Autonomous multilateral debridement with the Raven surgical robot

Ben Kehoe, Gregory Kahn, Jeffrey Mahler, Jonathan Kim, Alex Lee, Anna Lee, Keisuke Nakagawa, Sachin Patil, Walter D Boyd, Pieter Abbeel, Ken Goldberg

Research output: Chapter in Book/Report/Conference proceedingConference contribution

41 Citations (Scopus)

Abstract

Autonomous robot execution of surgical sub-tasks has the potential to reduce surgeon fatigue and facilitate supervised tele-surgery. This paper considers the sub-task of surgical debridement: removing dead or damaged tissue fragments to allow the remaining healthy tissue to heal. We present an autonomous multilateral surgical debridement system using the Raven, an open-architecture surgical robot with two cable-driven 7 DOF arms. Our system combines stereo vision for 3D perception with trajopt, an optimization-based motion planner, and model predictive control (MPC). Laboratory experiments involving sensing, grasping, and removal of 120 fragments suggest that an autonomous surgical robot can achieve robustness comparable to human performance. Our robot system demonstrated the advantage of multilateral systems, as the autonomous execution was 1.5× faster with two arms than with one; however, it was two to three times slower than a human. Execution speed could be improved with better state estimation that would allow more travel between MPC steps and fewer MPC replanning cycles. The three primary contributions of this paper are: (1) introducing debridement as a sub-task of interest for surgical robotics, (2) demonstrating the first reliable autonomous robot performance of a surgical sub-task using the Raven, and (3) reporting experiments that highlight the importance of accurate state estimation for future research. Further information including code, photos, and video is available at: http://rll.berkeley.edu/raven.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1432-1439
Number of pages8
DOIs
StatePublished - Sep 22 2014
Event2014 IEEE International Conference on Robotics and Automation, ICRA 2014 - Hong Kong, China
Duration: May 31 2014Jun 7 2014

Other

Other2014 IEEE International Conference on Robotics and Automation, ICRA 2014
CountryChina
CityHong Kong
Period5/31/146/7/14

Fingerprint

Model predictive control
Robots
State estimation
Tissue
Stereo vision
Surgery
Cables
Robotics
Experiments
Fatigue of materials
Robotic surgery

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Kehoe, B., Kahn, G., Mahler, J., Kim, J., Lee, A., Lee, A., ... Goldberg, K. (2014). Autonomous multilateral debridement with the Raven surgical robot. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 1432-1439). [6907040] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2014.6907040

Autonomous multilateral debridement with the Raven surgical robot. / Kehoe, Ben; Kahn, Gregory; Mahler, Jeffrey; Kim, Jonathan; Lee, Alex; Lee, Anna; Nakagawa, Keisuke; Patil, Sachin; Boyd, Walter D; Abbeel, Pieter; Goldberg, Ken.

Proceedings - IEEE International Conference on Robotics and Automation. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1432-1439 6907040.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kehoe, B, Kahn, G, Mahler, J, Kim, J, Lee, A, Lee, A, Nakagawa, K, Patil, S, Boyd, WD, Abbeel, P & Goldberg, K 2014, Autonomous multilateral debridement with the Raven surgical robot. in Proceedings - IEEE International Conference on Robotics and Automation., 6907040, Institute of Electrical and Electronics Engineers Inc., pp. 1432-1439, 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, Hong Kong, China, 5/31/14. https://doi.org/10.1109/ICRA.2014.6907040
Kehoe B, Kahn G, Mahler J, Kim J, Lee A, Lee A et al. Autonomous multilateral debridement with the Raven surgical robot. In Proceedings - IEEE International Conference on Robotics and Automation. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1432-1439. 6907040 https://doi.org/10.1109/ICRA.2014.6907040
Kehoe, Ben ; Kahn, Gregory ; Mahler, Jeffrey ; Kim, Jonathan ; Lee, Alex ; Lee, Anna ; Nakagawa, Keisuke ; Patil, Sachin ; Boyd, Walter D ; Abbeel, Pieter ; Goldberg, Ken. / Autonomous multilateral debridement with the Raven surgical robot. Proceedings - IEEE International Conference on Robotics and Automation. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1432-1439
@inproceedings{6439fbeb5cd745f783be377d292c2bce,
title = "Autonomous multilateral debridement with the Raven surgical robot",
abstract = "Autonomous robot execution of surgical sub-tasks has the potential to reduce surgeon fatigue and facilitate supervised tele-surgery. This paper considers the sub-task of surgical debridement: removing dead or damaged tissue fragments to allow the remaining healthy tissue to heal. We present an autonomous multilateral surgical debridement system using the Raven, an open-architecture surgical robot with two cable-driven 7 DOF arms. Our system combines stereo vision for 3D perception with trajopt, an optimization-based motion planner, and model predictive control (MPC). Laboratory experiments involving sensing, grasping, and removal of 120 fragments suggest that an autonomous surgical robot can achieve robustness comparable to human performance. Our robot system demonstrated the advantage of multilateral systems, as the autonomous execution was 1.5× faster with two arms than with one; however, it was two to three times slower than a human. Execution speed could be improved with better state estimation that would allow more travel between MPC steps and fewer MPC replanning cycles. The three primary contributions of this paper are: (1) introducing debridement as a sub-task of interest for surgical robotics, (2) demonstrating the first reliable autonomous robot performance of a surgical sub-task using the Raven, and (3) reporting experiments that highlight the importance of accurate state estimation for future research. Further information including code, photos, and video is available at: http://rll.berkeley.edu/raven.",
author = "Ben Kehoe and Gregory Kahn and Jeffrey Mahler and Jonathan Kim and Alex Lee and Anna Lee and Keisuke Nakagawa and Sachin Patil and Boyd, {Walter D} and Pieter Abbeel and Ken Goldberg",
year = "2014",
month = "9",
day = "22",
doi = "10.1109/ICRA.2014.6907040",
language = "English (US)",
pages = "1432--1439",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Autonomous multilateral debridement with the Raven surgical robot

AU - Kehoe, Ben

AU - Kahn, Gregory

AU - Mahler, Jeffrey

AU - Kim, Jonathan

AU - Lee, Alex

AU - Lee, Anna

AU - Nakagawa, Keisuke

AU - Patil, Sachin

AU - Boyd, Walter D

AU - Abbeel, Pieter

AU - Goldberg, Ken

PY - 2014/9/22

Y1 - 2014/9/22

N2 - Autonomous robot execution of surgical sub-tasks has the potential to reduce surgeon fatigue and facilitate supervised tele-surgery. This paper considers the sub-task of surgical debridement: removing dead or damaged tissue fragments to allow the remaining healthy tissue to heal. We present an autonomous multilateral surgical debridement system using the Raven, an open-architecture surgical robot with two cable-driven 7 DOF arms. Our system combines stereo vision for 3D perception with trajopt, an optimization-based motion planner, and model predictive control (MPC). Laboratory experiments involving sensing, grasping, and removal of 120 fragments suggest that an autonomous surgical robot can achieve robustness comparable to human performance. Our robot system demonstrated the advantage of multilateral systems, as the autonomous execution was 1.5× faster with two arms than with one; however, it was two to three times slower than a human. Execution speed could be improved with better state estimation that would allow more travel between MPC steps and fewer MPC replanning cycles. The three primary contributions of this paper are: (1) introducing debridement as a sub-task of interest for surgical robotics, (2) demonstrating the first reliable autonomous robot performance of a surgical sub-task using the Raven, and (3) reporting experiments that highlight the importance of accurate state estimation for future research. Further information including code, photos, and video is available at: http://rll.berkeley.edu/raven.

AB - Autonomous robot execution of surgical sub-tasks has the potential to reduce surgeon fatigue and facilitate supervised tele-surgery. This paper considers the sub-task of surgical debridement: removing dead or damaged tissue fragments to allow the remaining healthy tissue to heal. We present an autonomous multilateral surgical debridement system using the Raven, an open-architecture surgical robot with two cable-driven 7 DOF arms. Our system combines stereo vision for 3D perception with trajopt, an optimization-based motion planner, and model predictive control (MPC). Laboratory experiments involving sensing, grasping, and removal of 120 fragments suggest that an autonomous surgical robot can achieve robustness comparable to human performance. Our robot system demonstrated the advantage of multilateral systems, as the autonomous execution was 1.5× faster with two arms than with one; however, it was two to three times slower than a human. Execution speed could be improved with better state estimation that would allow more travel between MPC steps and fewer MPC replanning cycles. The three primary contributions of this paper are: (1) introducing debridement as a sub-task of interest for surgical robotics, (2) demonstrating the first reliable autonomous robot performance of a surgical sub-task using the Raven, and (3) reporting experiments that highlight the importance of accurate state estimation for future research. Further information including code, photos, and video is available at: http://rll.berkeley.edu/raven.

UR - http://www.scopus.com/inward/record.url?scp=84929146903&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929146903&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2014.6907040

DO - 10.1109/ICRA.2014.6907040

M3 - Conference contribution

SP - 1432

EP - 1439

BT - Proceedings - IEEE International Conference on Robotics and Automation

PB - Institute of Electrical and Electronics Engineers Inc.

ER -