Low Cost Control of Robotic Arms

This paper presents the practical implementation of a Kalman filter algorithm for state estimation on the Taiwan OWI robotic arm. The study highlights the integration of low-cost tools such as Arduino, HC-05 Bluetooth Module, and L298N Motor Driver Module in controlling the robotic arm. Key contributions include a novel approach to trajectory planning and path correction using imitation learning. The paper provides detailed methodologies for trajectory calculation, the role of the Extended Kalman Filter (EKF) in state estimation, and the application of AI techniques to enhance robotic arm autonomy. The results demonstrate the feasibility and effectiveness of the proposed methods, paving the way for more sophisticated robotic applications.