Robotic‐assisted bronchoscopy (RAB) is a newly developed bronchoscopic technique for the diagnosis of peripheral pulmonary lesions (PPLs). The objective of this meta‐analysis was to analyze the diagnostic yield and safety of RAB in patients with PPLs. Five databases (PubMed, Embase, Web of Science, CENTRAL, and ClinicalTrials.gov) were searched from inception to April 2023. Two independent investigators screened retrieved articles, extracted data, and assessed the study quality. The pooled diagnostic yield and complication rate were estimated. Subgroup analysis was used to explore potential sources of heterogeneity. Publication bias was assessed using funnel plots and the Egger test. Sensitivity analysis was also conducted to assess the robustness of the synthesized results. A total of 725 lesions from 10 studies were included in this meta‐analysis. No publication bias was found. Overall, RAB had a pooled diagnostic yield of 80.4% (95% CI: 75.7%–85.1%). Lesion size of >30 mm, presence of a bronchus sign, and a concentric radial endobronchial ultrasound view were associated with a statistically significantly higher diagnostic yield. Heterogeneity exploration showed that studies using cryoprobes reported better yields than those without cryoprobes (90.0%, 95% CI: 83.2%–94.7% vs. 79.0%, 95% CI: 75.8%–82.2%, p < 0.01). The pooled complication rate was 3.0% (95% CI: 1.6%–4.4%). In conclusion, RAB is an effective and safe technique for PPLs diagnosis. Further high‐quality prospective studies still need to be conducted.