知识卡片
动作预测对旧状态做边缘化
离散预测bel_minus(x)=Σxprev P(x|xprev,u)bel_prev(xprev),把每个原位置经运动模型转移来的概率累加。它依赖过去belief与本次动作,不是只把单个里程读数当作新的绝对位置。
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
As the robot’s location is uncertain, the real challenge is now that the robot could have potentially been anywhere to start with. We therefore have to calculate the posterior probability P(loc|odo) for all possible positions loc′. This can be accomplished by summing over all possible locations:
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:摘录中关于动作预测对旧状态做边缘化的定义、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:As the robot’s location is uncertain, the real challenge is now that the robot could have potentially been anywhere to start with. We therefore have to calculate the posterior probability P(loc|odo) for all possible positions loc′. This can be accomplished by summing over all possible locations: