The development of a new generation of minimally invasive surgery is mainly reflected in robot-assisted diagnosis and treatment methods and their clinical applications. It is a clinical concern for robot-assisted surgery to use a multi-joint robotic arm performing human ultrasound scanning or ultrasound-guided percutaneous puncture. Among them, the motion control of the robotic arm, and the guiding and contact scanning processes of the ultrasonic (US-) probe determine the diagnosis effect, as well as the accuracy and safety of puncture surgery. To address these challenges, this study developed an intelligent robot-assisted system integrating autonomous US inspection and needle positioning, which has relation to several intelligent algorithms such as adaptive flexible control of the robot arm, autonomous US-scanning, and real-time attitude adjustment of the puncture needle. To improve the cooperativity of the spatial operation of the robot end-effector, we propose an adaptive flexible control algorithm that allows the operator to control the robot arm flexibly with low damping. To achieve the stability and uniformity of contact detection and imaging, we introduced a self-scanning method of US-probe based on reinforcement learning and built a software model of variable stiffness based on MuJoco to verify the constant force and velocity required by the end mechanism. We conducted a fixed trajectory scanning experiment at a scanning speed of 0.06 m/s. The force curve generally converges towards the desired contact force of 10 N, with minor oscillations around this value. For surgical process monitoring, we adopted the puncture needle detection algorithm based on Unet++ to acquire the position and attitude information of the puncture needle in real time. In short, we proposed and verified an adaptive control method and learning strategy by using an UR robotic arm equipped with a US-probe and puncture needle, and we improved the intelligence of the US-guided puncture robot.

The precision and stability of the Robot-Assisted Percutaneous Puncture (RAPP) system have become increasingly crucial with the widespread integration of robotic technology in the field of medicine. The accurate calibration of the RAPP system prior to surgery significantly influences target positioning performance. This study proposes a novel system calibration method that simultaneously addresses system hand–eye calibration and robot kinematic parameters calibration, thereby enhancing the surgery success rate and ensuring patient safety. Initially, a Closed-loop Hand–eye Calibration (CHC) method is employed to rapidly establish transformation relationships among system components. These CHC results are then integrated with nominal robot kinematic parameters to preliminarily determine the system calibration parameters. Subsequently, a hybrid algorithm, combining the regularized Levenberg–Marquardt (LM) algorithm and a particle filtering algorithm, is utilized to accurately estimate the system calibration parameters in stages. Numerical simulations and puncture experiments were conducted using the proposed system calibration method and other comparative methods. The experimental results revealed that, among several comparative methods, the approach presented in this paper yields the greatest improvement in the puncture accuracy of the RAPP system, demonstrating the accuracy and effectiveness of this method. In conclusion, this calibration method significantly contributes to enhancing the precision, operational capability, and safety of the RAPP system in practical applications.

In recent years, minimally invasive surgery (MIS) has become a very suitable field for robotic systems. Minimally invasive surgery which can be used for diagnosis and surgical treatment is more and more popular in the medical field. We have developed a remote vascular intervention robot system for medical applications which is integrated by several modules. During the remote operation of intervention therapy, we need to transmit CT images, robot instructions, force feedback data to make the surgery smoothly. So, we have developed an open, simple and extensible peer-to-peer communication protocol. Experiments result show that the network communication protocol can meet the requirements of real-time capability in the surgery.