Path-Creation-on-an-Image-Using-RRT-Algorithm

This repository implements the RRT* (Rapidly-exploring Random Tree Star) algorithm for path planning in a 2D environment. The project integrates with ROS (Robot Operating System) and uses Turtlesim to visualize the planned path.

Features

• RRT Algorithm*: Efficient path planning with obstacle avoidance.
• Turtlesim Integration: Moves a turtle along the planned path in the Turtlesim simulator.
• Image-based Environment: Reads start, goal, and obstacles from an input image.
• Visualization: Displays the RRT* tree and the final path using OpenCV.

Project Structure

• Image1.png and Image2.png: Sample images defining the environment. Green represents the start point, red represents the goal, and black represents obstacles.
• move_turtle.py: ROS node to move the Turtlesim turtle along the planned path.
• RRT_Star.py: Implements the RRT* algorithm and publishes the planned path.
• turtle_rrt.launch: ROS launch file to start the Turtlesim node and the path planning nodes.

Prerequisites

• ROS (Robot Operating System) installed on your system.
• Python 3.x with the following libraries:
  • numpy
  • opencv-python
  • Pillow
• Turtlesim package installed in ROS.

Setup and Usage

1. Clone the Repository:

   git clone https://github.com/Dheeraj-yellapu/Path-Creation-on-an-Image-Using-RRT-Algorithm

2. Prepare the Environment: Ensure ROS is sourced and the required Python libraries are installed:

   pip install numpy opencv-python Pillow

3. Run the Launch File: Use the provided launch file to start the simulation:

   roslaunch turtle_rrt.launch

4. Modify the Image: Update the image_path in RRT_Star.py to point to your custom environment image.
5. Visualize the Path: The RRT* algorithm will display the tree and the final path in an OpenCV window. The turtle in Turtlesim will follow the planned path.

How It Works

• Environment Setup: The environment is defined by an image where:

  Green pixel ([34, 177, 76]) represents the start point. Red pixel ([237, 28, 36]) represents the goal point. Black pixels ([0, 0, 0]) represent obstacles.

• Path Planning: The RRT* algorithm generates a tree of possible paths and finds the optimal path to the goal while avoiding obstacles.

• Path Execution: The planned path is published as a ROS topic (/rrt_star_path), and the move_turtle.py node subscribes to this topic to move the turtle.