经典规划、控制与状态估计Classical Planning, Control & Estimation
三章、14 节，回答机器人最基本的三个问题：反馈控制讲怎样让关节和整台机器人稳稳地跟上指令，从 PID 一路走到全身 QP 控制；运动规划讲怎样找到一条不碰撞的路径和轨迹，从 A* 走到任务与运动规划；状态估计与建图讲机器人怎样知道自己在哪、周围有什么，从视觉惯性里程计走到 SLAM 与地图。 Three chapters and 14 lessons that answer a robot's three most basic questions: feedback control covers how to make a joint, and then the whole robot, follow a command reliably, from PID all the way to whole-body QP control; motion planning covers how to find a collision-free path and trajectory, from A* to task and motion planning; state estimation and mapping covers how a robot knows where it is and what is around it, from visual-inertial odometry to SLAM and maps.
1三章之间的关系How the three chapters connect
控制建立在 Part I 的微分方程与优化、Part II 的运动学与动力学之上；规划用到构型空间、动态规划和 SDF；估计用到概率滤波、因子图和 Part III 的多视图几何。把鼠标放在（或点击）任意一个方块上：琥珀色是它依赖的部分，紫色是用到它的部分；虚线框是前面的章节或后续部分。每一节具体依赖哪几节，见第 3 部分。
Control builds on Part I's ODEs and optimization and on Part II's kinematics and dynamics; planning uses configuration space, dynamic programming and SDFs; estimation uses probabilistic filters, factor graphs and Part III's multi-view geometry. Hover (or tap) any box: amber shows what it builds on, purple shows what builds on it; dashed boxes are earlier chapters or later parts. Section 3 lists exactly which lessons each lesson builds on.
2各章一览The chapters
★ 标记的是核心节，点击标题即可进入（灰色的是尚未上线的节）。每章都会写出它的"一句话直觉"和在机器人中的主要用途。
★ marks core lessons; click a title to open it (greyed-out lessons are not live yet). Each chapter lists its one-line intuition and its main uses in robotics.
3逐节内容与前置Each lesson and what it builds on
每节一句话说明它讲什么，下面列出最好先读的几节。青色边框的是本部分内的前置节，其余来自 Part I–III；点击即可跳转。
Each lesson gets one line on what it covers, followed by the lessons best read first. Prerequisites with a cyan border are inside this part; the rest come from Parts I–III. Click one to jump there.
4按目标选路线Pick a route by goal
时间有限的话，可以按你的方向挑一条路线先走通，再回头补全。
Short on time? Pick the route that matches your direction, walk it end to end, then come back and fill in the rest.