposed by this research.更多还原