知识卡片
运动卷积只适用于特定平移模型
若运动误差对空间位置具有平移不变性,预测可写成belief与位移核的卷积。地图约束、朝向和状态相关运动往往使转移更一般;不能把任意动作更新一概当普通一维卷积。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 定位
原书出处 · 1 处
- · 查看原书依据
In other words, the law of total probability requires us to consider all possible locations the robot could have ever been at. This step is known as the action update. In practice, we don’t need to calculate this for all possible locations but only those that are technically feasible, given the maximum speed of the robot. We note also that the sum notation technically corresponds
参考来源
- 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第16章《定位》(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_16.xhtml)
- 结论依据:摘录中关于运动卷积只适用于特定平移模型的定义、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 other words, the law of total probability requires us to consider all possible locations the robot could have ever been at. This step is known as the action update. In practice, we don’t need to calculate this for all possible locations but only those that are technically feasible, given the maximum speed of the robot. We note also that the sum notation technically corresponds