File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICACI.2016.7449855
- Scopus: eid_2-s2.0-84966670379
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Towards transferring skills to flexible surgical robots with programming by demonstration and reinforcement learning
Title | Towards transferring skills to flexible surgical robots with programming by demonstration and reinforcement learning |
---|---|
Authors | |
Keywords | inverse kinematics policy search programming by demonstration reinforcement learning surgical robot |
Issue Date | 2016 |
Publisher | IEEE. |
Citation | 2016 Eighth International Conference on Advanced Computational Intelligence (ICACI), Chiang Mai, Thailand, 14-16 February 2016, p. 378-384 How to Cite? |
Abstract | Flexible manipulators such as tendon-driven serpentine manipulators perform better than traditional rigid ones in minimally invasive surgical tasks, including navigation in confined space through key-hole like incisions. However, due to the inherent nonlinearities and model uncertainties, motion control of such manipulators becomes extremely challenging. In this work, a hybrid framework combining Programming by Demonstration (PbD) and reinforcement learning is proposed to solve this problem. Gaussian Mixture Models (GMM), Gaussian Mixture Regression (GMR) and linear regression are used to learn the inverse kinematic model of the manipulator from human demonstrations. The learned model is used as nominal model to calculate the output end-effector trajectories of the manipulator. Two surgical tasks are performed to demonstrate the effectiveness of reinforcement learning: tube insertion and circle following. Gaussian noise is introduced to the standard model and the disturbed models are fed to the manipulator to calculate the actuator input with respect to the task specific end-effector trajectories. An expectation maximization (E-M) based reinforcement learning algorithm is used to update the disturbed model with returns from rollouts. Simulation results have verified that the disturbed model can be converged to the standard one and the tracking accuracy is enhanced. |
Persistent Identifier | http://hdl.handle.net/10722/241699 |
ISBN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, J | - |
dc.contributor.author | Lau, HYK | - |
dc.contributor.author | Xu, W | - |
dc.contributor.author | Ren, HL | - |
dc.date.accessioned | 2017-06-20T01:47:21Z | - |
dc.date.available | 2017-06-20T01:47:21Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | 2016 Eighth International Conference on Advanced Computational Intelligence (ICACI), Chiang Mai, Thailand, 14-16 February 2016, p. 378-384 | - |
dc.identifier.isbn | 9781467377805 | - |
dc.identifier.uri | http://hdl.handle.net/10722/241699 | - |
dc.description.abstract | Flexible manipulators such as tendon-driven serpentine manipulators perform better than traditional rigid ones in minimally invasive surgical tasks, including navigation in confined space through key-hole like incisions. However, due to the inherent nonlinearities and model uncertainties, motion control of such manipulators becomes extremely challenging. In this work, a hybrid framework combining Programming by Demonstration (PbD) and reinforcement learning is proposed to solve this problem. Gaussian Mixture Models (GMM), Gaussian Mixture Regression (GMR) and linear regression are used to learn the inverse kinematic model of the manipulator from human demonstrations. The learned model is used as nominal model to calculate the output end-effector trajectories of the manipulator. Two surgical tasks are performed to demonstrate the effectiveness of reinforcement learning: tube insertion and circle following. Gaussian noise is introduced to the standard model and the disturbed models are fed to the manipulator to calculate the actuator input with respect to the task specific end-effector trajectories. An expectation maximization (E-M) based reinforcement learning algorithm is used to update the disturbed model with returns from rollouts. Simulation results have verified that the disturbed model can be converged to the standard one and the tracking accuracy is enhanced. | - |
dc.language | eng | - |
dc.publisher | IEEE. | - |
dc.relation.ispartof | International Conference on Advanced Computational Intelligence (ICACI) | - |
dc.rights | International Conference on Advanced Computational Intelligence (ICACI). Copyright © IEEE. | - |
dc.rights | ©2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.subject | inverse kinematics | - |
dc.subject | policy search | - |
dc.subject | programming by demonstration | - |
dc.subject | reinforcement learning | - |
dc.subject | surgical robot | - |
dc.title | Towards transferring skills to flexible surgical robots with programming by demonstration and reinforcement learning | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Lau, HYK: hyklau@hkucc.hku.hk | - |
dc.identifier.authority | Lau, HYK=rp00137 | - |
dc.identifier.doi | 10.1109/ICACI.2016.7449855 | - |
dc.identifier.scopus | eid_2-s2.0-84966670379 | - |
dc.identifier.hkuros | 272868 | - |
dc.identifier.spage | 378 | - |
dc.identifier.epage | 384 | - |
dc.publisher.place | United States | - |