SOURCE-LINKED INTELLIGENCE

Task-Relevant Feature-Dynamics Fidelity Enables Zero-Shot Sim-to-Real Transfer for Robotic Ultrasound Scanning

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Robotic ultrasound policies operating directly on B-mode images require extensive interaction data, whereas real-robot data collection is costly and safety-constrained. Simulation provides a scalable alternative, but zero-shot transfer depends not only on single-frame realism but also on whether simulated observations reproduce task-relevant feature changes induced by probe motion. We term this cross-domain consistency task-relevant feature-dynamics fidelity (TR-FDF). Under local regularity assumptions, our contraction analysis shows that greater sensitivity of TR-FDF mismatch to probe motion

Read original source ↗ Open in workspace

recordType

paper

region

Global