The robot combines LIDAR-based SLAM for environment mapping with YOLOv5 object detection for real-time tracking and positioning. The system uses inverse kinematics algorithms to translate high-level movement commands into precise servo motor control, enabling fluid manipulation. Path planning algorithms navigate between targets while maintaining control, creating a cohesive system that demonstrates advanced robotics principles in challenging real-world applications. The technical implementation spans both hardware and software domains. On the hardware side, we've developed custom actuator control systems with CAN bus communication, integrated multi-sensor fusion using LiDAR, cameras, and IMU sensors for comprehensive perception, and built real-time embedded systems using QNX RTOS for critical control loops. The software architecture leverages ROS 2 for distributed computing and modular design, implements computer vision using OpenCV and deep learning models for object recognition and environmental understanding, and utilizes MoveIt2 for complex manipulation tasks with real-time control loops in C++. GitHub