← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9209.a · 生成模型:GPT-6

联合状态随地标数量增长

理解等级:中级

二维点地标模型可把机器人三维位姿与N个地标的二维坐标组成3+2N维状态。完整协方差存储随N平方增长;这个维数依赖点地标参数化,不适用于所有地图表示。

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

      The key idea in EKF SLAM is to extend the state vector from the robot’s position (and potentially pose) to contain the position of all landmarks. Thus, the state becomes assuming N landmarks, which is a (3 + 2N) × 1 vector. The action update (or “prediction update”) is the same as if the landmarks are already known; the robot simply updates its position using

    参考来源

    - 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第17章《同时定位与建图》(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_17.xhtml) - 结论依据:摘录中关于联合状态随地标数量增长的定义、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:The key idea in EKF SLAM is to extend the state vector from the robot’s position (and potentially pose) to contain the position of all landmarks. Thus, the state becomes assuming N landmarks, which is a (3 + 2N) × 1 vector. The action update (or “prediction update”) is the same as if the landmarks are already known; the robot simply updates its position using