{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:50:33Z","timestamp":1777654233259,"version":"3.51.4"},"reference-count":49,"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"}],"funder":[{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009647","name":"Ministry of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009647","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247412","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"13215-13222","source":"Crossref","is-referenced-by-count":1,"title":["Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning"],"prefix":"10.1109","author":[{"given":"Giwon","family":"Lee","sequence":"first","affiliation":[{"name":"KAIST,Department of Mechanical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daehee","family":"Park","sequence":"additional","affiliation":[{"name":"DGIST,Department of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaewoo","family":"Jeong","sequence":"additional","affiliation":[{"name":"KAIST,Department of Mechanical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuk-Jin","family":"Yoon","sequence":"additional","affiliation":[{"name":"KAIST,Department of Mechanical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02256"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981663"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942976"},{"key":"ref7","first-page":"12 029","article-title":"Path planning using neural a* search","volume-title":"International conference on machine learning","author":"Yonetani"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084685"},{"key":"ref11","first-page":"1268","article-title":"Parting with misconceptions about learning-based vehicle motion planning","volume-title":"Proceedings of The 7th Conference on Robot Learning","volume":"229","author":"Dauner"},{"key":"ref12","article-title":"Differentiable constrained imitation learning for robot motion planning and control","author":"Diehl","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01453"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"ref15","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"144","article-title":"Language-guided traffic simulation via scene-level diffusion","volume-title":"conference on Robot Learning","author":"Zhong"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_14"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.75"},{"key":"ref19","article-title":"Training diffusion models with reinforcement learning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Black"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning","author":"Nichol"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28879"},{"key":"ref23","first-page":"1415","article-title":"Maximum likelihood training of score-based diffusion models","volume":"34","author":"Song","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Data-driven diffusion models for enhancing safety in autonomous vehicle traffic simulations","author":"Lu","year":"2024"},{"key":"ref25","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022"},{"key":"ref26","article-title":"Leveraging future relationship reasoning for vehicle trajectory prediction","volume-title":"The Eleventh International Conference on Learning Representations","author":"Park"},{"key":"ref27","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref31","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International Conference on Machine Learning","author":"Silver"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981757"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2904385"},{"key":"ref34","first-page":"199","article-title":"Leader: Learning attention over driving behaviors for planning under uncertainty","volume-title":"Conference on robot learning","author":"Danesh"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636442"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2991584"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_16"},{"key":"ref39","article-title":"Umbrella: Uncertainty-aware model-based offline reinforcement learning leveraging planning","author":"Diehl","year":"2021"},{"key":"ref40","article-title":"Model-based reinforcement learning for atari","author":"Kaiser","year":"2019"},{"key":"ref41","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proceedings of the nineteenth international conference on machine learning","author":"Kakade"},{"key":"ref42","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459260"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2007.01089.x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341265"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_22"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610550"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3283542"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01660"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"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\/11247412.pdf?arnumber=11247412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:38:23Z","timestamp":1766061503000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247412","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}