门外汉学Slam

slam入门笔记。。。

About Slam

Slam是Simultaneous Localization And Mapping的首字母缩写,中文可以翻译成同时定位与建图。其主要解决三个问题:
第一个问题称为定位 (Localization),第二个称为建图 (Mapping),第三个则是随后的路径规划。

SLAM is concerned with the problem of building a map of an unknown environment
by a mobile robot while at the same time navigating the environment using the map.

SLAM consists of multiple parts; Landmark extraction, data association, state
estimation, state update and landmark update

Hardware

  • Robot
  • Range Measure deivce
    Laser: 高精度 但是贵
    Sonar: 便宜,但是精度不高。
    Vision: 需要很多的计算,并且光线的变化可能会引起误差。

Process

The SLAM process consists of a number of steps. The goal of the process is to use the
environment to update the position of the robot.

An EKF (Extended Kalman Filter) is the heart of the SLAM process. It is responsible for updating where the robot thinks it is based on these features.

The Extended Kalman Filter is used to estimate the state (position) of the robot from
odometry data and landmark observations.

Project Tango

Project Tango是google的ATAP部分推出的一个在移动设备上(主要针对Android平台)开发computer vision平台。其已经支持motion tracking,depth perception,area learing等。感兴趣的可以去他们的观望了解更多信息。

值得一提的是tango提供了开发设备,可以从官网上购买,目前的硬件平台是基于Nvidia芯片,基于Intel RealSense的设备也很快可以买到了。

另外,Lenovo在2016 CES上宣布要和google合作开发第一款consumer mobile device with Project Tango.

Reference