Ultrasound imaging has emerged as a crucial tool for the diagnosis and navigation of spinal diseases. However, high-quality image acquisition heavily relies on experienced sonographers, which restricts its further popularization. In this paper, a robotic system designed for automated spinal ultrasound scanning is proposed. Drawing inspiration from the spinal anatomy and the actions of seasoned sonographers, the system integrates both a deep learning agent and a reinforcement learning agent to collaboratively guide the adjustment of the ultrasound probe in external-vision-independent environments, relying on real-time ultrasound images and contact force. Then, a hybrid force-to-velocity control framework is proposed to ensure proper ultrasound coupling during the scanning process. Experimental results on a phantom and human participants demonstrated that this system can accurately track spinal features (mean error: less than 1 mm) and maintain normal probe orientation (out-of-plane angular error: $1.61~pm ~1.1^{circ }$ , in-plane angular error: $1.27~pm ~0.9^{circ }$ ), resulting in high-quality and reproducible ultrasound images. Overall, our system shows great potential for clinical applications. Note to Practitioners—This paper is motivated by the increasing needs of human-robot interaction in medical applications, with a specific emphasis on robotic ultrasound imaging. Clinical sonographers suffer from repetitive workload during the diagnostic process, highlighting the significance of automated scanning solutions. In this work, we propose a modular control framework for ultrasound probe positioning that supports a multi-modal autonomous ultrasound scanning system. The system operates independently of external optics or prior geometric knowledge of the scanning object. Comprehensive experimental results demonstrate that the system can effectively cover the region of interest of the spine, facilitating high-quality ultrasound image acquisition and related disease assessment. This advancement is expected to enhance the efficiency of human-robot interaction in healthcare settings and holds promising clinical applications. Furthermore, our research offers valuable insights for the implementation of robotic ultrasound scanning systems applicable to other human tissues.
