Presidential Young Investigator Award: Robot Motion Planning

总统青年研究员奖：机器人运动规划

• 批准号: 8451218
• 负责人: Tomas Lozano-Perez
• 金额: $ 30.45万
• 依托单位: Massachusetts Institute of Technology
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1985
• 资助国家: 美国
• 起止时间: 1985-09-01 至 1991-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=8451218&HistoricalAwards=false
• 关键词: Presidential; Young; Investigator; Award; Robot

An investigation of robot motion planning will be expanded using configuration space. Current planning methods do not take into account the possibility of gross errors in the environment model, such as unmodeled obstacles or surface defects. These kinds of problems are quite common outside of well-controlled environments such as laboratories and factories. The challenge is to detect the error as early as possible and to undertake corrective action without requiring complete re-planning. Further, this approach will be extended to planning to deal with multiple moving objects whose motions are not completely known in advance. The idea is to be able to guarantee that there exists a plan that achieves the goal as long as the other objects move within their expected bounds. Both of these extensions will build on the basic idea that to plan ahead one does not need to know the state of the environment exactly.

对机器人运动计划的调查将使用配置空间进行扩展。 当前的计划方法没有考虑到环境模型中严重错误的可能性，例如未建模的障碍物或表面缺陷。 这些问题在控制良好的环境（例如实验室和工厂）之外非常普遍。 面临的挑战是尽早检测错误并采取纠正措施，而无需完整的重新计划。 此外，这种方法将扩展到计划处理多个动作的对象，其动作并不是完全知道的。 这个想法是能够确保存在一个计划，只要其他对象在其预期的范围内移动，就可以实现目标。 这两种扩展都将基于一个基本思想，即为了提前计划，一个人不需要完全了解环境的状态。