← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9180.c · 生成模型:GPT-6

任务规划从目标组合可用动作

理解等级:中级

预先手写树要枚举掉物、找物等许多分支,规划器则可根据当前符号状态和动作模型搜索达到目标的组合。灵活性来自模型覆盖的选择,不意味着机器人可在没有感知、权限或动作能力时自动执行任意现实方案。

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

      So far, we have seen how reactive behaviors can be composed into more complex programs using finite state machines and behavior trees. Although behavior trees facilitate dealing with the exploding number of possible state transitions by making them implicit, the programmer still needs to define the entire program flow. Consider again a pick-and-place task. This time, we will not simply grasp a new item in

    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:摘录中关于任务规划从目标组合可用动作的定义、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:So far, we have seen how reactive behaviors can be composed into more complex programs using finite state machines and behavior trees. Although behavior trees facilitate dealing with the exploding number of possible state transitions by making them implicit, the programmer still needs to define the entire program flow. Consider again a pick-and-place task. This time, we will not simply grasp a new item in