{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:10:45Z","timestamp":1730297445247,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/smc53992.2023.10394052","type":"proceedings-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:32:04Z","timestamp":1706553124000},"page":"3835-3841","source":"Crossref","is-referenced-by-count":0,"title":["EPO-S: A Constrained RL Method to Enhance UAV Safety with Spatial Representation"],"prefix":"10.1109","author":[{"given":"Qin","family":"Zhang","sequence":"first","affiliation":[{"name":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China"}]},{"given":"Linrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China"}]},{"given":"Zaihui","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China"}]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China"}]},{"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China"}]},{"given":"Yongzhe","family":"Chang","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11119-012-9274-5"},{"volume-title":"Remote sensing and image interpretation","year":"2015","author":"Lillesand","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"issue":"11","key":"ref5","first-page":"1647","article-title":"Mobile robot optimal path planning based on smoothing a* algorithm","volume":"38","author":"Wang","year":"2010","journal-title":"Journal of Tongji University(Natural Science)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2016.03.049"},{"issue":"4","key":"ref7","first-page":"514","article-title":"An improved rrt -connect algorithm used for uav 3d trajectory planning","volume":"9","author":"Tian","year":"2018","journal-title":"Advances in Aeronautical Science and Engineering"},{"issue":"3","key":"ref8","first-page":"203","article-title":"Ga\/dp hybrid solution for uav multi-target path planning","volume":"48","author":"Lin","year":"2016","journal-title":"Journal of Aeronautics, Astronautics and Aviation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107376"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3301273"},{"key":"ref12","article-title":"Au-tonomous uav navigation using reinforcement learning","author":"Pham","year":"2018","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5739-5"},{"key":"ref14","article-title":"Concrete problems in ai safety","author":"Amodei","year":"2016","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/IFIPNetworking52078.2021.9472202"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2017.03.095"},{"key":"ref17","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam","year":"2017"},{"key":"ref18","first-page":"15338","article-title":"First order constrained optimization in policy space","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Feasible actor-critic: Constrained reinforcement learning for ensuring statewise safety","author":"Ma","year":"2021","journal-title":"arXiv preprint"},{"issue":"1","key":"ref20","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Model-free safe control for zero-violation reinforcement learning","volume-title":"5th Annual Conference on Robot Learning","author":"Zhao","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982038"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref27","first-page":"1587","article-title":"Addressing function approxi-mation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto","year":"2018"},{"issue":"1","key":"ref28","first-page":"2","article-title":"Benchmarking safe exploration in deep reinforcement learning","volume":"7","author":"Ray","year":"2019","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2023,10,1]]},"location":"Honolulu, Oahu, HI, USA","end":{"date-parts":[[2023,10,4]]}},"container-title":["2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10391856\/10393862\/10394052.pdf?arnumber=10394052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T13:07:08Z","timestamp":1706792828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10394052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/smc53992.2023.10394052","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}