Intelligent Obstacle Avoidance and Object Manipulation
Introduction
This project leverages the Robomaster EP robot for autonomous obstacle detection, object color identification, and precise object placement on a 6×8 grid. Using components like an IR sensor, robotic arm, and camera, the robot autonomously navigates the grid, maps obstacles, detects object colors, and transports objects to designated drop-off points.
Mapping
The robot begins at a specific grid location and autonomously traverses the grid row by row, detecting obstacles and drop-off markers.
- Yaw Correction: Adjusts yaw angle upon entering each row to reduce orientation errors, ensuring accurate movement across the grid.
- Grid Generation: Creates a visual representation of the grid, marking obstacles and pathways for optimized traversal.
Detection
The robot moves closer to objects and captures images to detect colors accurately.
- Color Identification: Uses image processing techniques to convert RGB to HSV, isolating color using red, blue, and green masks.
- Dominant Color Analysis: Analyzes each mask to determine the primary color of the object, allowing for reliable classification.
Navigation
Uses pathfinding algorithms to guide the robot from its start position to obstacles and drop-off points.
- Pathfinding: Employs the BFS (Breadth First Search) algorithm to determine the optimal path, avoiding obstacles and ensuring efficient navigation.
- Object Handling: The robot aligns itself with each object using IR sensor data, grips the object, and transports it to the designated location.
- Yaw Control: Maintains consistent orientation across navigation tasks, with specific adjustments for precise object placement at each drop-off point.
