检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:徐人凤[1] 徐守祥[2] 陈建刚[2] 黄国伟[2]
机构地区:[1]深圳职业技术学院,广东深圳518055 [2]深圳信息职业技术学院,广东深圳518172
出 处:《小型微型计算机系统》2014年第4期858-863,共6页Journal of Chinese Computer Systems
基 金:广东省科技计划项目(2011B040300034)资助
摘 要:智能虚拟人在动态虚拟环境中的追击问题,是解决虚拟人自主行为规划的典型问题.构建基于认知的三层行为控制模型,依据情景状态、环境感知和形式化的知识库,实现目标驱动的智能虚拟人自主行动推理.将追击问题的视线法拓展到3D空间中的筒视线法,实现虚拟人的主动感知,用势函数构建动态人工势场,控制虚拟人的反应行为;以虚拟人与环境的交互实现对环境可供性的感知;以流演算的行动推理方式形式化目标驱动的追击行为,建立行动推理知识库,实现虚拟人的自主行为规划.最后给出了在3D网络游戏引擎基础上的原型实现.The chase issue of the intelligent virtual human in a dynamic virtual environment is a typical issue to solve the autonomous behavior planning of the virtual human. This paper proposes a cognitive-based three-tier behavior control model to achieve the goal- driven intelligent virtual human autonomous action reasoning, in accordance with the scenario state, the environment sensation and the formal knowledge base. In this model, the active perception of the intelligent virtual human is achieved by expanding the line-of-sight method of the chase issue to the tube line-of-sight method in the 3D space. The reaction behavior of the intelligent virtual human is controlled by building the dynamic artificial potential field with the potential function. The available perception of the environment is achieved by the interaction of the virtual human with the environment. The autonomous behavior planning of the virtual human is a- chieved by building the action reasoning knowledge base with the formalization of the goal-driven chase behavior through the reason- ing about action of the fluent calculus. Finally, a 3D online game engine based prototype is implemented.
分 类 号:TP391[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.15