This paper presents a fully autonomous robotic ultrasound system (FARUS) designed for thyroid scanning, aiming to reduce the reliance on human expertise and improve the efficiency and consistency of thyroid ultrasound examinations. FARUS integrates the roles of sonographers and radiologists, performing in-plane and out-of-plane scanning to provide comprehensive thyroid evaluations. The system uses human skeleton point recognition, reinforcement learning, and force feedback to locate thyroid targets accurately. Bayesian optimization is employed to dynamically adjust the orientation of the ultrasound probe, ensuring high-quality images. The system's performance is validated through experiments on human participants, demonstrating that it can produce high-quality ultrasound scans comparable to those obtained by clinicians. Additionally, FARUS can detect thyroid nodules and provide data for ACR TI-RADS classification. The study includes a comparative evaluation of FARUS-driven diagnostic results against established hospital benchmarks, showing good agreement with clinical practices. The system's potential for rapid screening in outpatient clinics and remote centers is highlighted, along with its advantages in minimizing the risk of infectious disease transmission. However, the paper also discusses limitations, such as challenges in detecting small or low-contrast nodules, and suggests further improvements and clinical studies are needed to enhance its reliability and safety.This paper presents a fully autonomous robotic ultrasound system (FARUS) designed for thyroid scanning, aiming to reduce the reliance on human expertise and improve the efficiency and consistency of thyroid ultrasound examinations. FARUS integrates the roles of sonographers and radiologists, performing in-plane and out-of-plane scanning to provide comprehensive thyroid evaluations. The system uses human skeleton point recognition, reinforcement learning, and force feedback to locate thyroid targets accurately. Bayesian optimization is employed to dynamically adjust the orientation of the ultrasound probe, ensuring high-quality images. The system's performance is validated through experiments on human participants, demonstrating that it can produce high-quality ultrasound scans comparable to those obtained by clinicians. Additionally, FARUS can detect thyroid nodules and provide data for ACR TI-RADS classification. The study includes a comparative evaluation of FARUS-driven diagnostic results against established hospital benchmarks, showing good agreement with clinical practices. The system's potential for rapid screening in outpatient clinics and remote centers is highlighted, along with its advantages in minimizing the risk of infectious disease transmission. However, the paper also discusses limitations, such as challenges in detecting small or low-contrast nodules, and suggests further improvements and clinical studies are needed to enhance its reliability and safety.