A production-ready simulation environment for UAV (drone) and UGV (ground vehicle) development using GPS-denied navigation with vision-based localization, while maintaining GPS-based geofencing for safety.

Navigation Mode: All vehicles navigate using relative positioning only:

Visual odometry from cameras
Optical flow sensors
IMU integration
Visual landmark tracking
Local coordinate frames

GPS Usage: GPS is ONLY used for:

Geofencing (safety boundaries)
NOT used for waypoint navigation
NOT used for position control

System Requirements

Ubuntu 22.04 LTS (or 24.04)
16GB RAM recommended (8GB minimum)
50GB disk space (for ArduPilot + Gazebo)
NVIDIA GPU recommended but not required

Supported Platforms

Native Ubuntu Linux
Windows WSL2 with Ubuntu 22.04

Installation (One Command)

# Clone the repository
git clone https://git.sirblob.co/SirBlob/simulation.git
cd simulation

# Run the complete setup (installs everything)
bash setup.sh

The setup script installs:

ROS 2 Humble
Gazebo 11
ArduPilot SITL
ardupilot_gazebo plugin
MAVROS
Python dependencies

Note: Full installation takes 20-40 minutes depending on your internet speed.

Quick Start

# Navigate to project
cd ~/simulation  # or wherever you cloned it

# Activate environment (sets up ROS 2, Gazebo, ArduPilot, Python)
source activate_venv.sh

# Run simulation
bash scripts/run_simulation.sh

# For WSL (if graphics issues):
bash scripts/run_simulation.sh --software-render

Controlling the UAV

Once the simulation is running, control via ROS 2:

# Arm the drone
ros2 service call /mavros/cmd/arming mavros_msgs/srv/CommandBool "{value: true}"

# Set GUIDED mode (allows position control)
ros2 service call /mavros/set_mode mavros_msgs/srv/SetMode "{custom_mode: 'GUIDED'}"

# Takeoff to 5 meters
ros2 service call /mavros/cmd/takeoff mavros_msgs/srv/CommandTOL "{altitude: 5}"

# Fly to position (LOCAL coordinates - no GPS!)
ros2 topic pub /mavros/setpoint_position/local geometry_msgs/PoseStamped \
  "{header: {frame_id: 'map'}, pose: {position: {x: 10, y: 5, z: 5}}}"

# Land
ros2 service call /mavros/cmd/land mavros_msgs/srv/CommandTOL "{}"

Features

Iris quadcopter with dual cameras (forward + downward)
Ground vehicle (UGV) with vision sensors
Visual odometry - camera-based position estimation
Optical flow - velocity estimation from downward camera
GPS geofencing - safety boundaries only
ArduPilot SITL - real flight controller firmware
MAVROS - ROS 2 interface for MAVLink
Multiple worlds - indoor warehouse, urban canyon

┌─────────────────────────────────────────────────────┐
│              Vision Sensors                         │
│  Forward Camera + Downward Camera + Optical Flow    │
└─────────────────┬───────────────────────────────────┘
                  │
                  ▼
┌─────────────────────────────────────────────────────┐
│         Visual Odometry & Feature Tracking          │
│  Estimates relative position from camera motion     │
└─────────────────┬───────────────────────────────────┘
                  │
                  ▼
┌─────────────────────────────────────────────────────┐
│         Position Estimator (EKF Fusion)             │
│  Fuses: Visual Odom + Optical Flow + IMU            │
│  Output: Local position estimate (relative)         │
└─────────────────┬───────────────────────────────────┘
                  │
                  ▼
┌─────────────────────────────────────────────────────┐
│         ArduPilot Flight Controller                 │
│  Receives position via MAVROS (external nav)       │
│  Controls motors based on local setpoints           │
└─────────────────────────────────────────────────────┘

Project Structure

simulation/
├── setup.sh                 # One-command installation
├── activate_venv.sh         # Environment activation
├── scripts/
│   ├── run_simulation.sh    # Launch full simulation
│   └── kill_simulation.sh   # Stop all processes
├── worlds/                  # Gazebo world files
├── models/                  # UAV and UGV models
├── src/
│   ├── vision/              # Visual odometry, optical flow
│   ├── localization/        # EKF sensor fusion
│   ├── navigation/          # Path planning
│   ├── control/             # UAV/UGV controllers
│   └── safety/              # Geofencing
├── config/                  # Configuration files
└── docs/                    # Documentation

Documentation

Setup Guide - Detailed installation
WSL Setup Guide - Windows WSL2
Usage Guide - How to use
Architecture - System design
GPS-Denied Navigation - Navigation approach
Troubleshooting - Common issues

Simulation Options

# Default (ArduPilot Iris world)
bash scripts/run_simulation.sh

# Custom world
bash scripts/run_simulation.sh --world worlds/indoor_warehouse.world

# Rover instead of copter
bash scripts/run_simulation.sh --vehicle rover

# Software rendering (WSL/no GPU)
bash scripts/run_simulation.sh --software-render

Aspect	GPS Navigation	This Project (GPS-Denied)
Position Source	GPS satellites	Visual odometry + sensors
Waypoint Type	GPS coordinates	Relative coordinates (x,y,z)
Reference Frame	Global (lat/lon)	Local (relative to start)
Indoor Capability	No	Yes
Drift	Minimal	Accumulates over time
Geofencing	GPS-based	GPS-based (safety only)

README.md

UAV-UGV Gazebo SITL Simulation

GPS-Denied Navigation with Geofencing

Key Feature: GPS-Denied Navigation