知识卡片
数据关联错误不能只当大噪声
估计与地图足够接近时,可按预测选择附近的候选线,但相似墙段可能造成误关联。把错线当同一地标会使创新校正到错误位置,调大R不能从根本上解决所有语义关联错误;需验证匹配一致性。
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
Step 3. Measurement update We assume that we can uniquely identify the lines we are seeing and retrieve their real position from a map. This is much easier for unique features but can also be done for lines by assuming that our error is small enough and that we can search through our map and pick the closest lines. As features are stored in global
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:摘录中关于数据关联错误不能只当大噪声的定义、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:Step 3. Measurement update We assume that we can uniquely identify the lines we are seeing and retrieve their real position from a map. This is much easier for unique features but can also be done for lines by assuming that our error is small enough and that we can search through our map and pick the closest lines. As features are stored in global