提升仿真与真实中探头运动引起的特征变化一致性，实现超声机器人零样本迁移。
Task-Relevant Feature-Dynamics Fidelity Enables Zero-Shot Sim-to-Real Transfer for Robotic Ultrasound Scanning
- 构建基于运动敏感特征动态一致性的仿真框架
- 400次部署中390次成功，零样本迁移率97.5%
- 适合需低成本训练的医疗机器人研究者
直接在B模式图像上运行的机器人超声策略需要大量交互数据，而真实机器人数据收集成本高且受安全限制。仿真提供可扩展替代方案，但零样本迁移不仅依赖单帧真实性，还取决于仿真观察是否复现探头运动引发的任务相关特征变化。我们称这种跨域一致性为任务相关特征动态保真度（TR-FDF）。在局部正则性假设下，我们的压缩分析表明，TR-FDF不匹配对探头运动更敏感会降低有效闭环压缩裕度，而运动无关误差主要扩大残差边界。基于此分析，我们开发了面向TR-FDF的超声仿真器，结合共享结构中间域、轨迹级固定噪声和少步条件流生成。在模型实验中，仅在仿真中训练的策略在四个目标平面的400次零样本部署中成功390次。该仿真器实现FID 29.66，生成速率达67.1 Hz。控制干预、消融实验和基线对比显示，TR-FDF敏感性与单帧真实性共同预测零样本迁移性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。