This study performed a health care utilization analysis between robotic arm assisted total knee arthroplasty (rTKA) and manual total knee arthroplasty (mTKA) techniques. Specifically, we compared (1) index costs and (2) discharge dispositions, as well as (3) 30-day (4) 60-day, and (5) 90-day (a) episode-of-care costs, (b) postoperative health care utilization, and (c) readmissions. The 100% Medicare Standard Analytical Files were used for rTKAs and mTKAs performed between January 1, 2016, and March 31, 2017. Based on strict inclusion–exclusion criteria and 1:5 propensity score matching, 519 rTKA and 2,595 mTKA patients were analyzed. Total episode payments, health care utilization, and readmissions, at 30-, 60-, and 90-day time points were compared using generalized linear model, binomial regression, log link, Mann–Whitney, and Pearson's chi-square tests. The rTKA versus mTKA cohort average total episode payment was US$17,768 versus US$19,899 (p < 0.0001) at 30 days, US$18,174 versus US$20,492 (p < 0.0001) at 60 days, and US$18,568 versus US$20,960 (p < 0.0001) at 90 days. At 30 days, 47% fewer rTKA patients utilized skilled nursing facility (SNF) services (13.5 vs. 25.4%; p < 0.0001) and had lower SNF costs at 30 days (US$6,416 vs. US$7,732; p = 0.0040), 60 days (US$6,678 vs. US$7,901, p = 0.0072), and 90 days (US$7,201 vs. US$7,947, p = 0.0230). rTKA patients also utilized fewer home health visits and costs at each time point (p < 0.05). Additionally, 31.3% fewer rTKA patients utilized emergency room services at 30 days postoperatively and had 90-day readmissions (5.20 vs. 7.75%; p = 0.0423). rTKA is associated with lower 30-, 60-, and 90-day postoperative costs and health care utilization. These results are of marked importance given the emphasis to contain and reduce health care costs and provide initial economic insights into rTKA with promising results.