| Summary: | This project focuses on the modeling, control, and simulation of a UR5 robotic manipulator for effective obstacle avoidance. It utilizes CoppeliaSim for the simulation environment and Python for external control. CoppeliaSim provides a flexible and multi-functional platform for accurate modeling and simulation. It offers realistic physics foundation and rendering capabilities that enables feasible studies of UR5’s behaviors in complex environments. Python is known for its simple but powerful library ecosystem which enhance the efficient implementation of control algorithms and interacts seamlessly with CoppeliaSim via its remote API. The core objective of this project was to evaluate and compare the effectiveness of three different obstacle avoidance algorithms: Advanced Rapidly-exploring Random Trees (RRT), Probabilistic Roadmap Method (PRM), and Artificial Potential Field (APF). Each of these algorithms was implemented and tested to determine their performance in navigating the UR5 arm through obstacles during task execution. The results demonstrate that the UR5, equipped with the integrated simulation and control setup, successfully performs pick-and-place operations without collision.
|
|---|