Teleoperation and SLAM using Jetson Nano and ROS 2


I would like to share the current progress of my autonomous mobile robot project using Jetson Nano.

It’s undeniable that Mobile robots are becoming increasingly important for a wide range of industries​. Today we can find them in warehouses, distribution centers, manufacturing intralogistics, hospitals, and agriculture. Moreover, the future holds a further expansion of Mobile Robots into unstructured environments like roads, sidewalks, homes, etc. ​

In general, an autonomous mobile robot consists of the following components: Sensing, Perception, Mapping, Localization, Planning, and Control.

This project currently focuses on sensing, perception, mapping, localization, and teleoperation aspects of an AMR.

So far, the software includes the following functionalities:

  • Teleoperation through WebSockets with live video feed using Webrtc, i.e., aiortc.

  • Custom Integration of Realsense d435 and t265 cameras for depth estimation and localization respectively.

  • 2D SLAM with cartographer.

  • 3D SLAM using Rtabmap: GitHub - introlab/rtabmap_ros at ros2

The software is implemented using ros2 and it’s still a work in progress. You can find the repo here: GitHub - jdgalviss/jetbot-ros2: ROS 2 implementation of a Teleoperated robot with live video feed using webrtc and SLAM using realsense's stereocameras. Running on a Jetson Nano



Great project!