参考1：COURSERA宾夕法尼亚大学机器人学课程 Robotics：Estimation and Learning

参考2：/ecoflex/p/9868474.html

参考3：《概率机器人》教材

参考4：古月居的博客/14968

building a semantic map requires

advanced object recognition techniques which go beyond our scope.

But we are most interested in the range sensor it has on the top.

/flash3d/archive//01/30/2332121.html

/Why-do-self-driving-cars-use-LIDAR-instead-of-depth-cameras-like-Kinect

/question/28749424

k-d tree算法

/eyeszjwang/articles/2429382.html