[
    {
        "id": "osp-18361",
        "type": "article-journal",
        "title": "Recon2Servo: Robotic Ultrasound Visual Servoing via Learned Image-to-Motion Inference",
        "author": [
            {
                "family": "Zhang",
                "given": "Yameng"
            },
            {
                "family": "Liu",
                "given": "Pei"
            },
            {
                "family": "Huang",
                "given": "Dianye"
            },
            {
                "family": "Qian",
                "given": "Yizhao"
            },
            {
                "family": "Chen",
                "given": "Zhongyu"
            },
            {
                "family": "Chu",
                "given": "Xiangyu"
            },
            {
                "family": "Au",
                "given": "K. W. Samuel"
            },
            {
                "family": "Jiang",
                "given": "Zhongliang"
            }
        ],
        "URL": "https://omanscience.com/en/articles/recon2servo-robotic-ultrasound-visual-servoing-via-learned-image-to-motion-inference",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Ultrasound visual servoing is essential for autonomous robotic ultrasound, yet 6-DoF probe control from 2D B-mode images remains challenging due to limited and ambiguous out-of-plane motion cues. Existing methods typically rely on anatomical priors or handcrafted visual features, limiting their generalizability across imaging targets. Inspired by trackerless 3D ultrasound reconstruction, we propose Recon2Servo, a visual servoing framework that learns image-to-motion inference directly from B-mode images for 6-DoF probe control. A DINOv3 encoder with low-rank adaptation and a bidirectional relation module estimate the relative probe pose between current and target images to guide iterative closed-loop target-view alignment. The framework combines supervised relative-pose learning, reconstruction-guided closed-loop adaptation, and bounded residual pose correction to improve motion inference during servoing. Evaluations on a public dataset and an in-house dataset collected from 12 healthy volunteers using different ultrasound systems demonstrate its effectiveness in reconstructed-volume servoing. Additional real-robot demonstrations of target-view alignment and dynamic tracking on a human forearm are provided in the supplementary video: https://youtu.be/qwsOdI-GMYk."
    }
]