Empirical Design of a Robotic Arm Control System based on Flex Sensors with Artificial Intelligence (AI) Association

The evolution of robotic control systems has significantly transformed industries ranging from manufacturing to healthcare. This paper presents an empirical design of a robotic arm control system based on flex sensors, integrated with Artificial Intelligence (AI) for enhanced precision and responsiveness. The proposed system utilizes a Hybrid CNN-RNN model for effective feature extraction and sequence learning from sensor data, followed by Support Vector Machine (SVM) classification. An AutoEncoder is employed for dimensionality reduction, optimizing the data input to the AI models. The final decision-making is executed through an ensemble of Decision Trees and Artificial Neural Networks (ANN), while Long Short-Term Memory (LSTM) networks are utilized for predictive movement control. Experimental evaluations demonstrate that the proposed model outperforms nine existing models across multiple performance metrics. The proposed system achieved an accuracy of 96.88%, with a response time of 24.3 milliseconds, and a precision rate of 96.00%. Additionally, the system exhibited remarkable robustness with only a 4.1% performance degradation under noisy conditions. The results highlight the potential of AI-assisted flex sensor-based control systems for applications requiring high precision and real-time responsiveness. This study provides a robust foundation for future advancements in robotic control systems, with potential applications in industrial automation, medical robotics, and assistive technologies.