The agricultural industry continually seeks innovative methods to improve quality control and to reduce waste. This paper proposes an automated solution for apple freshness detection and depth calculation. The developed system utilizes a mobile robot equipped with a stereo camera setup and advanced machine learning algorithms. The core of the system is the YOLOv8 model, trained to classify apples as fresh or rotten. The stereo camera setup, composed of two ESP32 cameras, is calibrated to compute depth information accurately. The robot navigates using tele-operation control and processes images in real-time to detect apple freshness and measure depth. Extensive testing demonstrated the system’s high accuracy, achieving \(97\%\) accuracy for fresh apple detection and \(85\%\) for rotten apple detection. The stereo camera setup provided reliable depth measurements, ensuring precise spatial awareness of the detected apples. The paper highlights the integration of computer vision and robotics to enhance agricultural quality control processes, offering a practical and effective solution for automated apple freshness detection and depth calculation. The findings suggest that with further improvements, this system could be commercially viable, benefiting the agricultural industry significantly.