• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Mechatronics, 2009. ICM 2009 >Learning navigation Teleo-Reactive Programs using behavioural cloning
【24h】

Learning navigation Teleo-Reactive Programs using behavioural cloning

机译：使用行为克隆学习导航Teleo-Reactive程序

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Programming a robot to perform tasks in dynamic environments is a complex process. Teleo-reactive programs (TRPs) have proved to be an effective framework to continuously perform a set of actions to achieve particular goals and react in the presence of unexpected events, however, their definition is a difficult and time-consuming process. In this paper, it is shown how a robot can learn TRPs from human guided traces. A user guides a robot to perform a task and the robot learns how to perform such task in similar dynamic environments. Our approach follows three steps: (i) it transforms traces with low-level sensor information into high-level traces based on natural landmarks, (ii) it learns TRPs that express when to perform an action to achieve simple tasks using an inductive logic programming (ILP) system, and (iii) it learns hierarchical TRPs that express how to achieve goals by following particular sequences of actions using a grammar induction algorithm. The learned TRPs were used to solve navigation tasks in different unknown and dynamic environments, both in simulation and in a service robot called Markovito.
机译：对机器人进行编程以在动态环境中执行任务是一个复杂的过程。远程响应程序（TRP）已被证明是一种有效的框架，可以连续执行一组操作以实现特定目标并在出现意外事件时做出反应，但是，其定义是一个困难且耗时的过程。在本文中，显示了机器人如何从人类引导的轨迹中学习TRP。用户指导机器人执行任务，并且机器人学习如何在类似的动态环境中执行此类任务。我们的方法分三个步骤：（i）将基于自然界标的具有低层传感器信息的迹线转换为高层迹线；（ii）通过归纳逻辑编程学习可以表达何时执行动作以实现简单任务的TRP （ILP）系统，以及（iii）学习分层TRP，这些TRP表示如何通过使用语法归纳算法遵循特定的动作序列来实现目标。学习到的TRP用于模拟和服务机器人Markovito的不同未知和动态环境中的导航任务。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号