Learning Robotic Ultrasound Scanning Skills via Human Demonstrations and Guided Explorations

The goal of our tasks images, position of probe, pose of probe, and contact force), the policy is to autonomously acquire ultrasound images with the centered region of should yield a befitting action. As mentioned above, four different sensory modalities ultrasound images have been proposed in [16], [17], [18], are closely related to the robotic ultrasound scanning skills, [19], [20], [21]. To the best of our knowledge, this is the first unified framework that learns As shown in Figure 3, with the target to perform autonomous the robotic ultrasound scanning skills representation and the ultrasound scanning process, the ultrasound scanning skills is corresponding manipulation skills from human demonstrations represented as a policy function π(s) a, which denotes the including the modalities of ultrasound image, pose/position mapping from the current state s to the predicted action a. of the probe and the contact force. The modeling and learning of policy π about the ultrasound scanning skills is described in the following section. B. Ultrasound Skills Modeling and Learning A. Problem Formulation of Ultrasound Scanning Tasks We proposed to use a deep neural network as shown For each ultrasound scanning task, the key point is to in Figure.