GithubHelp home page GithubHelp logo

neu-zjx / auto-complete-graph Goto Github PK

View Code? Open in Web Editor NEW

This project forked from malcolmmielle/auto-complete-graph

0.0 1.0 1.0 265.8 MB

a method to integrate an emergency map into a robot map, so that the robot can plan its way toward places it has not yet explored.

Home Page: https://malcolmmielle.wordpress.com/2017/08/07/using-emergency-maps-to-help-robots-save-you-in-emergencies/

License: GNU General Public License v3.0

CMake 6.49% C++ 90.56% Python 2.96%

auto-complete-graph's Introduction

Auto Complete Graph (ACG).

Using emergency maps to help robots save you in emergencies

Description

The goal of this program is described in this blog post and can be summarized by this sentence:

a method to integrate an emergency map into a robot map, so that the robot can plan its way toward places it has not yet explored.

Result example

Paper

The auto complete graph method is presented in this article on arxiv and on IEEE Xplore. The paper was awarded Best Student Paper Award at SSRR2018 so hopefully you'll enjoy reading it :).

@INPROCEEDINGS{8088137,
author={M. Mielle and M. Magnusson and H. Andreasson and A. J. Lilienthal},
booktitle={2017 IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR)},
title={SLAM auto-complete: Completing a robot map using an emergency map},
year={2017},
volume={},
number={},
pages={35-40},
keywords={SLAM (robots);graph theory;mobile robots;rescue robots;robot vision;SLAM auto-complete;aerial images;emergency map;graph-based SLAM;rescue missions;robot mapping;Buildings;Covariance matrices;Navigation;Simultaneous localization and mapping;Strain;Uncertainty},
doi={10.1109/SSRR.2017.8088137},
ISSN={},
month={Oct},}

Run the code example

This should all be soon ros parameters but for now here is how you can test the code:

  • Use roslaunch ndt_feature gustav_radar_tf.launch to create the ndt_graph that is going to be processed by the ACG. Modify the file so that it reads your bag file. Use this bag file if your only testing the algorithm.

  • The parameters for ACG are loaded from a file. The file is determined by a string in acg_node_review.cpp named parameters_for_ACG. An example of parameter file is present in ACG_params/param.txt

  • Use rosrun auto_complete_graph acg_node_review to run the algorithm.

  • In Rviz, one can give an approximation of the position of the prior compared to robot map using the Publish point button. Only two links are needed to initialize.

How to use your own prior

The class PriorLoaderInterface.hpp is used to load prior image and detected corners. Just inherit from this class to create your own prior loader. See an example in the class basementFull.hpp. This only argument needed for PriorLoaderInterface is the name of the file image where the prior is.

Dependencies

auto-complete-graph's People

Contributors

malcolmmielle avatar

Watchers

 avatar

Forkers

jdr-neu

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.