{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T06:35:53Z","timestamp":1787898953594,"version":"build-2784847793"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009019","name":"Shenzhen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009019","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,8]]},"DOI":"10.1109\/icarm62033.2024.10715841","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:27:32Z","timestamp":1729272452000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Robust UAV Policy Learning for Urban Infrastructure Surface Screening*"],"prefix":"10.1109","author":[{"given":"Bingqing","family":"Du","sequence":"first","affiliation":[{"name":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China,518060"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uddin Md.","family":"Borhan","sequence":"additional","affiliation":[{"name":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China,518060"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxing","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China,518060"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyong","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China,518060"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China,518060"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdeveco.2021.102629"},{"key":"ref2","article-title":"Upac safety guide for helicopter operators","volume-title":"Tech. Rep., Tech. Rep","author":"Committee","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CP.1943-5487.0000954"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967577"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980359"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103503"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1061\/(asce)cp.1943-5487.0000958"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1590\/s1983-41952023000100003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICARM58088.2023.10218933"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636814"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3391017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635893"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561917"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864373"},{"key":"ref16","article-title":"On reward shaping for mobile robot navigation: A reinforcement learning and slam based approach","author":"Botteghi","year":"2020","journal-title":"arXiv preprint:2002.04109"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-019-00310-w"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/app10238386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE56824.2022.9996006"},{"key":"ref20","article-title":"Reward shaping via meta-learning","author":"Zou","year":"2019","journal-title":"arXiv preprint arXiv:1901.09330"},{"key":"ref21","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","volume-title":"Proc. ICML","volume":"98","author":"Randl\u00f8v"},{"key":"ref22","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. ICML","volume":"99","author":"Ng"},{"key":"ref23","first-page":"792","article-title":"Principled methods for advising reinforcement learning agents","volume-title":"Proc. ICML","author":"Wiewiora"},{"key":"ref24","first-page":"433","article-title":"Dynamic potential-based reward shaping","volume-title":"Proc. AAMAS","author":"Devlin"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9628"},{"key":"ref26","article-title":"Reward shaping in episodic reinforcement learning","volume-title":"Proc. AAAI","author":"Grzes"},{"key":"ref27","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","volume-title":"Proc. ICLR","author":"Wu"},{"key":"ref28","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv preprint:1912.06680"},{"key":"ref29","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume-title":"Proc. NeurIPS","volume":"33","author":"Hu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.02.007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2854967"},{"key":"ref33","article-title":"Flightmare: A flexible quadrotor simulator","volume-title":"Proc. CoRL","author":"Song"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"}],"event":{"name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","location":"Tokyo, Japan","start":{"date-parts":[[2024,7,8]]},"end":{"date-parts":[[2024,7,10]]}},"container-title":["2024 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10715684\/10715739\/10715841.pdf?arnumber=10715841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T17:18:21Z","timestamp":1729531101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10715841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icarm62033.2024.10715841","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]}}}