Skip to content

FastSLAM and image processing algorithms for Tupã's autonomous project

License

Notifications You must be signed in to change notification settings

murilo-toddy/autunumus

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AuTUnumus

Repository used to condense all code related to Tupã's autonomous vehicle adventure.

Contents

This repository is divided into four main modules: Image Processing, SLAM, ROS and Telemetry-Api. Specific information about how to execute each module is specified in each module's README.

The improc module contains a Python algorithm for cone identification. It's built using the library OpenCV.

Contents

  • Camera calibration
  • Color picking in HSV spectrum based on sampled images or input video
  • Cone detection algorithm
    • Using input images
    • Using live video
  • ZMQ connection with SLAM

The slam module contains a Python and Numpy implementation of FastSLAM 2.0. It's able to simultaneously locate and map the robot.

Contents

  • FastSLAM 2.0 implementation
  • ZMQ connection to fetch input data
  • API handler to pass information to our telemetry-api

The ros module contains a simulation environment built using ROS Noetic. It contains a differential robot implementation and allows testing of the previously mentioned systems It's able to simultaneously locate and map the robot.

The telemetry-api contains a simple REST API built using Flask to receive data from our vehicle. It's used for real-time data visualization.

About

FastSLAM and image processing algorithms for Tupã's autonomous project

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published