A Novel eXtreme Gradient Boosting‐Shapley Additive Explanation Calibration Method for Six‐Axis Force/Torque Sensors

ABSTRACT Calibration is a crucial approach to enhancing the accuracy performance of six‐axis force/torque sensors. Although the least squares method is a widely used framework for six‐axis sensor calibration, it struggles to accurately capture the nonlinear relationship between analog and digital signals. Furthermore, traditional methods have difficulty in effectively addressing interaxis crosstalk in six‐axis force/torque sensors. This paper proposes an eXtreme Gradient Boosting (XGBoost) ensemble learning calibration algorithm, where the density‐based spatial clustering of applications with noise (DBSCAN) model is utilized to train sample weights and eliminate the interference of outliers. By leveraging the strong fitting and generalization capabilities of ensemble learning, the proposed method addresses both nonlinear relationships and crosstalk in calibration data. However, the inherent limitations of black‐box models have raised concerns about the appropriateness of machine learning and ensemble learning paradigms in the calibration process. To ensure the reliability and rationality of the calibration algorithm, this paper employs the shapley additive explanation (SHAP) model for interpretability analysis. Comparison with least squares method (LS), numerical and experimental results validate the effectiveness of the proposed calibration algorithm, demonstrating a significant improvement in the accuracy of the six‐axis force/torque sensor while reducing inter‐axis crosstalk. The Type I error of is reduced by [56.7%,65.6%,54.2%,27.5%,9%,99.9%] , while the Type II error is reduced by [68.3%,64%,2.1%,22.1%,7.6%,99.9%] .