摘要
定性空间推理在人工智能、地理信息系统、机器人等领域中有着非常重要的研究价值。在复杂区域的邻域连接图的基础上提出一种层次定性空间推理模型与方法。基于复杂区域的邻域连接图定义了一种邻域层次矩阵,可两两互斥并完备地表示复杂区域中n个成分间的连接关系,以此给出一种层次定性空间推理方法和启发式推理算法。利用该方法对机器人与障碍物的层次关系进行模拟,对制定机器人避障方案提供依据。从理论和实践上验证了该方法的有效性。
Qualitative spatial reasoning has a very important research value in the fields of artificial intelligence, geographic information system, robot and so on. In this paper, a hierarchical qualitative spatial reasoning model and method was proposed on the basis of neighborhood connection graph in complex arias. A neighborhood hierarchy matrix was defined based on the neighborhood join graph of complex arias, which was the connection between n components in complex regions. And then hierarchical heuristic reasoning algorithm were presented. This method was used to simulate obstacle, and provided a basis for the robot obstacle avoidance scheme. The thematically Keywords practically mutually exclusive and fully represented qualitative spatial reasoning method and the relationship between the robot and effectiveness of the method is verified theoretically and practically.
作者
雒海东
宫海彦
耿生玲
Luo Haidong;Gong Haiyan;Geng Shengling(Educational Administration,Qinghai Normal University,Xining 810008,Qinghai,China;School of Computer,Qinghai Normal University,Xining 810008,Qinghai,China)
出处
《计算机应用与软件》
北大核心
2018年第10期245-251,共7页
Computer Applications and Software
基金
青海省自然基金项目(2014-ZJ-908
2015-ZJ-718
2016-ZJ-920Q)
青海省重大研发项目(2016-SF-130)
关键词
定性空间推理
复杂区域
邻域层次矩阵
层次关系
机器人避障
Qualitative spatial reasoning
Complex regions
Neighborhood hierarchy matrix
Hierarchical relationship
Robot obstacle avoidance
