Purpose of Review This review provides an overview of the most recent robotic ultrasound systems that have contemporary emerged over the past five years, highlighting their status and future directions. The systems are categorized based on their level of robot autonomy (LORA). Recent Findings Teleoperating systems show the highest level of technical maturity. Collaborative assisting and autonomous systems are still in the research phase, with a focus on ultrasound image processing and force adaptation strategies. However, missing key factors are clinical studies and appropriate safety strategies. Future research will likely focus on artificial intelligence and virtual/augmented reality to improve image understanding and ergonomics. Summary A review on robotic ultrasound systems is presented in which first technical specifications are outlined. Hereafter, the literature of the past five years is subdivided into teleoperation, collaborative assistance, or autonomous systems based on LORA. Finally, future trends for robotic ultrasound systems are reviewed with a focus on artificial intelligence and virtual/augmented reality.

Most kinematic structures in robot architectures for medical tasks are not optimal. Further, the workspace and payloads are often oversized which results in high product prices that are not suitable for a clinical technology transfer. To investigate optimal kinematic structures and configurations, we have developed an adaptive simulation framework with an associated workflow for requirement analyses, modelling and simulation of specific robot kinematics. The framework is used to build simple and cost effective medical robot designs and was evaluated in a tool manipulation task where medical instruments had to be positioned precisely and oriented on the patient's body. The model quality is measured based on the maximum workspace coverage according to a configurable scoring metric. The metric generalizes among different human body shapes that are based on anthropometric data from UMTRI Human Shape. This dexterity measure is used to analyze different kinematic structures in simulations using the open source simulation tool V-REP. Therefor we developed simulation and visualization procedures for medical tasks based on a patchwork of size-variant anatomical target regions that can be configured and selectively activated in a motion planning controller. In our evaluations we compared the dexterity scores of a commercial lightweight robot arm with 7 joints to optimized kinematic structures with 6, 7 and 8 joints. Compared to the commercial hardware, we achieved improvements of 59% when using an optimized 6- dimensional robot arm, 64% with the 7-dimensional arm and 96% with an 8-dimensional robot arm. Our results show that simpler robot designs can outperform the typically used commercial robot arms in medical applications where the maximum workspace coverage is essential. Our framework provides the basis for a fully automatic optimization tool of the robot parameters that can be applied to a large variety of problems.

Optical coherence tomography (OCT) is a powerful imaging technique to non-invasively differentiate between healthy skin and pathological conditions. Unfortunately, commercially available OCT-systems are typically slow and not capable of scanning large areas at reasonable speed. Since skin lesions may extend over several square centimeters, potential inflammatory infiltrates remain undetected. Here, we present large area robotically assisted OCT (LARA-OCT) for skin imaging. Therefor a collaborative robot is combined with an existing, home-built 3.3 MHz-OCT-system and for surface tracking an online probe-to-surface control is implemented which is solely based on the OCT surface signal. It features a combined surface-distance and surface-orientation closed-loop control algorithm, which enables automatic positioning and alignment of the probe across the target while imaging. This allows to acquire coherent OCT images of skin areas beyond 10 cm².

Applications of force control and motion planning often rely on an inverse dynamics model to represent the high-dimensional dynamic behavior of robots during motion. The widespread occurrence of low-velocity, small-scale, locally isotropic motion (LIMO) typically complicates the identification of appropriate models due to the exaggeration of dynamic effects and sensory perturbation caused by complex friction and phenomena of hysteresis, e.g., pertaining to joint elasticity. We propose a hybrid model learning base architecture combining a rigid body dynamics model identified by parametric regression and time-series neural network architectures based on multilayerperceptron, LSTM, and Transformer topologies. Further, we introduce a novel joint-wise rotational history encoding, reinforcing temporal information to effectively model dynamic hysteresis. The models are evaluated on a KUKA iiwa 14 during algorithmically generated locally isotropic movements. Together with the rotational encoding, the proposed architectures outperform stateof-the-art baselines by a magnitude of 10 3 yielding an RMSE of 0.14 Nm. Leveraging the hybrid structure and time-series encoding capabilities, our approach allows for accurate torque estimation, indicating its applicability in critically force-sensitive applications during motion sequences exceeding the capacity of conventional inverse dynamics models while retaining trainability in face of scarce data and explainability due to the employed physics model prior.

Automation of the image acquisition process via robotic solutions offer a large leap towards resolving ultrasound's user-dependency. This paper, as part of a larger project aimed to develop a multipurpose 4d-ultrasonic forcesensitive robot for medical applications, focuses on achieving real-time remote visualisation for 4d ultrasound image transfer. This was possible through implementing our software modification on a GE Vivid 7 Dimension workstation, which operates a matrix array probe controlled by a KUKA LBR iiwa 7 7-DOF robotic arm. With the help of robotic positioning and the matrix array probe, fast volumetric imaging of target regions was feasible. By testing ultrasound volumes, which were roughly 880 kB in size, while using gigabit Ethernet connection, a latency of ~57 ms was achievable for volume transfer between the ultrasound station and a remote client application, which as a result allows a frame count of 17.4 fps. Our modification thus offers for the first time real-time remote visualization, recording and control of 4d ultrasound data, which can be implemented in teleoperation.