Understanding and Improving On-Line Planning Methods

理解和改进在线规划方法

• 批准号: 0098807
• 负责人: Craig Tovey
• 金额: $ 38.57万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2001
• 资助国家: 美国
• 起止时间: 2001-07-01 至 2006-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0098807&HistoricalAwards=false
• 关键词: Understanding; Improving; Line; Planning; Methods

This is the first year funding of a three year continuing award. A variety of on-line planning methods are used in artificial intelligence including, for example, real-time search methods such as LRTA*, reinforcement-learning methods such as Q-learning, and robot-navigation methods such as D*. The PIs intend to improve the performance of these and other on-line planning methods substantially so that, for example, future robot-navigation methods will be able to map unknown terrain significantly faster than is now possible, yet have the same advantageous properties as existing on-line planning methods. Many on-line planning methods, either always or most of the time, execute actions that move the agent in the perceived direction of the goal, that is, move the agent so that it reduces the estimates of the goal distances the most. However, the PIs preliminary theoretical results show that executing actions that move the agent in the perceived direction of the goal is usually not a good idea. For example, D* does not reach a goal location in unknown terrain with a minimal travel distance in the worst case. The key to improving the performance of these on-line planning methods then is to exploit the distance estimates that they maintain (or can maintain) in a way that is more directly related to the planning or learning objective. The PIs will study the properties of on-line planning methods both theoretically and experimentally, and will develop improved on-line planning methods that have the same interface as the existing methods, which allows users of these methods to easily substitute the new methods for the ones they are currently using. Side benefits of the proposed research include developing a test-bed for the experimental evaluation of robot navigation methods in unknown terrain, and creating a solid theoretical foundation for understanding robot-navigation methods in unknown terrain, including D*.

这是三年连续奖励的第一年资助。 人工智能中使用了多种在线规划方法，包括例如 LRTA* 等实时搜索方法、Q-learning 等强化学习方法以及 D* 等机器人导航方法。 PI 打算大幅提高这些和其他在线规划方法的性能，例如，未来的机器人导航方法将能够比现在更快地绘制未知地形地图，同时具有与现有在线规划方法相同的优势特性。 许多在线规划方法总是或大多数时间执行将智能体朝目标感知方向移动的动作，即移动智能体以使其最大程度地减少目标距离的估计。 然而，PI 的初步理论结果表明，执行使智能体朝着目标感知方向移动的动作通常不是一个好主意。 例如，在最坏的情况下，D* 不会以最小的行进距离到达未知地形中的目标位置。 提高这些在线规划方法性能的关键是以与规划或学习目标更直接相关的方式利用它们维持（或可以维持）的距离估计。 PI将从理论上和实验上研究在线规划方法的特性，并将开发改进的在线规划方法，其与现有方法具有相同的界面，使这些方法的用户能够轻松地用新方法替换他们当前使用的方法。 该研究的附带好处包括开发一个用于未知地形中机器人导航方法实验评估的测试平台，并为理解未知地形（包括 D*）中的机器人导航方法奠定坚实的理论基础。