SuFIA-BC: Generating High Quality Demonstration Data for Visuomotor Policy Learning in Surgical Subtasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moghani, Masoud, Nelson, Nigel, Ghanem, Mohamed, Diaz-Pinto, Andres, Hari, Kush, Azizian, Mahdi, Goldberg, Ken, Huver, Sean, Garg, Animesh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910915389030400
author Moghani, Masoud
Nelson, Nigel
Ghanem, Mohamed
Diaz-Pinto, Andres
Hari, Kush
Azizian, Mahdi
Goldberg, Ken
Huver, Sean
Garg, Animesh
author_facet Moghani, Masoud
Nelson, Nigel
Ghanem, Mohamed
Diaz-Pinto, Andres
Hari, Kush
Azizian, Mahdi
Goldberg, Ken
Huver, Sean
Garg, Animesh
contents Behavior cloning facilitates the learning of dexterous manipulation skills, yet the complexity of surgical environments, the difficulty and expense of obtaining patient data, and robot calibration errors present unique challenges for surgical robot learning. We provide an enhanced surgical digital twin with photorealistic human anatomical organs, integrated into a comprehensive simulator designed to generate high-quality synthetic data to solve fundamental tasks in surgical autonomy. We present SuFIA-BC: visual Behavior Cloning policies for Surgical First Interactive Autonomy Assistants. We investigate visual observation spaces including multi-view cameras and 3D visual representations extracted from a single endoscopic camera view. Through systematic evaluation, we find that the diverse set of photorealistic surgical tasks introduced in this work enables a comprehensive evaluation of prospective behavior cloning models for the unique challenges posed by surgical environments. We observe that current state-of-the-art behavior cloning techniques struggle to solve the contact-rich and complex tasks evaluated in this work, regardless of their underlying perception or control architectures. These findings highlight the importance of customizing perception pipelines and control architectures, as well as curating larger-scale synthetic datasets that meet the specific demands of surgical tasks. Project website: https://orbit-surgical.github.io/sufia-bc/
format Preprint
id arxiv_https___arxiv_org_abs_2504_14857
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SuFIA-BC: Generating High Quality Demonstration Data for Visuomotor Policy Learning in Surgical Subtasks
Moghani, Masoud
Nelson, Nigel
Ghanem, Mohamed
Diaz-Pinto, Andres
Hari, Kush
Azizian, Mahdi
Goldberg, Ken
Huver, Sean
Garg, Animesh
Robotics
Behavior cloning facilitates the learning of dexterous manipulation skills, yet the complexity of surgical environments, the difficulty and expense of obtaining patient data, and robot calibration errors present unique challenges for surgical robot learning. We provide an enhanced surgical digital twin with photorealistic human anatomical organs, integrated into a comprehensive simulator designed to generate high-quality synthetic data to solve fundamental tasks in surgical autonomy. We present SuFIA-BC: visual Behavior Cloning policies for Surgical First Interactive Autonomy Assistants. We investigate visual observation spaces including multi-view cameras and 3D visual representations extracted from a single endoscopic camera view. Through systematic evaluation, we find that the diverse set of photorealistic surgical tasks introduced in this work enables a comprehensive evaluation of prospective behavior cloning models for the unique challenges posed by surgical environments. We observe that current state-of-the-art behavior cloning techniques struggle to solve the contact-rich and complex tasks evaluated in this work, regardless of their underlying perception or control architectures. These findings highlight the importance of customizing perception pipelines and control architectures, as well as curating larger-scale synthetic datasets that meet the specific demands of surgical tasks. Project website: https://orbit-surgical.github.io/sufia-bc/
title SuFIA-BC: Generating High Quality Demonstration Data for Visuomotor Policy Learning in Surgical Subtasks
topic Robotics
url https://arxiv.org/abs/2504.14857