Nav Sim

A lightweight 2D simulation framework for mobile robot navigation using Pygame, with support for sensors, external controllers, and interactive visualization.

Compile

python.exe -m build   

python.exe -m twine upload dist/*

sudo apt install python3-tk

Necessário colocar a API token obtida do site pipy.

🚀 Key Features

• Dual Environment Representation: Supports both traditional coordinate-based circular obstacles AND image-based Occupancy Grid Maps.
• Interactive GUI:
  • Map Loading: Load maps dynamically during simulation with custom resolution.
  • Theming: Dynamic switching between Light and Dark themes.
  • Map Panning: Drag the environment view using SHIFT + Right Click.
• Map Generation (Benchmarking): Built-in MapGenerator for 'U', 'L', and Random maze patterns.
• Precision Sensing: Ray-casting based LiDAR using DDA algorithm for accurate grid-based collision.

🏗️ Architecture

• ✅ Simulator (nav_sim): Handles physics, UI, sensors, and environment.
• ✅ Occupancy Grid: Automatic conversion of images to binary/inflated grids for collision and LiDAR.
• ✅ External Controllers: Easily pluggable navigation strategies.

Supported Robot Models

• holonomic
  Command:

  {"vx": ..., "vy": ...}
  

• differential
  Command:

  {"v": ..., "omega": ...}
  

• ackermann
  Command:

  {"speed": ..., "steer": ...}
  

📡 Sensors

LiDAR (2D)

The simulator provides a configurable 2D LiDAR:

• Angular scan
• Range-limited
• Returns (angle, distance, hit_point)

⚙️ Installation

python -m venv .venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows

pip install -r requirements.txt

▶️ Run Examples

python examples/run_holonomic.py
python examples/run_differential.py
python examples/run_maze.py

🗺️ Occupancy Grid Maps

You can define map sources directly in your config or load them dynamically:

world:
  map_image: "maze.png"
  resolution: 0.1
  show_inflation: true
theme: "dark"

⌨️ User Interaction

• Left Click: Set Waypoint.
• Right Click: Add Obstacle (opens radius dialog).
• SHIFT + Right Click: Pan/Drag the environment.
• Scroll: Zoom.
• UI Panel: Toggle LiDAR, switch themes, load new maps.

🧩 Controller Interface

def controller(robot, world, goal, config, dt, lidar_readings=None) -> dict:
    ...

🛑 Collision Handling

The simulator detects collisions using: d <= r_robot + r_obstacle

• Immediate stop.
• Visual indicator (💥) displayed.

📄 License

Free for educational and research use.