{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T16:03:40Z","timestamp":1779811420383,"version":"3.53.1"},"reference-count":68,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.engappai.2026.114954","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T12:36:56Z","timestamp":1778071016000},"page":"114954","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["A study on deep reinforcement learning-based exploration intelligence for occluded object search"],"prefix":"10.1016","volume":"178","author":[{"given":"Haneul","family":"Jeon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taeho","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donggyu","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1814-2683","authenticated-orcid":false,"given":"Donghun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114954_b1","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3579863","article-title":"Autonomous mobile robot path planning techniques, a review: Classical and heuristic techniques.","author":"Badamasi","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114954_b2","series-title":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4678","article-title":"Occlusion-aware search for object retrieval in clutter","author":"Bejjani","year":"2021"},{"key":"10.1016\/j.engappai.2026.114954_b3","first-page":"679","article-title":"A Markovian decision process","author":"Bellman","year":"1957","journal-title":"J. Math. Mech."},{"key":"10.1016\/j.engappai.2026.114954_b4","doi-asserted-by":"crossref","first-page":"53146","DOI":"10.52202\/075280-2313","article-title":"Pomdp planning for object search in partially unknown environment","volume":"36","author":"Chen","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114954_b5","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"11224","article-title":"Language-guided active sensing of confined, cluttered environments via object rearrangement planning","author":"Chen","year":"2024"},{"key":"10.1016\/j.engappai.2026.114954_b6","series-title":"2020 IEEE International Conference on Robotics and Automation","first-page":"7791","article-title":"Where to relocate?: Object rearrangement inside cluttered and confined environments for robotic manipulation","author":"Cheong","year":"2020"},{"issue":"2","key":"10.1016\/j.engappai.2026.114954_b7","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.ejor.2021.10.045","article-title":"Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management","volume":"301","author":"De Moor","year":"2022","journal-title":"European J. Oper. Res."},{"key":"10.1016\/j.engappai.2026.114954_b8","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1178","article-title":"Viewpoint push planning for mapping of unknown confined spaces","author":"Dengler","year":"2023"},{"key":"10.1016\/j.engappai.2026.114954_b9","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1178","article-title":"Viewpoint push planning for mapping of unknown confined spaces","author":"Dengler","year":"2023"},{"key":"10.1016\/j.engappai.2026.114954_b10","series-title":"Reward design for reinforcement learning agents","author":"Devidze","year":"2025"},{"issue":"4","key":"10.1016\/j.engappai.2026.114954_b11","doi-asserted-by":"crossref","first-page":"80","DOI":"10.3390\/logistics7040080","article-title":"A systematic literature review on the application of automation in logistics","volume":"7","author":"Ferreira","year":"2023","journal-title":"Logistics"},{"key":"10.1016\/j.engappai.2026.114954_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.omega.2022.102634","article-title":"Joint shelf design and shelf space allocation problem for retailers","volume":"111","author":"Gecili","year":"2022","journal-title":"Omega"},{"key":"10.1016\/j.engappai.2026.114954_b13","series-title":"2021 20th International Conference on Advanced Robotics","first-page":"676","article-title":"Robotic weight-based object relocation in clutter via tree-based q-learning approach using breadth and depth search techniques","author":"Golluccio","year":"2021"},{"key":"10.1016\/j.engappai.2026.114954_b14","doi-asserted-by":"crossref","unstructured":"Gu, J., Li, K., Wang, F., Wei, Y., Wu, Z., Fan, H., Wang, M., 2025. Motion matters: Motion-guided modulation network for skeleton-based micro-action recognition. In: Proceedings of the 33rd ACM International Conference on Multimedia. pp. 5461\u20135470.","DOI":"10.1145\/3746027.3754722"},{"issue":"4","key":"10.1016\/j.engappai.2026.114954_b15","doi-asserted-by":"crossref","first-page":"1079","DOI":"10.1080\/01605682.2022.2056532","article-title":"Retail store layout optimization for maximum product visibility","volume":"74","author":"Gul","year":"2023","journal-title":"J. Oper. Res. Soc."},{"key":"10.1016\/j.engappai.2026.114954_b16","doi-asserted-by":"crossref","first-page":"159672","DOI":"10.1109\/ACCESS.2021.3131772","article-title":"Guided soft actor critic: A guided deep reinforcement learning approach for partially observable Markov decision processes","volume":"9","author":"Haklidir","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114954_b17","series-title":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"2045","article-title":"Mechanical search on shelves using lateral access x-ray","author":"Huang","year":"2021"},{"key":"10.1016\/j.engappai.2026.114954_b18","series-title":"Learning humanoid standing-up control across diverse postures","author":"Huang","year":"2025"},{"key":"10.1016\/j.engappai.2026.114954_b19","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3504735","article-title":"Comprehensive overview of reward engineering and shaping in advancing reinforcement learning applications","author":"Ibrahim","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114954_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2023.109262","article-title":"Picking with a robot colleague: A systematic literature review and evaluation of technology acceptance in human\u2013robot collaborative warehouses","volume":"180","author":"Jacob","year":"2023","journal-title":"Comput. Ind. Eng."},{"key":"10.1016\/j.engappai.2026.114954_b21","series-title":"A Study on Deep Reinforcement Learning-Based Exploration Intelligence for Occluded Object Search","author":"Jeon","year":"2025"},{"key":"10.1016\/j.engappai.2026.114954_b22","series-title":"2023 IEEE International Conference on Sensors, Electronics and Computer Engineering","first-page":"71","article-title":"Deep Q-network based target search of UAV under partially observable conditions","author":"Jiang","year":"2023"},{"key":"10.1016\/j.engappai.2026.114954_b23","series-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"10921","article-title":"Grasp planning for occluded objects in a confined space with lateral view using monte carlo tree search","author":"Kang","year":"2022"},{"key":"10.1016\/j.engappai.2026.114954_b24","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"2004","article-title":"Object rearrangement planning for target retrieval in a confined space with lateral view","author":"Kang","year":"2023"},{"key":"10.1016\/j.engappai.2026.114954_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.robot.2023.104461","article-title":"Online active and dynamic object shape exploration with a multi-fingered robotic hand","volume":"166","author":"Khadivar","year":"2023","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.engappai.2026.114954_b26","series-title":"Reward shaping for improved learning in real-time strategy game play","author":"Kliem","year":"2023"},{"key":"10.1016\/j.engappai.2026.114954_b27","series-title":"Sight over site: Perception-aware reinforcement learning for efficient robotic inspection","author":"Kuhlmann","year":"2025"},{"key":"10.1016\/j.engappai.2026.114954_b28","series-title":"2021 IEEE International Conference on Robotics and Automation","first-page":"8516","article-title":"Tree search-based task and motion planning with prehensile and non-prehensile manipulation for obstacle rearrangement in clutter","author":"Lee","year":"2021"},{"key":"10.1016\/j.engappai.2026.114954_b29","doi-asserted-by":"crossref","first-page":"134899","DOI":"10.1109\/ACCESS.2022.3232130","article-title":"Local and global search-based planning for object rearrangement in clutter","volume":"10","author":"Lee","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114954_b30","first-page":"4815","article-title":"Prototypical calibrating ambiguous samples for micro-action recognition","volume":"vol. 39","author":"Li","year":"2025"},{"key":"10.1016\/j.engappai.2026.114954_b31","series-title":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"2686","article-title":"Robotic occlusion reasoning for efficient object existence prediction","author":"Li","year":"2021"},{"key":"10.1016\/j.engappai.2026.114954_b32","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T., 2015. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10.1016\/j.engappai.2026.114954_b33","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.robot.2016.08.001","article-title":"Heuristic approaches in robot path planning: A survey","volume":"86","author":"Mac","year":"2016","journal-title":"Robot. Auton. Syst."},{"issue":"2","key":"10.1016\/j.engappai.2026.114954_b34","first-page":"239","article-title":"Adoption of service robots: exploring the emerging trends through the lens of bibliometric analysis","volume":"38","author":"Madhan","year":"2024","journal-title":"Int. Hosp. Rev."},{"issue":"5","key":"10.1016\/j.engappai.2026.114954_b35","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1111\/jpim.12756","article-title":"Service robots and innovation: An ecosystem approach","volume":"42","author":"Mahr","year":"2025","journal-title":"J. Prod. Innov. Manage."},{"key":"10.1016\/j.engappai.2026.114954_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbusres.2025.115204","article-title":"Evolution of service robots in marketing: A relational framework and future research agenda","volume":"192","author":"Mahr","year":"2025","journal-title":"J. Bus. Res."},{"key":"10.1016\/j.engappai.2026.114954_b37","series-title":"Intelligent humanoids in manufacturing to address worker shortage and skill gaps: Case of tesla optimus","author":"Malik","year":"2023"},{"key":"10.1016\/j.engappai.2026.114954_b38","series-title":"Isaac lab: A GPU-accelerated simulation framework for multi-modal robot learning","author":"Mittal","year":"2025"},{"issue":"20","key":"10.1016\/j.engappai.2026.114954_b39","doi-asserted-by":"crossref","first-page":"7938","DOI":"10.3390\/s22207938","article-title":"Review of learning-based robotic manipulation in cluttered environments","volume":"22","author":"Mohammed","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.engappai.2026.114954_b40","doi-asserted-by":"crossref","first-page":"209320","DOI":"10.1109\/ACCESS.2020.3038605","article-title":"A gentle introduction to reinforcement learning and its application in different fields","volume":"8","author":"Naeem","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114954_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107202","article-title":"Sample-efficient and occlusion-robust reinforcement learning for robotic manipulation via multimodal fusion dualization and representation normalization","volume":"185","author":"Noh","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.engappai.2026.114954_b42","series-title":"NVIDIA Isaac Sim: Robotics simulation and synthetic data generation","author":"NVIDIA","year":"2025"},{"key":"10.1016\/j.engappai.2026.114954_b43","series-title":"2020 IEEE International Conference on Robotics and Automation","first-page":"6723","article-title":"Non-prehensile manipulation in clutter with human-in-the-loop","author":"Papallas","year":"2020"},{"key":"10.1016\/j.engappai.2026.114954_b44","series-title":"2022 International Conference on Robotics and Automation","first-page":"9295","article-title":"Semi-autonomous teleoperation via learning non-prehensile manipulation skills","author":"Park","year":"2022"},{"key":"10.1016\/j.engappai.2026.114954_b45","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"7301","article-title":"Reinforcement learning for active search and grasp in clutter","author":"Pitcher","year":"2024"},{"key":"10.1016\/j.engappai.2026.114954_b46","series-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"10.1016\/j.engappai.2026.114954_b47","series-title":"Simplifying reward design through divide-and-conquer","author":"Ratner","year":"2018"},{"key":"10.1016\/j.engappai.2026.114954_b48","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"15388","article-title":"Neural rearrangement planning for object retrieval from confined spaces perceivable by robot\u2019s in-hand rgb-d sensor","author":"Ren","year":"2024"},{"key":"10.1016\/j.engappai.2026.114954_b49","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.engappai.2026.114954_b50","series-title":"Rsl-rl: A learning library for robotics research","author":"Schwarke","year":"2025"},{"key":"10.1016\/j.engappai.2026.114954_b51","article-title":"Grocery product arrangement using cluster analysis","author":"Seva","year":"2019","journal-title":"Int. MultiConference Eng. Comput. Sci."},{"issue":"1","key":"10.1016\/j.engappai.2026.114954_b52","doi-asserted-by":"crossref","DOI":"10.1002\/smb2.12008","article-title":"A comprehensive review of humanoid robots","volume":"1","author":"Sheng","year":"2025","journal-title":"SmartBot"},{"key":"10.1016\/j.engappai.2026.114954_b53","first-page":"2607","article-title":"Reward shaping for deep reinforcement learning in VizDoom","volume":"192","author":"Sopov","year":"2021","journal-title":"Procedia Comput. Sci."},{"issue":"19","key":"10.1016\/j.engappai.2026.114954_b54","doi-asserted-by":"crossref","first-page":"13145","DOI":"10.1007\/s00521-022-07691-7","article-title":"Influence-aware memory architectures for deep reinforcement learning in POMDPs","volume":"37","author":"Suau","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.engappai.2026.114954_b55","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"1998"},{"key":"10.1016\/j.engappai.2026.114954_b56","doi-asserted-by":"crossref","DOI":"10.1016\/j.jretconser.2024.104085","article-title":"Revolutionizing retail: the transformative power of service robots on shopping dynamics","volume":"82","author":"Vinoi","year":"2025","journal-title":"J. Retail. Consum. Serv."},{"key":"10.1016\/j.engappai.2026.114954_b57","series-title":"2019 International Conference on Robotics and Automation","first-page":"7194","article-title":"Multi-object search using object-oriented pomdps","author":"Wandzel","year":"2019"},{"key":"10.1016\/j.engappai.2026.114954_b58","doi-asserted-by":"crossref","DOI":"10.1016\/j.jretconser.2022.103002","article-title":"The impact of service robots in retail: Exploring the effect of novelty priming on consumer behavior","volume":"68","author":"Wang","year":"2022","journal-title":"J. Retail. Consum. Serv."},{"key":"10.1016\/j.engappai.2026.114954_b59","series-title":"2022 International Conference on Robotics and Automation","first-page":"1968","article-title":"Efficient and high-quality prehensile rearrangement in cluttered and confined spaces","author":"Wang","year":"2022"},{"key":"10.1016\/j.engappai.2026.114954_b60","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"5715","article-title":"Safe and effective picking paths in clutter given discrete distributions of object poses","author":"Wang","year":"2020"},{"key":"10.1016\/j.engappai.2026.114954_b61","series-title":"Reinforcement learning and Markov decision processes","author":"Williams","year":"2007"},{"key":"10.1016\/j.engappai.2026.114954_b62","doi-asserted-by":"crossref","unstructured":"Wu, Z., Chen, K., Li, K., Fan, H., Yang, Y., 2025a. BVINet: Unlocking blind video inpainting with zero annotations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 14017\u201314027.","DOI":"10.1109\/ICCV51701.2025.01301"},{"key":"10.1016\/j.engappai.2026.114954_b63","series-title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","first-page":"2063","article-title":"Drafting and revision: advancing high-fidelity video inpainting","author":"Wu","year":"2025"},{"key":"10.1016\/j.engappai.2026.114954_b64","first-page":"6180","article-title":"WaveFormer: wavelet transformer for noise-robust video inpainting","volume":"vol. 38","author":"Wu","year":"2024"},{"key":"10.1016\/j.engappai.2026.114954_b65","doi-asserted-by":"crossref","first-page":"147728","DOI":"10.1109\/ACCESS.2020.3014047","article-title":"Design of smart unstaffed retail shop based on IoT and artificial intelligence","volume":"8","author":"Xu","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114954_b66","series-title":"2022 International Conference on Robotics and Automation","first-page":"7313","article-title":"Towards optimal correlational object search","author":"Zheng","year":"2022"},{"issue":"10","key":"10.1016\/j.engappai.2026.114954_b67","doi-asserted-by":"crossref","first-page":"2634","DOI":"10.1016\/j.ifacol.2025.09.443","article-title":"Human robot collaboration in warehousing operations: a sociotechnical analysis","volume":"59","author":"Zheng","year":"2025","journal-title":"IFAC-PapersOnLine"},{"key":"10.1016\/j.engappai.2026.114954_b68","series-title":"RSJ International Conference on Intelligent Robots and Systems","first-page":"2022","article-title":"Multi-resolution pomdp planning for multi-object search in 3d. In 2021 IEEE","author":"Zheng","year":"2020"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626012364?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626012364?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T15:11:07Z","timestamp":1779808267000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626012364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":68,"alternative-id":["S0952197626012364"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114954","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A study on deep reinforcement learning-based exploration intelligence for occluded object search","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114954","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"114954"}}