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

2026-08-29

AI Summary

研究解决了机器人超声扫描中模拟到现实零样本迁移的问题，通过开发一个专注于任务相关特征动态保真度的仿真器，提高了迁移性能。

Abstract

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 reduces the effective closed-loop contraction margin, whereas motion-independent errors primarily enlarge the residual error bound. Guided by this analysis, we develop a TR-FDF-oriented ultrasound simulator that combines a shared structural intermediate domain, trajectory-level fixed noise, and few-step conditional flow generation. In phantom experiments, a policy trained exclusively in simulation succeeded in 390 of 400 zero-shot deployments across four target planes. The simulator achieved an FID of 29.66 and generated observations at 67.1 Hz. Controlled interventions, ablations, and baseline comparisons showed that TR-FDF sensitivity complements single-frame realism in predicting zero-shot transfer performance.

Problem

• zero-shot sim-to-real transfer
• task-relevant feature-dynamics fidelity
• ultrasound scanning
• simulation

Innovation

• task-relevant feature-dynamics fidelity
• zero-shot sim-to-real transfer
• ultrasound simulator