Background: Accurate pedicle screw placement is one of the fundamental surgical techniques for novice orthopedists in spinal oncology education. So, we set forth to establish a computer-assisted robotic navigation training program for spinal oncology education. Novice orthopedists and patients are involved in this study to evaluate the feasibility and safety of the computer-assisted robotic navigation (CARN) training program. Methods: In this research, 2 trainees were randomly taught by the CARN training program and the traditional training program. We prospectively collected clinical data from 1st May 2021 to 1st March 2022 in 45 patients with spinal tumors, including the time of PSP, serving as primary outcomes, the accuracy of the pedicle screw, and other clinical data. Then the ability of PSP was evaluated by cumulative sum (CUSUM) analysis, learning curve, and accuracy of pedicle screws. Results: The patients included in both groups had similar baseline characteristics. 169 pedicle screws in the CARN group and 179 pedicle screws in the traditional group were evaluated in our research. In the CUSUM analysis of the learning curve for the time of PSP, the turning point in the CARN group (70th pedicle screw) was less than the one in the traditional group (92nd pedicle screw). The LC-CUSUM test signaled competency for PSP at the 121st pedicle screw in the CARN group, while 138th in the traditional group. Then the accuracy of pedicle screws showed that the rate of grade A in the Gertzbein-Robbins classification was significantly higher in the CARN group than in the traditional group (88.17% and 79.55%, P=0.03 <0.05). Furthermore, no major complications occurred in both groups. Conclusion: We firstly described computer-assisted robotic navigation in spinal oncology education. We also indicated the CARN training program as a novel education method, and an efficient and safe surgical training program in spine surgery.