Learn Robotics and Computer Vision with JdeRobot
- 1 Installation and use
- 2 Exercises on Computer Vision
- 3 Exercises on autonomous cars
- 4 Exercises on mobile robots
- 5 Exercises on drones
Installation and use
Robotics Academy uses ROS and Gazebo as underlying infrastructure for the exercises. Computer Vision exercises use OpenCV.
Use it from your web browser with no installation
Just play with Robotics Academy at its WebIDE, it is free :-)
Local installation on Linux machines
The programming framework is composed of the Gazebo simulator, ROS middleware and the Robotics Academy package. All this software is open source so there are alternative ways to install all of them directly from the source code. Currently we use Gazebo-7.4.0, ROS Kinetic and JdeRobot-Academy (20180606) releases. Follow the installation recipe in the github repository to get the framework up and running, ready to use on your computer.
Local installation on Windows machines
We prepared docker images which include all the infrastructure software so you can run the framework from the container. Follow the installation recipe in the github repository to get the framework up and running, ready to use on your computer.
Exercises on Computer Vision
Visual 3D reconstruction from a stereo pair of RGB cameras
Exercises on autonomous cars
Program a Formula1 car to autonomously complete a lap to the Nürburgring circuit as fast as it can. Compare the evolution of your car with the record along the whole circuit!.
Visual follow-line behavior on a Formula1
The students program a Formula1 car in a race circuit to follow the red line in the middle of the road.
In a race circuit the students have to program the navigation algorithm of a Formula1 car endowed with a laser (in Gazebo simulator).
Car stop at a joint
Exercises on mobile robots
Robot self-localization using particle filter and laser sensor
Bump and go
There is a Kobuki robot inside a labyrinth or scenario. The robot will go front until it gets close to an obstacle. The it will go back, turn a random angle and go front again repeating the process. This exercise aims to show the power of automata when building robot behavior.
Program a robotic vacuum-cleaner like Roomba to clean your home. It does have a compass but not precise self-localization.
Vacuum-cleaner with visualSLAM
Program a robotic vacuum-cleaner like Roomba to clean your home. This Roomba model has a precise self-localization algorithm, so its navigation to clean may be better than without localization.
Exercises on drones
Follow the road
Program a autonomous drone to follow a road using its onboard cameras. This exercise has been completely refactored to use ROS infrastructure and mavROS.
Follow the ground robot
Drone cat and mouse
Landing on a moving car
Escaping from a labyrinth using visual cues
People rescue after an earthquake