Return to Video

06-13 Slam

  • 0:00 - 0:03
    Hi, students. I am back to teach you a bit about SLAM.
  • 0:03 - 0:07
    There was a request--a popular request, actually, in email and the discussion forum.
  • 0:07 - 0:14
    SLAM is a method for mapping that's short for "simultaneous localization and mapping."
  • 0:14 - 0:20
    Some of the this might show up in the final exam, so do pay attention.
  • 0:20 - 0:23
    Mapping is all about building maps of the environment.
  • 0:23 - 0:27
    You might remember in the localization classes we assumed the map was given.
  • 0:27 - 0:32
    One of the big passions in my life has been to understand how to make a robot
  • 0:32 - 0:37
    make these maps like this map here, which is a 3D map
  • 0:37 - 0:42
    of an abandoned underground coal mine in Pennsylvania
  • 0:42 - 0:45
    near Carnegie-Mellon University.
  • 0:45 - 0:48
    Over the past 10 years or so, I have worked on a number of different methods
  • 0:48 - 0:51
    for buildings maps that are quite sophisticated,
  • 0:51 - 0:55
    like this particle filter method over here that you can see.
  • 0:55 - 0:58
    All these methods have in common that we build a model of the environment
  • 0:58 - 1:04
    while also addressing the fact that the robot itself accrues uncertainty while it moves.
  • 1:04 - 1:07
    When, in this example here, the loop is being closed,
  • 1:07 - 1:12
    you can see how our mapping technology is able to accommodate this
  • 1:12 - 1:18
    and find a consistent map despite the fact that the robot drifted a little along the way.
  • 1:18 - 1:22
    The key insight in building maps is the robot itself
  • 1:22 - 1:26
    might lose track of where it is by virtue of its motion uncertainty.
  • 1:26 - 1:30
    You accommodate this in localization by using an existing map,
  • 1:30 - 1:33
    but now we don't have an existing map. We're building a map.
  • 1:33 - 1:35
    That's where SLAM comes into play.
  • 1:35 - 1:38
    SLAM doesn't stand for "slamming" a robot.
  • 1:38 - 1:43
    What it really means is "simultaneous localization and mapping."
  • 1:43 - 1:46
    This is a big, big, big research field.
  • 1:46 - 1:50
    Most of my AI book is about this technology,
  • 1:50 - 1:54
    and today I want to show you my favorite method called "graph SLAM,"
  • 1:54 - 1:58
    which is also by far the easiest method to understand.
  • 1:58 - 2:02
    We will reduce the mapping problem to a couple of very intuitive
  • 2:02 -
    additions into a big matrix and a vector, and that's it.
Title:
06-13 Slam
Description:

Other units in this course below:
Unit 1: http://www.youtube.com/playlist?list=PL1EF620FCB11312A6
Unit 2: http://www.youtube.com/playlist?list=PL107FD47786234011
Unit 3: http://www.youtube.com/playlist?list=PL5493E5D24A081719
Unit 4: http://www.youtube.com/playlist?list=PLAADAB4F235FE8D65
Unit 5: http://www.youtube.com/playlist?list=PL1B9983ACF22B1920
Unit 6: http://www.youtube.com/playlist?list=PLC9ED5AC39694C141
QA: http://www.youtube.com/playlist?list=PL3475310BFB1CBE34

To gain access to interactive quizzes, homework, programming assignments and a helpful community, join the class at http://www.udacity.com

more » « less
Video Language:
English
Team:
Udacity
Project:
CS373 - Artificial Intelligence
Duration:
02:06
Amara Bot added a translation

English subtitles

Revisions