← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9212.b · 生成模型:GPT-6

闭环利用旧地标修正累计漂移

理解等级:中级

再次观测先前地标可对累计运动误差形成约束,使相关地图与位姿共同调整。错误闭环也可能把一致轨迹拉坏,必须先确认重识别和几何一致性。

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

      Usually, a robot obtains an initial estimate of where it is using some onboard sensors (e.g., odometry, optical flow), leverages this estimate to localize landmarks (e.g., walls, corners, graphical patterns) in the environment, and finally refines its pose estimate by matching sensor information in consecutive fields-of-view using, for example, the iterative closest point (ICP) algorithm (section 12.2) or feature matching. As soon as a robot

    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:摘录中关于闭环利用旧地标修正累计漂移的定义、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:Usually, a robot obtains an initial estimate of where it is using some onboard sensors (e.g., odometry, optical flow), leverages this estimate to localize landmarks (e.g., walls, corners, graphical patterns) in the environment, and finally refines its pose estimate by matching sensor information in consecutive fields-of-view using, for example, the iterative closest point (ICP) algorithm (section 12.2) or feature matching. As soon as a robot