STITCH: Augmented Dexterity for Suture Throws Including Thread Coordination and Handoffs

    April 2024 in “ arXiv (Cornell University)
    Kush Hari, Hansoul Kim, Will Panitch, Kishore Srinivas, Vincent Schorp, Karthik Dharmarajan, Shreya Ganti, Tara Sadjadpour, Ken Goldberg
    TLDR STITCH improves suture accuracy and efficiency, especially with human help.
    STITCH is an augmented dexterity pipeline designed to enhance suture throws by incorporating thread coordination and handoffs. It utilizes a novel visual 6D needle pose estimation framework with a stereo camera pair and new suturing motion primitives. In experiments conducted over 15 trials, STITCH achieved an average of 2.93 sutures without human intervention and 4.47 sutures with human intervention, demonstrating its effectiveness compared to baselines that rely solely on proprioception or lack visual servoing.
    Discuss this study in the Community →