ForceU-VLA: A Force-Aware Vision-Language-Action Model for Embodied Ultrasound Scanning

Xingzheng Wu; Cheng Zhang; Guihao Yan; Xifeng Hu; Zhi Liu; Qing Cai

cs.ROAug 15, 2026

ForceU-VLA: A Force-Aware Vision-Language-Action Model for Embodied Ultrasound Scanning

Authors: Xingzheng Wu, Cheng Zhang, Guihao Yan, Xifeng Hu, Zhi Liu, Qing Cai

Organizations: Faculty of Computer Science and Technology, Ocean University of China Qingdao, China · School of Information Science and Engineering, Shandong University Qingdao, China · Innovation School of Artificial Intelligence, Hefei University of Technology Hefei, China

Abstract

Embodied intelligent ultrasound scanning enables the automation and standardization of the ultrasound examination process by integrating perception, decision-making, and execution capabilities. However, existing methods suffer from loosely coupled modeling between force and ultrasound modalities and lack awareness of scanning stages, which limits their ability to capture dynamic probe-tissue interactions. To address these issues, we propose ForceU-VLA, a force-aware Vision-Language-Action model for autonomous embodied ultrasound scanning, which leverages force signals and ultrasound image feedback throughout the scanning process to enable accurate and high-quality ultrasound acquisition. Firstly, we propose a Force-Ultrasound Synergistic Fusion Module (FUSFM) that synergistically fuses ultrasound visual and force-feedback information to provide stable, reliable guidance for probe motion. Secondly, a Stage-Adaptive Modulation Mechanism (SAMM) is proposed to accommodate the task requirements across different scanning stages by adaptively modulating multimodal features to enhance their representation quality. Additionally, we introduce ForceU-VLA-Data, a real-world, force-aware embodied ultrasound dataset that integrates visual, force, and action signals, including data from two organs across five representative clinical scanning views, and comprising 450 expert-collected trajectories with approximately 100,000 synchronized multimodal frames. Extensive experimental results demonstrate that ForceU-VLA significantly improves contact stability and probe pressure regulation in embodied ultrasound scanning, thereby effectively enhancing task execution quality and overall system reliability. The source code is available at https://github.com/VMVLab/ForceU-VLA.

Figures & tables

Figure 1. Comparison between classical VLA methods and the proposed ForceU-VLA. By explicitly modeling both ultrasound and force information, ForceU-VLA improves contact stability and probe pressure regulation, thereby enhancing both the efficiency and quality of ultrasound scanning.

Figure 2. Overview of ForceU-VLA. First, multimodal inputs are encoded into high-dimensional representations. Then, the Force–Ultrasound Synergistic Fusion Module performs collaborative fusion. Based on the fused features, the Stage-Adaptive Modulation Mechanism applies stage-aware adaptive weighting. Finally, the model generates the action sequence.

Figure 3. Overview of ForceU-VLA-Data, illustrating the dataset contents, acquisition system, collection trajectories, and representative standard planes.

Figure 4. Comparison of success rates between the proposed method and baseline approaches across five tasks. The proposed method significantly outperforms all baselines.

Figure 5. Visualization comparison of the scanning processes of $\pi_{0.5}$ and ForceU-VLA on Task 1.

Method	Task1	Task2	Task3	Task4	Task5	Average
$\pi_{0}$	593	831	611	557	399	598.2
$\pi_{0}$ w/ US	461	735	601	457	351	521.0
$\pi_{0}$ w/ US, F	420	702	586	410	342	492.0
$\pi_{0}$ w/ US, F, S	414	695	536	435	328	481.6
ForceVLA	450	742	669	466	365	538.4
$\pi_{0.5}$	580	645	532	440	301	499.6

Table 1. Scanning timesteps on five ultrasound tasks. Bold values denote the best performance.

Figure 6. Visualization of force comparison during the scanning processes of $\pi_{0.5}$ and ForceU-VLA on Task 2.

Figure 7. Comparison of scanning processes under different lying positions

US	FUSFM	SAMM	Success rates $\uparrow$						Scanning timesteps $\downarrow$
US	FUSFM	SAMM	Task1	Task2	Task3	Task4	Task5	Average	Task1	Task2	Task3	Task4	Task5	Average
			80.0	66.7	62.2	68.9	84.4	72.4	580	645	532	440	301	499.6
$\checkmark$			84.4	71.1	71.1	84.4	91.1	80.4	423	576	476	351	287	422.6
$\checkmark$	$\checkmark$		91.1	77.8	80.0	91.1	97.8	87.6	351	563	447	274	260	379.0
$\checkmark$	$\checkmark$	$\checkmark$	97.8	86.7	84.4	97.8	100.0	93.3	329	528	419	237	243	351.2

Table 2. Ablation study of core Modules in ForceU-VLA.

Explore similar work

US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina
Aug 17, 2026Cheng Zhang, Xingzheng Wu, Guihao Yan +4Robotic Ultrasound Vision-Language-Action Models
Innovation School of Artificial Intelligence, Hefei University of Technology Hefei, China
Visuotactile and Explicitly Force-Controlled Robotic Ultrasound for Abdominal Volumetric Reconstruction
Jun 4, 2026Adrian Piedra, R Brooke Jeffrey, Oussama KhatibRobotic Control 3D Medical Imaging
Stanford Robotics Laboratory, Computer Science Department, Stanford University, Stanford, CA 94305 USA · Department of Radiology, School of Medicine, Stanford University, Stanford, CA 94305 USA
Action-Conditioned World Model for Goal Plane Probe Guidance in Robotic Ultrasound
Jul 24, 2026Siqi Fan, Mingcong Chen, Ran Liu +5World Model Learning Action-Conditioned World Models
Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, Hong Kong SAR · Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong SAR · Department of Biomedical Engineering, City University of Hong Kong, Hong Kong SAR +3

Aug 17, 2026J/K move · Enter open · S save

US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina

Cheng Zhang, Xingzheng Wu, Guihao Yan, Xifeng Hu+3

Innovation School of Artificial Intelligence, Hefei University of Technology Hefei, China

Robotic Ultrasound Vision-Language-Action Models Ultrasound Imaging VLMs for Robotics

Open paper AskPDF arXiv

Artificial intelligence-assisted ultrasound scanning enhances diagnostic reliability and efficiency by providing real-time guidance for standardized image acquisition and reducing operator dependence. However, existing reinforcement learning and learning-assisted ultrasound scanning methods typically rely on carefully designed reward functions or extensive interaction data, which limits their generalization ability and stability across different devices, patient populations, and complex clinical scenarios. To address these challenges, we propose an ultrasound vision-language-action model (US-VLA) for automated ultrasound scanning that explicitly encodes clinical semantic goals and generates sequential probe manipulation actions under real-time ultrasound feedback. In particular, we first design an ultrasound-aware expert fusion module to jointly integrate ultrasound observations with auxiliary contextual information, enabling semantic ultrasound feedback to effectively guide the scanning process. Then, we construct US-VLA-Data, a real-world dataset covering liver and kidney examinations, which includes five clinically defined standard planes and comprises 320 expert scanning trajectories with approximately 80,000 synchronized timesteps. Extensive experiments demonstrate that US-VLA achieves competitive performance in ultrasound probe manipulation tasks, indicating its effectiveness and promising generalization within the evaluated abdominal ultrasound setting. The source code is available at https://github.com/VMVLab/US-VLA.

Abstract

Explore similar work

US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina

Visuotactile and Explicitly Force-Controlled Robotic Ultrasound for Abdominal Volumetric Reconstruction

Action-Conditioned World Model for Goal Plane Probe Guidance in Robotic Ultrasound