Learning Autonomous Ultrasound via Latent Task Representation and Robotic Skills Adaptation

by   Xutian Deng, et al.

As medical ultrasound is becoming a prevailing examination approach nowadays, robotic ultrasound systems can facilitate the scanning process and prevent professional sonographers from repetitive and tedious work. Despite the recent progress, it is still a challenge to enable robots to autonomously accomplish the ultrasound examination, which is largely due to the lack of a proper task representation method, and also an adaptation approach to generalize learned skills across different patients. To solve these problems, we propose the latent task representation and the robotic skills adaptation for autonomous ultrasound in this paper. During the offline stage, the multimodal ultrasound skills are merged and encapsulated into a low-dimensional probability model through a fully self-supervised framework, which takes clinically demonstrated ultrasound images, probe orientations, and contact forces into account. During the online stage, the probability model will select and evaluate the optimal prediction. For unstable singularities, the adaptive optimizer fine-tunes them to near and stable predictions in high-confidence regions. Experimental results show that the proposed approach can generate complex ultrasound strategies for diverse populations and achieve significantly better quantitative results than our previous method.


page 1

page 2

page 3

page 4

page 7

page 8

page 9

page 10


Learning Robotic Ultrasound Scanning Skills via Human Demonstrations and Guided Explorations

Medical ultrasound has become a routine examination approach nowadays an...

Learning Ultrasound Scanning Skills from Human Demonstrations

Recently, the robotic ultrasound system has become an emerging topic owi...

Reliability of Robotic Ultrasound Scanning for Scoliosis Assessment in Comparison with Manual Scanning

Background: Ultrasound (US) imaging for scoliosis assessment is challeng...

Robotic Sonographer: Autonomous Robotic Ultrasound using Domain Expertise in Bayesian Optimization

Ultrasound is a vital imaging modality utilized for a variety of diagnos...

Multimodal-GuideNet: Gaze-Probe Bidirectional Guidance in Obstetric Ultrasound Scanning

Eye trackers can provide visual guidance to sonographers during ultrasou...

UltraBots: Large-Area Mid-Air Haptics for VR with Robotically Actuated Ultrasound Transducers

We introduce UltraBots, a system that combines ultrasound haptic feedbac...

Good and Bad Boundaries in Ultrasound Compounding: Preserving Anatomic Boundaries While Suppressing Artifacts

Ultrasound 3D compounding is important for volumetric reconstruction, bu...

Please sign up or login with your details

Forgot password? Click here to reset