Abstract: A rock-drilling jumbo is the main piece of tunneling equipment used in the energy and infrastructure industries in various countries. The positioning accuracy of its drilling boom greatly affects tunneling efficiency and section-forming quality of mine roadways and engineering tunnels. In order to improve the drilling-positioning accuracy of a three-boom drilling jumbo, we established a kinematics model of the multi degree-of-freedom (DOF) multi-boom system, using the improved Denavit-Hartenberg (D-H) method, and obtained the mapping relationship between the end position and the amount of motion of each joint. The error of the inverse kinematics calculation for the drilling boom is estimated by an analytical method and a global search algorithm based on particle swarm optimization (PSO) for a straight blasting hole and inclined blasting hole. On this basis, we propose a back-propagation (BP) neural network optimized by an improved sparrow search algorithm to predict the positioning error of the drilling booms of a three-boom drilling jumbo. In order to verify the accuracy of the proposed error-compensation model, we built an automatic-control test platform for the boom, and carried out a positioning-error compensation test on the boom. The results show that the average drilling-positioning error was reduced from 9.79 cm to 5.92 cm, and the error was reduced by 39.5%. Therefore, the proposed method effectively reduces the positioning error of the drilling boom, and improves the accuracy and efficiency of rock drilling.