{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:07:29Z","timestamp":1784203649245,"version":"3.55.0"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T00:00:00Z","timestamp":1780185600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134135","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:25:13Z","timestamp":1780327513000},"page":"134135","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A hybrid transformer deep Q-network for path planning"],"prefix":"10.1016","volume":"696","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3962-8889","authenticated-orcid":false,"given":"Jiawei","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4277-0773","authenticated-orcid":false,"given":"Yichuan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ge","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2735-5840","authenticated-orcid":false,"given":"Junlin","family":"Ou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134135_bib1","article-title":"Path planning for autonomous mobile robots: a review","volume":"Dec. 01","author":"S\u00e1nchez-Ib\u00e1\u00f1ez","year":"2021","journal-title":"MDPI"},{"issue":"24","key":"10.1016\/j.neucom.2026.134135_bib2","doi-asserted-by":"crossref","DOI":"10.3390\/s24248089","article-title":"A comprehensive study of recent path-planning techniques in dynamic environments for autonomous robots","volume":"24","author":"AbuJabal","year":"2024","journal-title":"Sensors"},{"issue":"3","key":"10.1016\/j.neucom.2026.134135_bib3","doi-asserted-by":"crossref","DOI":"10.1145\/3469086","article-title":"Integrating algorithmic sampling-based motion planning with learning in autonomous driving","volume":"13","author":"Zhang","year":"2022","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"18","key":"10.1016\/j.neucom.2026.134135_bib4","article-title":"Path planning for autonomous vehicles in unknown dynamic environment based on deep reinforcement learning","volume":"13","author":"Hu","year":"2023","journal-title":"Appl. Sci. (Switz. )"},{"key":"10.1016\/j.neucom.2026.134135_bib5","unstructured":"G. Sotirchos and Z. Ajanovic, \u201cSearch-based versus Sampling-based Robot Motion Planning: A Comparative Study,\u201d Jun. 2024, [Online]. Available: \u3008http:\/\/arxiv.org\/abs\/2406.09623\u3009."},{"key":"10.1016\/j.neucom.2026.134135_bib6","doi-asserted-by":"crossref","unstructured":"T. Xu, \u201cRecent advances in Rapidly-exploring random tree: A review,\u201d Jun. 15, 2024, Elsevier Ltd. doi: 10.1016\/j.heliyon.2024.e32451.","DOI":"10.1016\/j.heliyon.2024.e32451"},{"issue":"2024","key":"10.1016\/j.neucom.2026.134135_bib7","first-page":"285","article-title":"Sampling-based motion planning: a comparative review,\u201d Robotics, and Autonomous Systems","volume":"53","author":"Orthey","year":"2025","journal-title":"Annu. Rev. Control. Robot. Auton. Syst."},{"key":"10.1016\/j.neucom.2026.134135_bib8","series-title":"2020 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2020","first-page":"96","article-title":"A generalization of the CHOMP algorithm for UAV collision-free trajectory generation in unknown dynamic environments","author":"Men","year":"2020"},{"key":"10.1016\/j.neucom.2026.134135_bib9","doi-asserted-by":"crossref","unstructured":"Z. Zhang, Y. Xue, N. Figueroa, and K. \u00c5kesson, \u201cGradient Field-Based Dynamic Window Approach for Collision Avoidance in Complex Environments,\u201d Jul. 2025, [Online]. Available: \u3008http:\/\/arxiv.org\/abs\/2504.03260\u3009.","DOI":"10.1109\/IROS60139.2025.11246091"},{"issue":"18","key":"10.1016\/j.neucom.2026.134135_bib10","article-title":"Path planning for autonomous vehicles in unknown dynamic environment based on deep reinforcement learning","volume":"13","author":"Hu","year":"2023","journal-title":"Appl. Sci. (Switz. )"},{"key":"10.1016\/j.neucom.2026.134135_bib11","series-title":"Proceedings - 2023 38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023","first-page":"695","article-title":"Path planning in dynamic environments through trajectory prediction and reinforcement learning","author":"Kong","year":"2023"},{"key":"10.1016\/j.neucom.2026.134135_bib12","unstructured":"S. Gu et al., \u201cA Review of Safe Reinforcement Learning: Methods, Theory and Applications,\u201d May 2022, [Online]. Available: \u3008http:\/\/arxiv.org\/abs\/2205.10330\u3009."},{"key":"10.1016\/j.neucom.2026.134135_bib13","series-title":"2023 5th International Conference on Artificial Intelligence and Computer Applications, ICAICA 2023","first-page":"86","article-title":"A privacy protection method of blockchain-based E-voting using homomorphic encryption and order-preserving encryption","author":"Tang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134135_bib14","unstructured":"\u201cMODEL-BASED OFFLINE REINFORCEMENT LEARNING WITH LOWER EXPECTILE Q-LEARNING.\u201d."},{"issue":"2","key":"10.1016\/j.neucom.2026.134135_bib15","doi-asserted-by":"crossref","first-page":"3918","DOI":"10.1109\/LRA.2021.3065271","article-title":"Uncertainty-aware contact-safe model-based reinforcement learning","volume":"6","author":"Kuo","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.134135_bib16","article-title":"Model-based reinforcement learning: a survey","author":"Moerland","year":"2023","journal-title":"Now. Publ. Inc."},{"key":"10.1016\/j.neucom.2026.134135_bib17","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2022.883562","article-title":"Deep reinforcement learning based trajectory planning under uncertain constraints","volume":"16","author":"Chen","year":"2022","journal-title":"Front. Neurorobot"},{"issue":"1","key":"10.1016\/j.neucom.2026.134135_bib18","doi-asserted-by":"crossref","DOI":"10.1080\/17538947.2024.2376273","article-title":"A deep reinforcement learning with dynamic spatio-temporal graph model for solving urban logistics delivery planning problems","volume":"17","author":"Li","year":"2024","journal-title":"Int. J. Digit. Earth"},{"key":"10.1016\/j.neucom.2026.134135_bib19","unstructured":"N. Kapila, J. Glattki, and T. Rathi, \u201cCNNtention: Can CNNs do better with Attention?,\u201d Dec. 2024, [Online]. Available: \u3008http:\/\/arxiv.org\/abs\/2412.11657\u3009."},{"key":"10.1016\/j.neucom.2026.134135_bib20","unstructured":"S. Editor Wolfgang Walz, \u201cMachine Learning for Brain Disorders.\u201d [Online]. Available: \u3008http:\/\/www.springer.com\/series\/7657\u3009."},{"key":"10.1016\/j.neucom.2026.134135_bib21","doi-asserted-by":"crossref","unstructured":"J. Lin and Q. Ren, \u201cRethinking Spatio-Temporal Transformer for Traffic Prediction:Multi-level Multi-view Augmented Learning Framework,\u201d Jun. 2024, [Online]. Available: \u3008http:\/\/arxiv.org\/abs\/2406.11921\u3009.","DOI":"10.2139\/ssrn.4858193"},{"key":"10.1016\/j.neucom.2026.134135_bib22","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2022.883562","article-title":"Deep reinforcement learning based trajectory planning under uncertain constraints","volume":"16","author":"Chen","year":"2022","journal-title":"Front. Neurorobot"},{"key":"10.1016\/j.neucom.2026.134135_bib23","doi-asserted-by":"crossref","unstructured":"R. Singh, J. Ren, and X. Lin, \u201cA Review of Deep Reinforcement Learning Algorithms for Mobile Robot Path Planning,\u201d Dec. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: \u300810.3390\/vehicles5040078\u3009.","DOI":"10.3390\/vehicles5040078"},{"issue":"17","key":"10.1016\/j.neucom.2026.134135_bib24","article-title":"Reinforcement-learning-based path planning: a reward function strategy","volume":"14","author":"Jaramillo-Mart\u00ednez","year":"2024","journal-title":"Appl. Sci. (Switz. )"},{"key":"10.1016\/j.neucom.2026.134135_bib25","doi-asserted-by":"crossref","first-page":"100083","DOI":"10.1109\/ACCESS.2023.3311519","article-title":"Mobile service robot path planning using deep reinforcement learning","volume":"11","author":"Kumaar","year":"2023","journal-title":"IEEE Access."},{"issue":"1","key":"10.1016\/j.neucom.2026.134135_bib26","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)CP.1943-5487.0001056","article-title":"Prediction-based path planning for safe and efficient human\u2013robot collaboration in construction via deep reinforcement learning","volume":"37","author":"Cai","year":"2023","journal-title":"J. Comput. Civil. Eng."},{"key":"10.1016\/j.neucom.2026.134135_bib27","unstructured":"S. Huang, X. Wu, and G. Huang, \u201cDeep Reinforcement Learning-based Multi-objective Path Planning on the Off-road Terrain Environment for Ground Vehicles.\u201d"},{"issue":"9","key":"10.1016\/j.neucom.2026.134135_bib28","doi-asserted-by":"crossref","first-page":"7747","DOI":"10.1109\/LRA.2024.3421188","article-title":"Deep reinforcement learning with dynamic graphs for adaptive informative path planning","volume":"9","author":"Vashisth","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"9","key":"10.1016\/j.neucom.2026.134135_bib29","article-title":"Iada*-rl: anytime graph-based path planning with deep reinforcement learning for an autonomous uav","volume":"11","author":"Maw","year":"2021","journal-title":"Appl. Sci. (Switz. )"},{"key":"10.1016\/j.neucom.2026.134135_bib30","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"IEEE Conf. Comput. Vision. Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134135_bib31","unstructured":"J. Ho, N. Kalchbrenner, D. Weissenborn, and T. Salimans, \u201cAxial Attention in Multidimensional Transformers,\u201d Dec. 2019, [Online]. Available: \u3008http:\/\/arxiv.org\/abs\/1912.12180\u3009."},{"key":"10.1016\/j.neucom.2026.134135_bib32","unstructured":"Z. Huang et al., \u201cCCNet: Criss-Cross Attention for Semantic Segmentation,\u201d Jul. 2020, [Online]. Available: \u3008http:\/\/arxiv.org\/abs\/1811.11721\u3009."},{"key":"10.1016\/j.neucom.2026.134135_bib33","series-title":"ITM Web of Conferences","first-page":"01001","article-title":"Optimizing waste management systems through image recognition and feature extraction techniques integrating DQN-based models","author":"Liang","year":"2025"},{"issue":"10","key":"10.1016\/j.neucom.2026.134135_bib34","doi-asserted-by":"crossref","first-page":"129","DOI":"10.23919\/JCC.2022.00.025","article-title":"Convolutional neural network-based deep Q-network (CNN-DQN) resource management in cloud radio access network","volume":"19","author":"Iqbal","year":"2022","journal-title":"China Commun."},{"issue":"20","key":"10.1016\/j.neucom.2026.134135_bib35","doi-asserted-by":"crossref","first-page":"4460","DOI":"10.3390\/app9204460","article-title":"Deep LSTM with reinforcement learning layer for financial trend prediction in FX high frequency trading systems","volume":"9","author":"Rundo","year":"2019","journal-title":"Appl. Sci."},{"key":"10.1016\/j.neucom.2026.134135_bib36","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111290","article-title":"Deep LSTM and LSTM-attention Q-learning based reinforcement learning in oil and gas sector prediction","volume":"284","author":"Oyewola","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.neucom.2026.134135_bib37","unstructured":"E.T. Owusu et al., \u201cA transformer-based deep q learning approach for dynamic load balancing in software-defined networks,\u201d arXiv preprint arXiv:2501.12829, 2025."},{"key":"10.1016\/j.neucom.2026.134135_bib38","unstructured":"K. Esslinger, R. Platt, and C. Amato, \u201cDeep transformer q-networks for partially observable reinforcement learning,\u201d arXiv preprint arXiv:2206.01078, 2022."},{"key":"10.1016\/j.neucom.2026.134135_bib39","series-title":"ECAI 2023","first-page":"899","article-title":"Pretraining the vision transformer using self-supervised methods for vision based deep reinforcement learning","author":"Goul\u00e3o","year":"2023"},{"key":"10.1016\/j.neucom.2026.134135_bib40","doi-asserted-by":"crossref","unstructured":"E. Kargar and V. Kyrki, \u201cVision transformer for learning driving policies in complex multi-agent environments,\u201d arXiv preprint arXiv:2109.06514, 2021.","DOI":"10.1109\/IV51971.2022.9827348"},{"key":"10.1016\/j.neucom.2026.134135_bib41","unstructured":"T. Ota, \u201cDecision mamba: Reinforcement learning via sequence modeling with selective state spaces,\u201d arXiv preprint arXiv:2403.19925, 2024."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523122601533X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523122601533X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:41:32Z","timestamp":1784202092000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S092523122601533X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":41,"alternative-id":["S092523122601533X"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134135","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A hybrid transformer deep Q-network for path planning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134135","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134135"}}