# EmbodiedUS-FS: Fast Slow Intelligence for Ultrasound Robotics

arXiv: https://arxiv.org/abs/2606.22319 · HTML: https://mlsanity.com/paper/2606.22319/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [Pre-Trained Language Models for Interactive Decision-Making](https://mlsanity.com/paper/2202.01771/) (2022)
- [RoCo: Dialectic Multi-Robot Collaboration with Large Language Models](https://mlsanity.com/paper/2307.04738/) (2023)
- [Task and Motion Planning with Large Language Models for Object Rearrangement](https://mlsanity.com/paper/2303.06247/) (2023)
- [Correcting Robot Plans with Natural Language Feedback](https://mlsanity.com/paper/2204.05186/) (2022)
- [Vision-Language Embodiment for Monocular Depth Estimation](https://mlsanity.com/paper/2503.16535/) (2025)
- [Transforming Surgical Interventions with Embodied Intelligence for Ultrasound Robotics](https://mlsanity.com/paper/2406.12651/) (2024)
- [USPilot: An Embodied Robotic Assistant Ultrasound System with Large Language Model Enhanced Graph Planner](https://mlsanity.com/paper/2502.12498/) (2025)
- [Automated Genomic Interpretation via Concept Bottleneck Models for Medical Robotics](https://mlsanity.com/paper/2510.01618/) (2025)

## Abstract (arXiv)

Robotic ultrasound scanning in real clinical environments requires both high-level clinical workflow reasoning and low-level closed-loop execution. Physicians natural-language instructions often contain implicit anatomical targets, procedural logic, image-quality requirements, and safety constraints, while execution is affected by patient motion, contact variations, and target drift. We propose a fast and slow hierarchical embodied ultrasound system for safe and interpretable robotic ultrasound assistance. The Slow Brain performs intent parsing and stage-wise task planning with knowledge augmentation from an API and handbook corpus, and generates executable plans through task-graph construction and structured plan verification. The Fast Brain fuses multimodal feedback, including ultrasound images, robot pose and force states, and patient-motion information, to refine local actions and perform image-quality-guided recovery behaviors. The system further integrates a Safety Shield and a hierarchical escalation policy to constrain risky actions and trigger replanning or human confirmation under persistent failures or safety-bound violations. Experiments on planning evaluation, closed-loop execution under dynamic perturbations, and safety-mechanism validation demonstrate that the proposed hierarchical design improves task success rates while reducing safety violations.