Code Monkey home page Code Monkey logo

ros-ad-slam-evaluation's Introduction

ROS-AD-SLAM-Evaluation

Build Status Codacy Badge

How to setup Carla Environment to replicate the test results

Requirements

  • Ubuntu 18.04.
  • 16gb RAM.
  • Vulkan enabled GPU is preferred , Follow the LINK to check your GPU compatibility.
  • Unreal Engine 4.24 , for build instructions follow LINK.
  • Carla 0.9.8, for build instructions follow LINK.
  • ROS Melodic , for install instructions follow LINK.

Setup the ROS Environment

  • Navigate to carla build directory , you should find *.egg file in carla/Dist/CARLA_Shipping_0.9.8-***********/LinuxNoEditor/PythonAPI/carla/dist/ folder, which to be exported to python environment to run further simulations. Make sure you export appropiate egg file based on your preferred python version.
  • Install SLAM Nodes - Install Gmapping by sudo apt-get install ros-melodic-slam-gmapping. - Install Hector SLAM by sudo apt-get install ros-melodic-hector-slam. - Install RTAB-Map by sudo apt-get install ros-kinetic-rtabmap-ros. - Karto SLAM needs to be build from the source , follow standard ROS package installation procedure. The Kartoslam Github repo can be found LINK.
  • Clone the SLAM packages https://github.com/prithvisekhar/ROS-AD-SLAM-Evaluation.git
  • Copy the ros-bridge contents to a ros workspace src folder and build the workspace and source the workspace before running the roscore.

Running the Simulator

  • Run Carla simulator by navigating to carla/Dist/CARLA_Shipping_0.9.8-***********/LinuxNoEditor/ and running ./CarlaUE4.sh if you are using opengl then you should pass -opengl as configuration along with the carla launch command. it should open the simulator (Refer the below image as reference). For More info on graphics support follow this LINK Carla Window
  • Run the Carla ROS Client roslaunch carla_ros_bridge carla_ros_bridge_with_example_ego_vehicle.launch , Refer the below image as reference Carla Window
    • Run the Gmapping Node roslaunch carlabg Gmapping_Carla.launch , for configuration option see ros-bridge/carlabg/launch folder. After mapping session is over save the map using map_saver tool rosrun map_server map_saver -f /path to your file.
    • Run the Hector SLAM Node roslaunch carlabg Hectormapping_Carla.launch. Follow the same map saver command to save the map for Hector SLAM.
    • Run the Karto SLAM Node roslaunch carlabg KartoSLAM2.launch. Follow the same map saver command but this time pass the map frame as map2.
    • Launch the RTAB-Map Node roslaunch carlabg RtabMapping_Carla.launch. RTAB Map can be directly saved from the RTAB map application.

ros-ad-slam-evaluation's People

Contributors

pisers avatar prithvisekhar avatar thrilochans avatar

Stargazers

avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar

ros-ad-slam-evaluation's Issues

Missing CarlaPCtoLS.launch in pointcloud_to_laserscan

It seems that the CarlaPCtoLS.launch file in pointcloud_to_laserscan is missing in this repo. Could you please kindly update it in this repo or just copy and paste it here. I'm figuring out how to publish 2D LaserScan in Carla.

Great repo! Thanks in advance!

Can't get a map

Hello! I am trying to run gmapping with CARLA following the instructions given in README.md but the map doesn't exist in RViz. Specifically, I am running the following commands:

  • cd /opt/carla-simulator/bin
  • ./CarlaUE4.sh
  • roslaunch carla_ros_bridge carla_ros_bridge_with_example_ego_vehicle.launch
  • roslaunch carlabg Gmapping_Carla.launch
    I am trying to see if the corresponding topics take messages correctly using the command "rostopic hz 'topic name' or rostopic echo 'topic name' " but I take the following result which means that these topics don't take any messages.
    Screenshot from 2020-08-27 17-32-53
    I know that gmapping needs as input "sensor_msgs/LaserScan" messages in order to work properly, but as I see at the available topics the output of the Lidar gives "sensor_msgs/PointCloud2" messages. Then I tried to convert them from pointcloud2 to laserscan by using this package http://wiki.ros.org/pointcloud_to_laserscan and running the following command:
  • rosrun pointcloud_to_laserscan pointcloud_to_laserscan_node cloud_in:= 'topic name of point cloud' but I couldn't take the map.

Generally, I couldn't make any algorithm to work properly and give me back a map, so your help will be precious. I can give you information about other ways that I tried to run SLAM with CARLA and ROS. Thanks!

I am using:

  • Ubuntu 16.04
  • ROS kinetic
  • CARLA 0.9.7 installed by apt-get
  • carla_ros_bridge installed by apt-get

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.