Autonomous Dental Surgery for Root Canal Treatment: Compensating for Robot-Patient Misalignment and File Deflection

Robotic technologies are increasingly used in den- tistry for their precision in delicate procedures. While most dental robots focus on implant surgery, automating root canal treatment (RCT) remains challenging due to the need to guide a thin, flexible endodontic file through a narrow, curved root canal without causing ledging or file fracture. Patient movements—particularly those that induce additional file bending during insertion—further complicate robot-assisted procedures. This study presents an autonomous approach for root canal cleaning and shaping by combining force admittance and position tracking. A novel Patient Tracking Module, which con- nects the patient’s dental brace to the robot end-effector via string potentiometers, is developed to estimate real-time robot-patient pose. Additionally, a file flexibility model is proposed to predict and compensate for file deflection during insertion. A hybrid position/force control strategy, which integrates these estimations, autonomously guides file manipulation, minimizes misalignment, and therefore reduces the risk of file fracture. Experimental validation demonstrates the system’s feasibility and potential for clinical application in precision endodontic procedures. Note to Practitioners—This paper addresses the challenge of automating root canal treatment in robot-assisted endodontics, which is complicated by unpredictable patient movements and bending of endodontic files. The proposed system follows a structured workflow: (1) the dentist first diagnoses the case, labels the working length of the canal on preoperative cone- beam computed tomography (CBCT) scans, and performs access opening to the pulp chamber; (2) a custom-designed tooth brace is then installed; (3) the endodontic file held by the robot is aligned with the root canal entrance; (4) the robot is connected to the patient via a string-based Patient Tracking Module (PTM); and (5) the robot autonomously performs canal cleaning and shaping until the working length is reached. The PTM Received 13 February 2025; revised 17 June 2025 and 13 August 2025; accepted 11 September 2025. Date of publication 19 Septem- ber 2025; date of current version 26 September 2025. This article was recommended for publication by Associate Editor T. L. Lam and Editor L. Zhang upon evaluation of the reviewers’ comments. This work was supported in part by the National Science and Tech- nology Council (NSTC) in Taiwan under Grant 111-2636-E-002-028, Grant 112-2628-E-002-021-MY3, Grant 113-2314-B-075-010, and Grant 114- 2628-B-075-002; and in part by the Yin Shu-Tien Foundation Tapei Veterans General Hospital-National Yang Ming Chiao Tung University Excellent Physi- cian Scientists Cultivation Program under Grant 114-V-B-033. (Corresponding author: Cheng-Wei Chen.) Hao-Fang Cheng and Cheng-Wei Chen are with the Department of Electri- cal Engineering, National Taiwan University, Taipei 10617, Taiwan (e-mail: cwchenee@ntu.edu.tw). Yi-Ching Ho is with the Division of Endodontics, Department of Stomatol- ogy, Taipei Veterans General Hospital, Taipei 112, Taiwan, and also with the Department of Dentistry, National Yang Ming Chiao Tung University, Taipei 30010, Taiwan. This article has supplementary downloadable material available at https://doi.org/10.1109/TASE.2025.3611997, provided by the authors. Digital Object Identifier 10.1109/TASE.2025.3611997 estimates patient movement in real time and compensates for it. Combined with force sensing and file deflection compensation, the system dynamically adjusts the surgical path to maintain alignment and reduce the risk of file fracture. This improves procedural safety, precision, and efficiency. Preclinical tests on acrylic models and 3D-printed teeth show promising results, but further validation in live patient settings is needed. Future work will explore automating additional steps, such as access opening and obturation, to enhance the overall treatment workflow.