Advances in Artificial Intelligence Enhanced Robotics for Dental Implant Placement: A Scoping Review

To map current evidence on artificial intelligence (AI)-enhanced robotic systems for dental implant placement, focusing on system autonomy, accuracy, and clinical applicability. This mixed-method scoping review followed PRISMA-ScR guidelines and included studies published up to August 2025. Five electronic databases were systematically searched (PubMed, Scopus, Web of Science, Embase, Cochrane Library), supplemented by grey literature search, to identify English-language studies assessing robotic-assisted dental implant placement in terms of accuracy, time efficiency, or clinical feasibility. Two reviewers independently performed study selection, data extraction, and quality appraisal. Quantitative data were pooled descriptively using random-effects models with subgroup analyses, while remaining findings were synthesized narratively. A parallel search identified commercially available robotic and dynamic navigation systems, including their regulatory status, validation level, and human–robot interaction features. The systematic search identified 27 studies evaluating robotic-assisted dental implant placement met the inclusion criteria. Methodological quality was generally high, with 92.6% of studies scoring ≥ 8/10 on the Mixed Methods Appraisal Tool (MMAT). Robotic systems demonstrated high placement accuracy, with a mean coronal deviation of 0.45 mm, apical deviation of 0.50 mm, and angular deviation of 0.80°. However, statistical heterogeneity was high across outcomes (I² > 97%). Subgroup analyses indicated that fully autonomous robotic systems achieved the lowest deviation values. Implant placement in the mandible showed greater accuracy compared with maxillary and zygomatic sites. When compared with dynamic navigation systems, robotic-assisted approaches demonstrated comparable linear deviations but superior angular precision. Limited evidence suggested potential improvements in procedural efficiency, particularly in multi-implant cases. Robotic systems show strong technical performance, but current evidence is dominated by in vitro and single-center studies with limited long-term clinical data. Future multicenter trials with standardized outcomes and long-term follow-up are needed to confirm clinical benefits. Robotic systems offer high accuracy and reproducibility in dental implant placement, potentially improving efficiency and reducing variability in complex cases. However, clinical adoption should be guided by further multicenter trials with long-term outcomes.