{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:41:34Z","timestamp":1775068894798,"version":"3.50.1"},"reference-count":35,"publisher":"Tech Science Press","issue":"2","license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"vor","delay-in-days":328,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2024]]},"DOI":"10.32604\/cmc.2024.056791","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T07:14:10Z","timestamp":1729149250000},"page":"2769-2790","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":7,"title":["Improved Double Deep Q Network Algorithm Based on Average Q-Value Estimation and Reward Redistribution for Robot Path Planning"],"prefix":"10.32604","volume":"81","author":[{"given":"Yameng","family":"Yin","sequence":"first","affiliation":[]},{"given":"Lieping","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xiaoxu","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Yilin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jiansheng","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Jianchu","family":"Zou","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2024]]},"reference":[{"key":"ref1","article-title":"A review on path planning and obstacle avoidance algorithms for autonomous mobile robots","volume":"2022","author":"Rafai","journal-title":"J. Robot."},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.3390\/biomimetics8040374","article-title":"Application of the improved rapidly exploring random tree algorithm to an insect-like mobile robot in a narrow environment","volume":"8","author":"Wang","year":"2023","journal-title":"Biomimetics"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1002\/tee.23592","article-title":"Path planning algorithm for unmanned surface vehicle based on optimized ant colony algorithm","volume":"17","author":"Cui","year":"2022","journal-title":"IEEJ Trans. Electr. Electron. Eng."},{"key":"ref4","series-title":"Int. Conf. Neur. Com. Adv. App.","author":"Hou","year":"Jul. 8\u201310, 2022"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"92433","DOI":"10.1109\/ACCESS.2023.3302698","article-title":"Route planning for an autonomous robotic vehicle employing a weight-controlled particle swarm-optimized Dijkstra algorithm","volume":"11","author":"Sundarraj","year":"2023","journal-title":"IEEE Access"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2255","DOI":"10.2514\/1.J062670","article-title":"Path planning of slender tensegrities based on the artificial potential field method","volume":"61","author":"Mao","year":"2023","journal-title":"AIAA J."},{"key":"ref7","doi-asserted-by":"crossref","first-page":"e1347","DOI":"10.7717\/peerj-cs.1347","article-title":"Green city logistics path planning and design based on genetic algorithm","volume":"2023","author":"Ran","year":"2023","journal-title":"PeerJ. Comput. Sci."},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.3390\/drones7030211","article-title":"Review of autonomous path planning algorithms for mobile robots","volume":"7","author":"Qin","year":"2023","journal-title":"Drones"},{"key":"ref9","article-title":"Path following for autonomous mobile robots with deep reinforcement learning","volume":"24","author":"Cao","year":"2024","journal-title":"Sensors"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.3390\/s22062367","article-title":"A hierarchical path planning approach with Multi-SARSA based on topological map","volume":"22","author":"Wen","year":"2022","journal-title":"Sensors"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111400","article-title":"An optimized Q-Learning algorithm for mobile robot local path planning","volume":"286","author":"Zhou","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128085","article-title":"Real-time local path planning strategy based on deep distributional reinforcement learning","volume":"599","author":"Du","year":"2024","journal-title":"Neurocomputing"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.110543","article-title":"Deep reinforcement learning for optimal rescue path planning in uncertain and complex urban pluvial flood scenarios","volume":"144","author":"Li","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.3390\/app13127202","article-title":"Autonomous navigation of robots: Optimization with DQN","volume":"13","author":"Escobar-Naranjo","year":"2023","journal-title":"Appl. Sci."},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.3390\/electronics13132568","article-title":"A deep reinforcement learning algorithm for trajectory planning of swarm uav fulfilling wildfire reconnaissance","volume":"13","author":"Demir","year":"2024","journal-title":"Electronics"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"565","DOI":"10.53106\/160792642023052403001","article-title":"Automatic path planning for spraying drones based on deep Q-Learning","volume":"24","author":"Huang","year":"2023","journal-title":"J. Internet Technol."},{"key":"ref17","doi-asserted-by":"crossref","first-page":"5895","DOI":"10.1109\/LRA.2024.3398428","article-title":"On the role of the action space in robot manipulation learning and sim-to-real transfer","volume":"9","author":"Aljalbout","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.3390\/act13010026","article-title":"Experimental research on avoidance obstacle control for mobile robots using Q-Learning (QL) and deep Q-Learning (DQL) algorithms in dynamic environments","volume":"13","author":"Ha","year":"2024","journal-title":"Actuators"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1007\/s11227-021-03878-2","article-title":"An improved DQN path planning algorithm","volume":"78","author":"Li","year":"2022","journal-title":"J. Supercomput."},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.3390\/s24051523","article-title":"Enhancing stability and performance in mobile robot path planning with PMR-Dueling DQN algorithm","volume":"24","author":"Deguale","year":"2024","journal-title":"Sensors"},{"key":"ref21","unstructured":"R. Q. Zhao, X. Lu, S. B. Lyu, J. H. Zhang, and F. S. Li, \u201cDeep reinforcement learning based path planning for mobile robots using time-sensitive reward,\u201d presented at 2022 19th ICCWAMTIP, Chengdu, China, Dec. 16\u201318, 2022."},{"key":"ref22","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1016\/j.cja.2024.03.008","article-title":"Controlling underestimation bias in reinforcement learning via minmax operation","volume":"37","author":"Huang","year":"2024","journal-title":"Chin. J. Aeronaut."},{"key":"ref23","doi-asserted-by":"crossref","first-page":"17495","DOI":"10.1109\/JIOT.2024.3359277","article-title":"Qiu \u201cdeep-reinforcement-learning-based distributed dynamic spectrum access in multiuser multichannel cognitive radio internet of things networks","volume":"11","author":"Zhang","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref24","article-title":"Research on dynamic path planning of wheeled robot based on deep reinforcement learning on the slope ground","volume":"2020","author":"Wang","year":"2020","journal-title":"J. Robot."},{"key":"ref25","doi-asserted-by":"crossref","first-page":"51012","DOI":"10.1109\/ACCESS.2024.3354075","article-title":"Path planning for outdoor mobile robots based on IDDQN","volume":"12","author":"Jiang","year":"2024","journal-title":"IEEE Access"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127491","article-title":"Adaptive operator selection with dueling deep Q-network for evolutionary multi-objective optimization","volume":"581","author":"Yin","year":"2024","journal-title":"Neurocomputing"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.3390\/e24121767","article-title":"Path planning research of a UAV base station searching for disaster victims\u2019 location information based on deep reinforcement learning","volume":"24","author":"Zhao","year":"2022","journal-title":"Entropy"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"825","DOI":"10.18494\/SAM.2021.3050","article-title":"Enhanced autonomous navigation of robots by deep reinforcement learning algorithm with multistep method","volume":"33","author":"Peng","year":"2021","journal-title":"Sensors & Materials"},{"key":"ref29","article-title":"A DDQN path planning algorithm based on experience classification and multi steps for mobile robots","volume":"11","author":"Zhang","year":"2022","journal-title":"Electronics"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1109\/TIV.2022.3153352","article-title":"Path planning based on deep reinforcement learning for autonomous underwater vehicles under ocean current disturbance","volume":"8","author":"Chu","year":"2023","journal-title":"IEEE Trans. Intell. Vehicles"},{"key":"ref31","article-title":"Global path planning algorithm based on double DQN for multi-tasks amphibious unmanned surface vehicle","volume":"266","author":"Yang","year":"2022","journal-title":"Ocean Eng."},{"key":"ref32","series-title":"Proc. 34th In Int. conf. Mach. Learn.","first-page":"176","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","author":"Anschel","year":"2017"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.3390\/app9224964","article-title":"A novel searching method using reinforcement learning scheme for multi-UAVs in unknown environments","volume":"9","author":"Yue","year":"2019","journal-title":"Appl. Sci."},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1142\/S0218126622502589","article-title":"Mobile robot path planning method based on deep reinforcement learning algorithm","volume":"31","author":"Meng","year":"2022","journal-title":"J. Circuits, Syst. Comput."},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1109\/LRA.2020.2965857","article-title":"Deep reinforcement learning for instruction following visual navigation in 3D maze-like environments","volume":"5","author":"Devo","year":"2020","journal-title":"IEEE Robot. Autom. Lett."}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.techscience.com\/files\/cmc\/2024\/TSP_CMC-81-2\/TSP_CMC_56791\/TSP_CMC_56791.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T04:18:09Z","timestamp":1741321089000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v81n2\/58661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":35,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024]]},"published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2024.056791","relation":{},"ISSN":["1546-2226"],"issn-type":[{"value":"1546-2226","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2024-07-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-30","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-18","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}