Precision Error Compensation Algorithm for Automated Drill Pipe Gripping in Underground Coal Mine Drilling Robots

ABSTRACT To address the industry challenge of traditional error compensation methods failing in large spaces under harsh conditions—such as high dust, strong vibrations, and the explosion‐proof MA certification requirements in underground coal mines—this paper proposes a novel error compensation algorithm based on zoning and Gaussian regression. It develops a sensorless compensation framework that operates within explosion‐proof constraints by integrating zonal calibration with Gaussian Process Regression (GPR), which overcomes the dual challenges of visual failure and the limited availability of MA explosion‐proof sensors. To tackle the accuracy issue in large workspaces, a three‐level partition‐boundary‐regression architecture is designed. The workspace, with a ± 20° azimuth angle and 16 layers of drill pipes, is divided into 12 sector cells. The boundary layer uses cubic polynomial error compensation, while the internal cells employ spatial continuity error prediction based on the RBF kernel function. Experimental results show a significant reduction in grasping errors after compensation ( X / Y / Z ≤ 4.5/2.5/1.5 mm), with an accuracy improvement of 82%. Additionally, an industrial downhole test has completed 2448 rod pickings with a success rate of 98.5%. This study offers a novel solution for precision control of robots in highly constrained environments.