学习SLAM需要哪些预备知识？

9to5iot

作者：bobin
链接：https://www.zhihu.com/question/35186064/answer/145219653
来源：知乎
著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

还是说视觉slam吧。
先说视觉这块，首先射影几何的一些内容相机模型，单视几何，双视几何和多视几何。这些内容可以在Multiple View Geometry in Computer Vision这本书中找到。英文版的，另外中科院的吴福朝编著的“计算机视觉中的数学方法”也很好，涵盖了上述了MVG in CV book中的大部分内容，强烈安利。
然后是一些视觉特征，这方面就是一些特征，描述子，匹配相关等。见SIFT，ORB、BRISK、SURF等文章。
数学方面首先是三维空间的刚体运动，参考《机器人学(第2版)》 蔡自兴【摘要 书评 试读】图书。
关于优化，SLAM中的优化方法十分基本，参考高斯牛顿，LM，结合稀疏线性代数。其实用的时候会使用一种g2o的图优化库或者ceres。参考文章 g2o: A General Framework for Graph Optimization
http://ais.informatik.uni-freiburg.de/publications/papers/kuemmerle11icra.pdf
最难的应该算是李群和李代数，这方面可以参考book [state estimation for Robotics](http://asrl.utias.utoronto.ca/~tdb/bib/barfoot_ser15.pdf)。当然不想看书的话可以参考博客李代数 - 标签 - 半闲居士 - 博客园。
为了看论文的时候能够比较流畅，还应该具备一些概率论的知识，这里推荐book[Probabilistic Robotics](http://www.probabilistic-robotics.org/) [pdf](https://docs.ufpr.br/~danielsantos/ProbabilisticRobotics.pdf)
话说高翔博士近期完成一本SLAM的入门book，有理论有实践，写的不错，推荐。他包含了上述在视觉slam需要的所有基础知识，真是造福大众啊。详细研读此书，以后读各种论文就不会显得那么吃力了吧。最后列举一些玩slam的一些必备工具和相关资源。
tools
1. ubuntu,  cmake, bash, vim, qt(optional).
2. OpenCV install, read the opencv reference manual and tutorial
3. ros, [install](ROS/Installation - ROS Wiki), [tutorial}(ROS/Tutorials - ROS Wiki).
4. python. 可以使用pycharm,作为IDE.
为什么使用ubuntu？因为大家的代码，全是用linux，而且很多使用ros的，ros一定是要Linux的，同时还要cmake。Ubuntu是比较适合初学Linux的人，非常好用。
somethind about Calibration
1. [opencv camera Calibration](http://docs.opencv.org/2.4/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.html)
2. [matlab camera Calibration toolbox](Camera Calibration Toolbox for Matlab)
3. [svo camera Calibration](uzh-rpg/rpg_svo)
4. [ros wiki camera Calibration](camera_calibration - ROS Wiki)
为什么要标定相机呢，因为slam的模型中假设 相机的内参数是已知的，因此有了这个内参数我们才能正确的初始化slam系统。
slam open sources
1. [svo](uzh-rpg/rpg_svo)
2. [orb slam](raulmur/ORB_SLAM2)
3. [ar_tracker_alvar githun page](sniekum/ar_track_alvar) [ros page](ar_track_alvar - ROS Wiki)
4. [ros ptam](ethzasl_ptam - ROS Wiki),原始代码不支持ros, 这里给出ros版本的代码. 原始[代码](Oxford-PTAM/PTAM-GPL)[网站](Parallel Tracking and Mapping for Small AR Workspaces (PTAM))
5. DSO JakobEngel/dso
ros books
1. Learning ROS for Robotics Programming
2. 机器人操作系统（ROS）浅析
3.  ros by example http://www.lulu.com/shop/http://www.lulu.com/shop/r-patrick-goebel/ros-by-example-indigo-volume-1/ebook/product-23032353.html
some blogs about ros
1. 古月居 - 怕什么真理无穷，进一寸有一寸的欢喜

SLAM基础学习
1. [Multiple View Geometry in Computer Vision](Multiple View Geometry in Computer Vision)。
2. Sparse Matrix [Sparse Non-Linear Least Squares in C/C++](Sparse Non-Linear Least Squares in C/C++)
3. [openSLAM](https://www.openslam.org/)
4. dataset [tum](RGB-D SLAM Dataset and Benchmark)
5. [PCL](PointCloudLibrary/pcl)
6. [opencv](OpenCV | OpenCV)

9to5iot

推荐阅读的书
1. [Multiple View Geometry in Computer Vision](Multiple View Geometry in Computer Vision)
2. [Probabilistic Robotics](http://www.probabilistic-robotics.org/) [pdf](https://docs.ufpr.br/~danielsantos/ProbabilisticRobotics.pdf)
3. [state estimation for Robotics](http://asrl.utias.utoronto.ca/~tdb/bib/barfoot_ser15.pdf)
4. [Quaternion kinematics for the error-state KF](http://www.iri.upc.edu/people/js ... otes/kinematics.pdf)
5. 凸优化，https://web.stanford.edu/~boyd/cvxbook/bv_cvxbook.pdf
6. 线性系统理论，Chi-Tsong Chen: 9780199959570: Amazon.com: Books
7. An Invitation to 3-D Vision，https://www.eecis.udel.edu/~cer/arv/readings/old_mkss.pdf
8. Rigid Body Dynamics，http://authors.library.caltech.e ... ner-HudsonDyn80.pdf。
paper about vision slam
- Georg Klein and David Murray, "Parallel Tracking and Mapping for Small AR Workspaces", In Proc. International Symposium on Mixed and Augmented Reality (ISMAR'07, Nara).
- D. Scaramuzza, F. Fraundorfer, "Visual Odometry: Part I - The First 30 Years and Fundamentals IEEE Robotics and Automation Magazine", Volume 18, issue 4, 2011.
- F. Fraundorfer and D. Scaramuzza, "Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications," in IEEE Robotics & Automation Magazine, vol. 19, no. 2, pp. 78-90, June 2012.
doi: 10.1109/MRA.2012.2182810
- A Kalman Filter-Based Algorithm for IMU-Camera Calibration Observability Analysis and Performance Evaluation
- SVO- Fast Semi-Direct Monocular Visual Odometry
- [eth zasl sensor](ethzasl_sensor_fusion - ROS Wiki),
- Stephan Weiss. Vision Based Navigation for Micro Helicopters PhD Thesis, 2012 pdf
- Stephan Weiss, Markus W. Achtelik, Margarita Chli and Roland Siegwart. Versatile Distributed Pose Estimation and Sensor Self-Calibration for Autonomous MAVs. in IEEE International Conference on Robotics and Automation (ICRA), 2012. pdf
- Stephan Weiss, Davide Scaramuzza and Roland Siegwart, Monocular-SLAM–based navigation for autonomous micro helicopters in GPS-denied environments, Journal of Field Robotics (JFR), Vol. 28, No. 6, 2011, 854-874. pdf
- Stephan Weiss and Roland Siegwart. Real-Time Metric State Estimation for Modular Vision-Inertial Systems. in IEEE International Conference on Robotics and Automation (ICRA), 2011. pdf
- Simon Lynen, Markus Achtelik, Stephan Weiss, Margarita Chli and Roland Siegwart, A Robust and Modular Multi-Sensor Fusion Approach Applied to MAV Navigation. in Proc. of the IEEE/RSJ Conference on - - Intelligent Robots and Systems (IROS), 2013. pdf
- [orb slam]
- Raúl Mur-Artal, J. M. M. Montiel and Juan D. Tardós. ORB-SLAM: A Versatile and Accurate Monocular SLAM System. IEEE Transactions on Robotics, vol. 31, no. 5, pp. 1147-1163, 2015. (2015 IEEE Transactions on Robotics Best Paper Award). PDF.
- Dorian Gálvez-López and Juan D. Tardós. Bags of Binary Words for Fast Place Recognition in Image Sequences. IEEE Transactions on Robotics, vol. 28, no. 5, pp. 1188-1197, 2012.
最后来张脑图