Chat with your robotics, drone, and IoT data — ChatGPT for the physical world.

Aerial Object Detection using a Drone with PX4 Autopilot and ROS 2. PX4 SITL and Gazebo Garden used for Simulation. YOLOv8 used for Object Detection.

A simple tool to generate gazebo terrain using satellite images and DEM data.

MAVLink Camera Manager Service

ROS2 package that implements a nonlinear model predictive control (NMPC) pipeline for trajectory tracking for aerial vehicles that use the PX4 Autopilot

Template to set up a simulation environment for a quadcopter equipped with a camera. Uses PX4, Gazebo and ROS2. Enable the development and testing of software for a drone with a companion computer for mission planning and computer vision.

Deep reinforcement learning for drone precision landing, docker container for simulation in Gazebo-ROS2 dashing/foxy with PX4-Autopilot RTPS controller.

Autonomous UAV navigation system featuring real-time 2.5D occupancy-grid mapping, A* global path planning, and depth + LiDAR sensor fusion for dynamic obstacle avoidance in complex urban environments. Fully integrated with ROS 2, PX4 Offboard control, and Gazebo simulation for high-fidelity testing and deployment.

UAV control and SLAM with PX4, ROS 2 Jazzy, and Gazebo Harmonic, including RL environments and YOLO-based perception and 2D lidar.

Real-time obstacle avoidance utilizing the ModalAI Sentinel Drone with the PX4 flight stack and an Intel Realsense D435i .

An Omniverse Extension for PX4-Autopilot

Obstacle avoidance for drone with cable suspended payload using RGBD Camera, Octomap and PX4 Firmware

A modular simulation framework for controlling multiple drones in a PX4-based environment. It features ROS 2 integration, G-code trajectory planning, multi-agent communication, and a Dockerized setup for easy deployment and visualization.

DroneCAN support for Arduino on STM32!

A template for generating a docker development environment suited for PX4, Gazebo and ROS2.

Read UBX M8P-2 and publish RTCM messages for mavros from ROS

A general-purpose robotic agent framework based on LLMs. The LLM can independently reason, plan, and execute actions to operate diverse robot types across various scenarios to complete unpredictable, complex tasks.

An open library of robotics data transformations

Multi-Drone Control Software w/ Trajectory Generation

A ROS package to control multi-copters via MAVROS