RoboPick: ArUco-Driven Task Prioritized Manipulation on Mobile Robotic Systems

This paper presents RoboPick, an advanced Vehicle-Manipulator System (VMS) designed to perform efficient and precise object manipulation tasks. The system integrates a TurtleBot 2 mobile base with a 4-DOF Swift Pro robotic arm, enabling the robot to autonomously navigate and interact with its environment. The system is equipped with an Intel RealSense D435i camera and ArUco markers for accurate object localization and positioning. The control system uses a task-priority algorithm to ensure that the robot performs pick-and-place operations efficiently, while adhering to safety constraints and maintaining high precision throughout. Behavior trees are implemented to manage the sequence of operations, ensuring that the robot executes tasks smoothly and effectively. The system's capabilities are validated through extensive simulation tests, demonstrating its high reliability and consistent efficiency in completing tasks. The robot's performance in terms of task completion time and success rate highlights its robustness in handling complex manipulation routines across multiple trials. This research emphasizes the importance of combining robust control architectures with precise localization techniques to enhance the performance of autonomous mobile manipulators in real-world object manipulation applications.