File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.2316/J.2019.206-5461
- Scopus: eid_2-s2.0-85064385915
- WOS: WOS:000465082100011
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: POLICY GRADIENT-BASED INVERSE KINEMATICS REFINEMENT FOR TENDON-DRIVEN SERPENTINE SURGICAL MANIPULATOR
Title | POLICY GRADIENT-BASED INVERSE KINEMATICS REFINEMENT FOR TENDON-DRIVEN SERPENTINE SURGICAL MANIPULATOR |
---|---|
Authors | |
Keywords | Inverse kinematics policy gradient reinforcement learning surgical manipulator tendon-driven |
Issue Date | 2019 |
Publisher | ACTA Press. The Journal's web site is located at http://www.actapress.com/Editors.aspx?JournalID=5 |
Citation | International Journal of Robotics and Automation, 2019, v. 34 n. 3, p. 303-311 How to Cite? |
Abstract | Minimally invasive surgery (MIS) has attracted continuous interests over the last decade due to its better surgical outcomes than that of conventional open procedures. However, conducting MIS effectively requires long-term training and special expertise for the surgeons and physicians, which highlights the importance of robot-assisted MIS. A two-degrees-of-freedom tendon-driven serpentine surgical manipulator is designed in this work requiring only a trocar with a radius of 3.5 mm for single port laparoscopy. Based on piecewise constant curvature assumption, the inverse kinematics (IK) of the system is derived. Then, a novel policy gradient algorithm is developed to refine the derived IK to compensate for system internal nonlinearities, of which the performance is evaluated by a number of trajectory tracking tasks. Rooted mean square error (RMSE) of trajectory tracking experiments in real world with the original IK is 9.693 mm. After deploying reinforcement learning, RMSE reduces significantly to 1.101 mm after only 45 iterations. Therefore, the proposed method provides an efficient alternative to enhance the motion control accuracy for the challenging tendon-driven serpentine surgical manipulators and furthers its application to robot-assisted interventions in MIS. |
Persistent Identifier | http://hdl.handle.net/10722/272204 |
ISSN | 2021 Impact Factor: 1.042 2020 SCImago Journal Rankings: 0.249 |
ISI Accession Number ID | |
Grants |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | CHEN, J | - |
dc.contributor.author | Lau, H | - |
dc.date.accessioned | 2019-07-20T10:37:42Z | - |
dc.date.available | 2019-07-20T10:37:42Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | International Journal of Robotics and Automation, 2019, v. 34 n. 3, p. 303-311 | - |
dc.identifier.issn | 0826-8185 | - |
dc.identifier.uri | http://hdl.handle.net/10722/272204 | - |
dc.description.abstract | Minimally invasive surgery (MIS) has attracted continuous interests over the last decade due to its better surgical outcomes than that of conventional open procedures. However, conducting MIS effectively requires long-term training and special expertise for the surgeons and physicians, which highlights the importance of robot-assisted MIS. A two-degrees-of-freedom tendon-driven serpentine surgical manipulator is designed in this work requiring only a trocar with a radius of 3.5 mm for single port laparoscopy. Based on piecewise constant curvature assumption, the inverse kinematics (IK) of the system is derived. Then, a novel policy gradient algorithm is developed to refine the derived IK to compensate for system internal nonlinearities, of which the performance is evaluated by a number of trajectory tracking tasks. Rooted mean square error (RMSE) of trajectory tracking experiments in real world with the original IK is 9.693 mm. After deploying reinforcement learning, RMSE reduces significantly to 1.101 mm after only 45 iterations. Therefore, the proposed method provides an efficient alternative to enhance the motion control accuracy for the challenging tendon-driven serpentine surgical manipulators and furthers its application to robot-assisted interventions in MIS. | - |
dc.language | eng | - |
dc.publisher | ACTA Press. The Journal's web site is located at http://www.actapress.com/Editors.aspx?JournalID=5 | - |
dc.relation.ispartof | International Journal of Robotics and Automation | - |
dc.subject | Inverse kinematics | - |
dc.subject | policy gradient | - |
dc.subject | reinforcement learning | - |
dc.subject | surgical manipulator | - |
dc.subject | tendon-driven | - |
dc.title | POLICY GRADIENT-BASED INVERSE KINEMATICS REFINEMENT FOR TENDON-DRIVEN SERPENTINE SURGICAL MANIPULATOR | - |
dc.type | Article | - |
dc.identifier.email | Lau, H: hyklau@hku.hk | - |
dc.identifier.authority | Lau, H=rp00137 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.2316/J.2019.206-5461 | - |
dc.identifier.scopus | eid_2-s2.0-85064385915 | - |
dc.identifier.hkuros | 298269 | - |
dc.identifier.volume | 34 | - |
dc.identifier.issue | 3 | - |
dc.identifier.spage | 303 | - |
dc.identifier.epage | 311 | - |
dc.identifier.isi | WOS:000465082100011 | - |
dc.publisher.place | Canada | - |
dc.relation.project | Task characterization for intelligent control of tendon-driven serpentine surgical manipulators with learning from demonstration | - |
dc.identifier.issnl | 0826-8185 | - |