Scribd
Upload
42 views2 pages

SLAM

The document discusses Simultaneous Localization and Mapping (SLAM) which estimates a map of an environment and a robot's trajectory using sensor measurements. It mentions several SLAM algorithms like Gmapping which uses laser scans and an Extended Kalman Filter to localize a robot and build a map. Adaptive Monte Carlo Localization is also discussed as a probabilistic method for robot localization using particles to represent location and sensor data.

Uploaded by

Prasad Kulkarni
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
42 views2 pages

SLAM

The document discusses Simultaneous Localization and Mapping (SLAM) which estimates a map of an environment and a robot's trajectory using sensor measurements. It mentions several SLAM algorithms like Gmapping which uses laser scans and an Extended Kalman Filter to localize a robot and build a map. Adaptive Monte Carlo Localization is also discussed as a probabilistic method for robot localization using particles to represent location and sensor data.

Uploaded by

Prasad Kulkarni
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

A map is a representation of the environment where the robot is operating

In order to create a map, it is necessary to merge the measurements from previous positions
and also keep a track of current measurements and the pose of the bot as they are changing.
To overcome this problem, we use a technique called Simultaneous Localization and Mapping
(SLAM). It estimates the map of the environment and the trajectory of a moving device using a
sequence of sensor measurements.
There are a lot of SLAM algorithms around. To name a few, Gmapping, Hector mapping,
Cartogrpaher, Rtab mapping etc.
The Gmapping package provides laser-based SLAM

 First, it takes the measurement from odometry and laser scan, it tries to localize the bot
along with the laser scan matching and then using Extended Kalman Filter (EKF) it
estimates the output by fusing odometry and laser scan matching values. Along with
this, it uses a particle filter for localization.
We need to launch Rviz in order to visualize the map and other parameters
Robot localization is the process of determining where a mobile robot is located with respect to
its environment. In this project we have used Adaptive Monte Carlo Localization which is a
probabilistic localization system for a robot moving in 2D

1. At start the robot has map of a room and the probability of location and heading
are randomly assigned using discrete particles (or poses). Each of this particle is
saved in the filter as the possible estimate of the state.
2. The filter can go through each of the particles and compare it with what the Lidar
sensor output would have returned if that pose was actual one. Some of the
wrong guess are removed
3. It will compare the the scene seen from the particle pose to the actual robot
pose, the closer the scenes match higher the probability. Higher probability
particles are given more weights. The particles are re-sampled by removing low
probability particles.
4. As the robot moves the estimated motion is applied to every particle predicting
each of the poses whether it is same as current position of robot.

Cost map is a grid in which every cell gets assigned a value (cost) determining distance
to obstacle, where higher value means closer distance. Using this map, the robot plans
the path in such a way that it avoids obstacles by creating a trajectory with lowest cost.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy