← 返回起始笔记位置

知识卡片

结构图卡 · 9181.e · 生成模型:GPT-6

任务执行中的反馈闭环

理解等级:中级

任务分解或计划只描述希望做什么,执行过程还需依据传感结果确认动作状态,并决定继续、等待或恢复。行为树的Running不等于失败,成功也应代表动作的业务结果。

结构图:

flowchart TD
 G[任务目标] --> P[分解或计划]
 P --> A[动作执行]
 A --> O[观测结果]
 O --> S{动作状态}
 S -->|成功| P
 S -->|仍运行| A
 S -->|失败| R[恢复或重规划]
 R --> P
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

      In their most basic implementation, sensors and actuators can be directly tied to each other, removing the need for computation. Such robots are purely reactive, thereby missing the ability to “think” or plan. In order to achieve more complex behavior, memory and state are needed to switch between different controllers and algorithms.

    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:摘录中关于任务执行中的反馈闭环的定义、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:In their most basic implementation, sensors and actuators can be directly tied to each other, removing the need for computation. Such robots are purely reactive, thereby missing the ability to “think” or plan. In order to achieve more complex behavior, memory and state are needed to switch between different controllers and algorithms.