This episode is dedicated to all those people that are thinking to move their robots to ROS2. One of the problems to move to ROS2 was the lack of a stable navigation system for ROS2 robots. But as you will learn today, this problem has been solved. So if you want to move to ROS2 and want to try to make a robot navigate, then this episode is dedicated to you.
Today we are going to talk about the ROS2 navigation stack which allows ROS2 robots to navigate autonomously.
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:
- Linux for Robotics
- Python for Robotics
- ROS Basic Concepts
- Understanding TF
- URDF for modeling robots
- ROS Control
- Build your own robot and ROSify it… and become a ROS Developer!
Now let me introduce you Steve Macenski. Steve works for Samsung Research America. There he is the open source robotics engineering lead of the company. He is a member of the board of the ROS2 Technical Steering Committee, and maintainer and developer of many important ROS2 packages related to the navigation system in ROS2.
This is the second time Steve comes to the podcast. Actually Steve was the winner of the ROS Award 2020 as the best ROS Developer of the world.
Congratulations and welcome to the podcast Steve!
Related links:
- Follow Steve Macenski on LinkedIn
- Previous interview to Steve on the ROS Developers Podcast about SLAM Toolbox
- ROS Developer Awards 2020
- The ROS2 Navigation Stack
- The ROS2 Marathon paper Steve presented at IROS2020
- SLAM Toolbox
- Behavior Trees implementation in ROS
- Podcast interview to Davide Faconti about Behavior Trees in ROS
- AMCL localization package in ROS
Subscribe to the podcast using any of the following methods
- ROS Developers Podcast on iTunes
- ROS Developers Podcast on Stitcher
Or listen to it on Spotify:
- ROS Developers Podcast on Spotify
Podcast: Play in new window | Download | Embed
SUBSCRIBE NOW: RSS
I am going to write code by using ROS, but since I m beginner, I don’t know where I have to start learning Ros for both control of manipulators and also control of multi-agent eBots for swarm control. Please advise me where I have to start from to learn it step by step for both systems mentioned above. Thanks.
Hi Vahid,
if you want to learn about control of manipulators with ROS, I sincerely recommend you our online academy where we deal about this subject deeply.
About control of multi-agent robots, our academy doesn’t have related courses. Also, there is not much work about it in ROS. I would start with the code of Swarm Base Code – ROS (https://github.com/mason-uren/MultiAgentSlam-ROS) even if it has not been updated in 2 years and it is very specific for the NASA robots (you may need to modify it for your robots).
Additionally, I know about specific applications of multi-agents, like for example, to create a map of a large space with a set of robots (check this video lecture I gave about it https://www.youtube.com/watch?v=G_RhKZUQCkc) or about patrolling an area (check this ROS package http://wiki.ros.org/patrolling_sim, a little bit outdated).
Finally, let me tell you that if you are really into swarm robots, it may be more useful for you to switch to ROS2, since it is better designed to manage multirobot systems.