Python sample code and guide documents covering autonomous vehicle control algorithms, intended as a beginner-friendly study resource.
rlxai/rbot
An open-source ROS 2 Jazzy and Gazebo Harmonic simulation stack for autonomous mobile robots, covering mapping, localization and Nav2 navigation.
- Stars
- 122
- Forks
- 27
- Open issues
- 0
- Last commit
- 7 days ago
What is it?
rbot is a simulation-first reference stack for autonomous mobile robots (AMRs) built on ROS 2 Jazzy and Gazebo Harmonic. It brings together a robot description (URDF/Xacro), Gazebo simulation, ros2_control, joystick and keyboard teleoperation, simulated sensors, EKF and AMCL localization, SLAM Toolbox mapping, and Nav2 navigation in a single ROS 2 workspace.
The project targets people who want a working AMR baseline to run, inspect and modify, covering the full path from mapping a warehouse-style environment to navigating within the saved map. Simulated sensors include a 2-D LiDAR, IMU, depth and stereo cameras, and GPS. Gazebo Harmonic is the only supported simulator today; Isaac Sim packages exist as scaffolding for future integration.
Setup is Docker-first, with Docker Compose, a VS Code Dev Container and native Ubuntu 24.04 instructions all provided. The repository includes example maps, several bundled Gazebo worlds, CI and tests.
Key features
- 01Gazebo Harmonic simulation with demo and benchmark warehouse worlds.
- 02ros2_control differential-drive setup with joystick and keyboard teleoperation.
- 03Simulated 2-D LiDAR, IMU, depth and stereo cameras, and GPS.
- 04SLAM Toolbox mapping with a saved-map workflow, plus AMCL and EKF localization.
- 05Nav2 navigation using an MPPI controller and SMAC Hybrid-A* planner.
Use cases
- Learning the ROS 2 and Nav2 mapping-to-navigation pipeline without physical hardware.
- Prototyping navigation or localization configs in a simulated warehouse.
- Providing a Docker-based AMR baseline for a robotics team to adapt to its own robot.
Quick start
- 1
Install Docker with Compose support on the host
- 2
Build and run the Gazebo simulation stack
bash scripts/run_sim.sh - 3
Start teleoperation to drive the robot
docker compose -f docker/docker-compose.yml run --rm teleop
Things to know
- Gazebo Harmonic is the only supported simulator; Isaac Sim is scaffolding only.
- Targets Ubuntu 24.04 with ROS 2 Jazzy, so other platforms need extra setup.
- License is listed as NOASSERTION in metadata, though the README mentions Apache 2.0; verify before reuse.
In collections
Topics
FAQ
- What is rbot?
- An open-source ROS 2 Jazzy and Gazebo Harmonic simulation stack for autonomous mobile robots, covering mapping, localization and Nav2 navigation. rbot is a simulation-first reference stack for autonomous mobile robots (AMRs) built on ROS 2 Jazzy and Gazebo Harmonic. It brings together a robot description (URDF/Xacro), Gazebo simulation, ros2_control, joystick and keyboard teleoperation, simulated sensors, EKF and AMCL localization, SLAM Toolbox mapping, and Nav2 navigation in a single ROS 2 workspace.
- Is rbot free to use? What license does it have?
- rbot is open source under the Other license. Check the license terms before using it in commercial products.
- Is rbot still maintained?
- Actively maintained. The last commit to rbot was on Oct 30, 2026.
- What can I use rbot for?
- Learning the ROS 2 and Nav2 mapping-to-navigation pipeline without physical hardware. Prototyping navigation or localization configs in a simulated warehouse. Providing a Docker-based AMR baseline for a robotics team to adapt to its own robot.
- How do I install rbot?
- Install Docker with Compose support on the host Build and run the Gazebo simulation stack: bash scripts/run_sim.sh Start teleoperation to drive the robot: docker compose -f docker/docker-compose.yml run --rm teleop
- Where can I get rbot?
- The source code and installation instructions are on GitHub: https://github.com/rlxai/rbot
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open source robotics simulator with physics, 3D rendering, sensor models and a graphical interface, the latest version of Gazebo.
A simulation environment built on Gazebo and ROS 2 for testing unmanned surface vehicles in marine scenarios, based on RobotX competition tasks.
Lightweight 2.5D dynamics simulator for wheeled mobile robots and vehicles, usable standalone, via ROS 1/2, or from C++ and Python.
A Gazebo Sim and ROS 2 simulator for the Crazyflie 2.x nano-quadcopter, with its flight controllers, ported from the ROS 1 RotorS-based CrazyS.
A framework on NVIDIA Isaac Sim for simulating multirotor drones, with PX4 and ArduPilot autopilot integration and a Python control interface.