{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:21:16Z","timestamp":1765520476130,"version":"3.48.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247575","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"21559-21565","source":"Crossref","is-referenced-by-count":0,"title":["Jacobian Exploratory Dual-Phase Reinforcement Learning for Dynamic Endoluminal Navigation of Deformable Continuum Robots"],"prefix":"10.1109","author":[{"given":"Yu","family":"Tian","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi Kit","family":"Ng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2489500"},{"key":"ref2","first-page":"253","article-title":"Concentric tube robots: The state of the art and future directions","author":"Dupont","year":"2015","journal-title":"Robot. Res."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2014.2325992"},{"issue":"40","key":"ref4","first-page":"eaaz4896","article-title":"Soft robotics enables neuroprosthetic hand design","volume":"5","author":"Wang","year":"2020","journal-title":"Sci. Robot."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910368147"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2011.2160469"},{"issue":"6","key":"ref7","first-page":"1923","article-title":"Continuum robot dynamics using the principle of virtual power","volume":"37","author":"Lee","year":"2021","journal-title":"IEEE Trans. Robot."},{"issue":"1","key":"ref8","first-page":"580","article-title":"Adaptive control of soft robots using online system identification","volume":"39","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Robot."},{"issue":"1","key":"ref9","article-title":"Deep recurrent q-learning for partially observable mdps","volume-title":"AAAI Conf. Artif. Intell","volume":"29","author":"Hausknecht"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/aa839f"},{"key":"ref11","first-page":"73","article-title":"Neural network and jacobian method for solving the inverse statics of a cable-driven soft arm","volume-title":"IEEE\/RSJ Int. Conf. Intell. Robots Syst. (IROS)","author":"Giorelli"},{"key":"ref12","first-page":"4890","article-title":"Deformable linear object manipulation with online model parameters estimation","volume-title":"IEEE Int. Conf. Robot. Autom. (ICRA)","author":"Zhang"},{"issue":"2","key":"ref13","first-page":"3545","article-title":"Jacobian-based learning for inverse kinematics of soft robots","volume":"7","author":"Chen","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref17","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2878318"},{"article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","year":"2018","author":"Kalashnikov","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"issue":"9","key":"ref21","first-page":"1021","article-title":"Generalizable whole-body global manipulation of deformable linear objects by dual-arm robot in 3-d constrained environments","volume":"43","author":"Li","year":"2024","journal-title":"Int. J. Robot. Res."},{"key":"ref22","first-page":"13","article-title":"SOFA: An open source framework for medical simulation","author":"Allard","year":"2007","journal-title":"Med. Meets Virtual Real. (MMVR)"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247575.pdf?arnumber=11247575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:17:31Z","timestamp":1765520251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247575","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}