Robot Planning, Learning and Selective Perception in Stochastic Domains

随机域中的机器人规划、学习和选择性感知

• 批准号: 9312395
• 负责人: Thomas Dean
• 金额: $ 20.6万
• 依托单位: Brown University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1994
• 资助国家: 美国
• 起止时间: 1994-08-01 至 1998-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9312395&HistoricalAwards=false
• 关键词: Robot; Planning; Learning; Selective; Perception

9312398 Dean The project will address problems in building integrated planning and learning systems for applications in mobile robotics, such as errand running, surveillance, target following, and searching for objects of a specified type. These applications require robots to work under uncertainty, complexity, and time pressure. Solutions to the associated control problems require efficient algorithms for directing movement and sensing to acquire information about the environment.

9312398 Dean该项目将解决为移动机器人应用构建综合规划和学习系统的问题，如跑腿、监视、目标跟踪和搜索特定类型的对象。这些应用需要机器人在不确定性、复杂性和时间压力下工作。解决相关的控制问题需要有效的算法来指导运动和感知获取有关环境的信息。