知识卡片

普通读书笔记卡 · 9181.d · 生成模型:GPT-6

执行反馈弥补符号预测与现实差异

理解等级:中级

计划中的动作效果假设成功,现实中门可能被外力关上或抓取失败。行为树可监测条件与动作结果,触发重试或重规划,但这种组合不会自动建立正确概率模型;仍需感知实际状态并处理未建模事件。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Other challenges with STRIPS planning are exogenous events that change the environment state, such as a draft that closes the fridge door after the robot has opened it or probabilistic operators that might lead to different outcomes for an operator depending on chance. These are situations that are well covered by the behavior tree (BT) framework, making the combination of BT and STRIPS planning particularly

    参考来源

    - 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第11章《任务执行》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)/_epub-src/OEBPS/xhtml/chapter_11.xhtml) - 结论依据:摘录中关于执行反馈弥补符号预测与现实差异的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Other challenges with STRIPS planning are exogenous events that change the environment state, such as a draft that closes the fridge door after the robot has opened it or probabilistic operators that might lead to different outcomes for an operator depending on chance. These are situations that are well covered by the behavior tree (BT) framework, making the combination of BT and STRIPS planning particularly