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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hari, Kush, Kim, Hansoul, Panitch, Will, Srinivas, Kishore, Schorp, Vincent, Dharmarajan, Karthik, Ganti, Shreya, Sadjadpour, Tara, Goldberg, Ken
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910402352250880
author Hari, Kush
Kim, Hansoul
Panitch, Will
Srinivas, Kishore
Schorp, Vincent
Dharmarajan, Karthik
Ganti, Shreya
Sadjadpour, Tara
Goldberg, Ken
author_facet Hari, Kush
Kim, Hansoul
Panitch, Will
Srinivas, Kishore
Schorp, Vincent
Dharmarajan, Karthik
Ganti, Shreya
Sadjadpour, Tara
Goldberg, Ken
contents We present STITCH: an augmented dexterity pipeline that performs Suture Throws Including Thread Coordination and Handoffs. STITCH iteratively performs needle insertion, thread sweeping, needle extraction, suture cinching, needle handover, and needle pose correction with failure recovery policies. We introduce a novel visual 6D needle pose estimation framework using a stereo camera pair and new suturing motion primitives. We compare STITCH to baselines, including a proprioception-only and a policy without visual servoing. In physical experiments across 15 trials, STITCH achieves an average of 2.93 sutures without human intervention and 4.47 sutures with human intervention. See https://sites.google.com/berkeley.edu/stitch for code and supplemental materials.
format Preprint
id arxiv_https___arxiv_org_abs_2404_05151
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle STITCH: Augmented Dexterity for Suture Throws Including Thread Coordination and Handoffs
Hari, Kush
Kim, Hansoul
Panitch, Will
Srinivas, Kishore
Schorp, Vincent
Dharmarajan, Karthik
Ganti, Shreya
Sadjadpour, Tara
Goldberg, Ken
Robotics
We present STITCH: an augmented dexterity pipeline that performs Suture Throws Including Thread Coordination and Handoffs. STITCH iteratively performs needle insertion, thread sweeping, needle extraction, suture cinching, needle handover, and needle pose correction with failure recovery policies. We introduce a novel visual 6D needle pose estimation framework using a stereo camera pair and new suturing motion primitives. We compare STITCH to baselines, including a proprioception-only and a policy without visual servoing. In physical experiments across 15 trials, STITCH achieves an average of 2.93 sutures without human intervention and 4.47 sutures with human intervention. See https://sites.google.com/berkeley.edu/stitch for code and supplemental materials.
title STITCH: Augmented Dexterity for Suture Throws Including Thread Coordination and Handoffs
topic Robotics
url https://arxiv.org/abs/2404.05151