87. Optimized embedded Linux for ROS with Raul Muñoz

87. Optimized embedded Linux for ROS with Raul Muñoz

I would like to dedicate this episode to all the ROS Developers that are using an embedded computer to control their ROS robot.

Today we are going to learn how we can optimize the Linux distribution for embedded computers and how we can use that with ROS.

But before going into that, let me remind you about our ROS online academy. Yes, at the Construct we have created an online academy named The Robot Ignite Academy which contains a ROS learning path for beginners. The path is composed by:

Some other robotics theory courses included are:

Of course all our courses are based on practice with simulated robots! (theory+practice)

Now let me introduce you Raul Muñoz. He is the Community Engineer at Foundries.io.

Welcome to the podcast Raul!

Related links

Subscribe to the podcast using any of the following methods

Or watch the video interview

86. Reproducing Robotic Simulations for Reinforcement Learning with Gym-Ignition

86. Reproducing Robotic Simulations for Reinforcement Learning with Gym-Ignition

I would like to dedicate this episode to all the ROS Developers that are doing research on reinforcement learning applied to robotics. That is a difficult subject for which there is not much about it, specially with ROS. There are some works using other frameworks and simulators but not many that use ROS as their framework. So if you are in that field ROS + Reinforcement Learning + Robots, then this episode is dedicated to you.

Today we are going to learn how we can speed our development of such algorithms for ROS robots by using Gym-Ignition.

But before going into that, let me remind you about our ROS online academy. Yes, at the Construct we have created an online academy named The Robot Ignite Academy which contains a ROS learning path for beginners. The path is composed by:

Some other robotics theory courses included are:

Of course all our courses are based on practice with simulated robots! (theory+practice)

Now let me introduce you Diego Ferigo. Diego is a PhD fellow at Italian Institute of Technology, where he is doing research about using reinforcement learning for humanoid robot locomotion. Today he is here to talk about reinforcement learning with ROS, and about the framework he has developed for that, the Gym-Ignition.

Welcome to the podcast Diego!

Related Links

Subscribe to the podcast using any of the following methods

Or watch the video interview

 

85. ROS2 Control with Bence Magyar

85. ROS2 Control with Bence Magyar

Today we are going to learn about the current status of ROS2 Control, you know, the packages that allow us to control joints using ROS topics.

But before going into that, let me remind you about our ROS online academy. Yes, at the Construct we have created an online academy named The Robot Ignite Academy which contains a ROS learning path for beginners. The path is composed by:

Some other robotics theory courses included are:

Of course all our courses are based on practice with simulated robots! (theory+practice)

Now let me introduce you Bence Magyar. Bence and I we worked together at Pal Robotics. Now he works as Lead software engineer for FiveAI. But the main reason he is here with us today is because he is the main maintainer of the ROS control packages.

Welcome to the podcast Bence!

Related Links

Subscribe to the podcast using any of the following methods

Or watch the video interview

 

84. Hybrid ROS1 ROS2 Industrial applications

84. Hybrid ROS1 ROS2 Industrial applications

This episode is dedicated to all those pioneers that are building industrial applications with ROS2. That is a tough position to be because there is a lot of uncharted territory. It is very hard to get results. That is for the really brave ROS Developers. You are making ROS2 a reality in industry. Thank you for moving forward the frontiers of ROS2. This episode is dedicated to you.

Today we are going to talk with some guys from SWRI and ROS-Industrial consortium that have just done that: built hybrid applications with ROS1 and ROS2 on industrial robots.

But before going into that, let me remind you about our ROS online academy. Yes, at the Construct we have created an online academy named The Robot Ignite Academy which contains a ROS learning path for beginners. The path is composed by:

Some other robotics theory courses included are:

Of course all our courses are based on practice with simulated robots! (theory+practice)

Now let me introduce you Joseph Schornak and Jorge Nicho. They are research engineers at Southwest Research Institute in charge of software development for robotics systems in industrial environments. They are here today to talk about a hybrid ROS1 and ROS2 system for industrial robots that they have built.

Related Links

Subscribe to the podcast using any of the following methods

Or watch the video interview

83. Real Time Control in ROS with Luca Marchionni

83. Real Time Control in ROS with Luca Marchionni

This episode is dedicated to all those people that building humanoid robots with ROS and need extra care in their control algorithms (otherwise the robot falls down)

Today we have a super very special guest with who we are going to talk about how achieve real time control under ROS.

But before going into that, let me remind you about our ROS online academy. Yes, at the Construct we have created an online academy named The Robot Ignite Academy which contains a ROS learning path for beginners. The path is composed by:

Some other robotics theory courses included are:

Of course all our courses are based on practice with simulated robots! (theory+practice)

Now let me introduce you Luca Marchionni. What can I say about Luca? Luca and I we have worked together for 5 years at Pal Robotics designing navigation algorithms for the humanoid robots. Then Luca worked on problems of control of closed loop systems, whole body control, walking, motion planning and control for the human size humanoid robots built at Pal Robotics. For that he had to develop algorithms with real time control using ROS. Now Luca is the CTO of Pal Robotics and he is in charge of the technical vision of the company.

Welcome to the podcast Luca!

Related Links

Subscribe to the podcast using any of the following methods

Or watch the video interview

82. Available ROS2 Hardware

82. Available ROS2 Hardware

Today we are going to talk about robots that exist running ROS2 as well as sensors that have ROS2 drivers available.

But before going into that, let me remind you about our ROS online academy. Yes, at the Construct we have created an online academy named The Robot Ignite Academy which contains a ROS learning path for beginners. The path is composed by:

Some other robotics theory courses included are:

Of course all our courses are based on practice with simulated robots! (theory+practice)

About the robots available

Turtlebot 3, by Robotis

This was the first commercial robot able to run ROS2 on it. Turtlebot3 was designed to run ROS1 by default, so if you buy it, it will come with ROS1 pre-installed. However, the guys from Robotis quickly prepared a tutorial about how to make your Turtlebot3 run ROS2. The full tutorial is here.

Hands-on With TurtleBot 3, a Powerful Little Robot for Learning ROS - IEEE  Spectrum

ROSbot, by Husarion.

Again, this robot default system is ROS1 but Husarion has released a full tutorial about how to change the default ROS version to ROS2. The full tutorial is here.

Husarion

Rover Zero, by Rover Robotics

Same procedure as the previous 2. Default system is ROS1 but Rover provides a git repo with the code and instructions about how to install the ROS2 drivers for that robot. Check it out here.

Hadabot, by Hadabot

This is the first ROS2 native robot I have seen. It is a very simple robot with the main purpose of learn ROS2 while applying it to the real robot. Basically, just a pair of wheels with encoders, more than enough for learning basic ROS2. Check it out here.

Running Robot Operating System, ROS2, from the Web Browser with Docker –  Full-Stack Feed

e-puck 2, by GCTronic.

The e-puck 2 robot is a very small and cool robot with lots of sensors. The e-puck 2, from conception, it has nothing to do with ROS. However, recently Cyberbotics company created a ROS2 driver for that robot so we can now use this excellent robot with our favorite ROS. Here the drivers with tutorials.

e-puck v.2 – RoadNarrows Robotics

Open Manipulator, by Robotis

This is the only arm robot running ROS2 that I’m aware of. It is produced by the creators of the Turtlebot3 and, again, the robot boots initially with ROS1. However, the Robotis team have created a detailed tutorial about how to set this manipulator work with ROS2. Find the tutorial here.

OpenManipulator

About the sensors avaialble

Laser / LIDAR Sensors

  • Velodyne lidars: Drivers here for ROS2 Dashing
  • SICK lidars: Check this page for the drivers and the list of supported LIDARS
  • EAI YDLIDAR: Drivers here
  • Ouster OS-1 3D lidars: Drivers here for ROS2 Foxxy
  • Slamtech RPLidar: Drivers here (select the ROS2 branch).
  • Hokuyo URG laser: Drivers here.

Cameras

Point Cloud Devices

  1. Orbbec Astra: Drivers here for ROS2 Dashing
  2. Intel RealSense D400 series cameras: Drivers here for ROS2 Dashing
  3. Xsense device: Drivers developed inside the Autoware.Auto project. Get them here.

IMU sensors

  • IMU Bosch BNO055: Drivers here
  • TrackIMU: Drivers here.
  • SBG System IMU: Drivers here for ROS2 Foxy

GPS

  • MNEA navsat based devices: Drivers here
  • NovAtel GPS: Drivers here for ROS2 Dashing

Radars

  • Denso Toyota/Lexus radar: Drivers here

Subscribe to the podcast using any of the following methods

Pin It on Pinterest