Benchmark Feature Detection Method for Mobile Robot Automatic Drilling System Integrated with Deep Learning

Abstract

Benchmark feature detection is critical in mobile robot automatic drilling systems for compensating robot accuracy and assembly errors in aerospace manufacturing. System accuracy is influenced by reference feature recognition, which is often hindered by material interference and background noise. To address these issues, this paper proposes a method that uses a 2D industrial camera for image capture, applies deep learning for initial target recognition and positioning, and then determines the feature extraction location based on the initial recognition. The extracted benchmark positions are accurately fitted using an improved Huber algorithm. Experimental results demonstrate that this approach improves the benchmark feature detection recognition rate by 43.8%, center recognition accuracy by 78.26%, and overall hole processing accuracy by 54.69%.