{"id":607,"date":"2016-02-21T07:06:48","date_gmt":"2016-02-21T07:06:48","guid":{"rendered":"http:\/\/www.labren.org\/mm\/?p=607"},"modified":"2018-05-31T07:08:49","modified_gmt":"2018-05-31T07:08:49","slug":"towards-transferring-skills-to-flexible-surgical-robots-with-programming-by-demonstration-and-reinforcement-learning","status":"publish","type":"post","link":"http:\/\/www.labren.org\/mm\/projects\/towards-transferring-skills-to-flexible-surgical-robots-with-programming-by-demonstration-and-reinforcement-learning\/","title":{"rendered":"Towards transferring skills to flexible surgical robots with programming by demonstration and reinforcement learning"},"content":{"rendered":"
Abstract:<\/strong><\/div>\n
Flexible manipulators such as tendon-driven ser-<\/span><\/div>\n
pentine manipulators perform better than traditional rigid <\/span><\/div>\n
ones in minimally invasive surgical tasks, including navigation <\/span><\/div>\n
in confined space through key-hole like incisions. However, due<\/div>\n
to the inherent nonlinearities and model uncertainties, motion <\/span><\/div>\n
control of such manipulators becomes extremely challenging. <\/span><\/div>\n
In this work, a hybrid framework combining Programming by<\/div>\n
Demonstration (PbD) and reinforcement learning is proposed<\/div>\n
to solve this problem. Gaussian Mixture Models (GMM),<\/div>\n
Gaussian Mixture Regression (GMR) and linear regression are<\/div>\n
used to learn the inverse kinematic model of the manipulator <\/span><\/div>\n
from human demonstrations. The learned model is used as<\/div>\n
nominal model to calculate the output end-effector trajectories <\/span><\/div>\n
of the manipulator. Two surgical tasks are performed to<\/div>\n
demonstrate the effectiveness of reinforcement learning: tube <\/span><\/div>\n
insertion and circle following. Gaussian noise is introduced to<\/div>\n
the standard model and the disturbed models are fed to the<\/div>\n
manipulator to calculate the actuator input with respect to the<\/div>\n
task specific end-effector trajectories. An expectation <\/span><\/div>\n
maximization (E-M) based reinforcement learning algorithm is<\/div>\n
used to update the disturbed model with returns from rollouts.<\/div>\n
Simulation results have verified that the disturbed model can <\/span><\/div>\n
be converged to the standard one and the tracking accuracy is<\/div>\n
enhanced.<\/div>\n
More Information:<\/strong><\/div>\n
Full Text<\/a><\/div>\n","protected":false},"excerpt":{"rendered":"

Abstract: Flexible manipulators such as tendon-driven ser- pentine 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\u2026 Continue reading<\/a><\/p>\n","protected":false},"author":12,"featured_media":608,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[9],"tags":[],"class_list":["post-607","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-projects"],"_links":{"self":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/607","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/users\/12"}],"replies":[{"embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/comments?post=607"}],"version-history":[{"count":1,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/607\/revisions"}],"predecessor-version":[{"id":609,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/607\/revisions\/609"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/media\/608"}],"wp:attachment":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/media?parent=607"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/categories?post=607"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/tags?post=607"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}