Semi-autonomous navigation for robot assisted tele-echography using generalized shape models and co-registered RGB-D cameras

This paper proposes a semi-autonomous navigated master-slave system, for robot assisted remote echography for early trauma assessment. Two RGB-D sensors are used to capture real-time 3D information of the scene at the slave side where the patient is located. A 3D statistical shape model is built and used to generate a customized patient model based on the point cloud generated by the RGB-D sensors. The customized patient model can be updated and adaptively fitted to the patient. The model is also used to generate a trajectory to navigate a KUKA robotic arm and safely conduct the ultrasound examination. Extensive validation of the proposed system shows promising results in terms of accuracy and robustness.