Abstract: An ultrasound system comprises a robotic system to position an ultrasound probe against and move the probe over a body part; and a data generating module to control the robotic system to generate training data comprising images associated with target view(s), being associated with a target position of the probe that has a plurality of training positions that includes a direction pointing towards the target position; a machine learning module comprising a trained algorithm to receive image(s) at a current probe position information defining a direction pointing towards an estimated position based on the image(s); and, an execution module to autonomously control the robotic system including: moving the probe to find an optimal position for each of the target view(s) based on estimated direction information generated by the algorithm for different probe positions and to capture at the optimal position for each of the target view(s), image(s).