{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T04:51:01Z","timestamp":1785905461558,"version":"3.56.0"},"reference-count":29,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009096","name":"Firat University","doi-asserted-by":"crossref","award":["ADEP.23.22"],"award-info":[{"award-number":["ADEP.23.22"]}],"id":[{"id":"10.13039\/100009096","id-type":"DOI","asserted-by":"crossref"}]},{"award":["ADEP.23.22"],"award-info":[{"award-number":["ADEP.23.22"]}],"id":[{"id":"https:\/\/ror.org\/05teb7b63","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biomimetics"],"abstract":"<jats:p>Autonomous locomotion in robotic fish requires task-dependent control capabilities under changing environmental conditions. This paper proposes a hierarchical simulation-based control framework for a two-joint robotic fish in a two-dimensional (2D) planar environment. This framework integrates the twin delayed deep deterministic policy gradient (TD3) algorithm with a sensory-feedback central pattern generator (CPG). A nonlinear planar dynamic model is designed as the learning environment, and a CPG network generates rhythmic undulatory swimming. The CPG network generates smooth locomotor patterns, while the TD3 policy performs high-level neuromotor modulation for task-dependent behavior. In the target-reaching benchmark, TD3\u2013CPG achieves a 100.0% success rate with a Wilson 95% confidence interval (CI) of [96.30%, 100.00%], outperforming benchmark models. The proposed controller is also evaluated with obstacle avoidance in target reaching and station keeping under current disturbances. In circular obstacle avoidance, TD3\u2013CPG achieves a 98.0% success rate and a 98.0% safe-pass rate, whereas the multiple rectangular obstacle scenarios yield an overall success rate of 91.7% over 96 trials. In station keeping, the controller achieves stay ratios of 87.57 \u00b1 12.81% under constant current and 96.88 \u00b1 10.79% under gust current, while keeping the mean target distance below the 0.25 m station keeping radius in both cases. Within the adopted 2D planar simulation environment, the obtained results demonstrate that the proposed method exhibits task-dependent maneuvering performance within the evaluated scenarios.<\/jats:p>","DOI":"10.3390\/biomimetics11080534","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T11:50:21Z","timestamp":1785757821000},"page":"534","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Task-Oriented Locomotion Control of a 2D Planar Robotic Fish Model Using Deep Reinforcement Learning and Sensory-Feedback CPG Network"],"prefix":"10.3390","volume":"11","author":[{"given":"Gonca","family":"Ozmen Koca","sequence":"first","affiliation":[{"name":"Department of Mechatronics Engineering, Faculty of Technology, Firat University, 23200 Elazig, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deniz","family":"Korkmaz","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Faculty of Engineering and Natural Sciences, Malatya Turgut Ozal University, 44900 Malatya, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1199-2637","authenticated-orcid":false,"given":"Cafer","family":"Bal","sequence":"additional","affiliation":[{"name":"Department of Mechatronics Engineering, Faculty of Technology, Firat University, 23200 Elazig, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9056-9975","authenticated-orcid":false,"given":"Mustafa","family":"Ay","sequence":"additional","affiliation":[{"name":"Department of Mechatronics Engineering, Faculty of Technology, Firat University, 23200 Elazig, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7935-7031","authenticated-orcid":false,"given":"Zuhtu Hakan","family":"Akpolat","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Faculty of Engineering, Fatih Sultan Mehmet Vakif University, 34015 Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"129328","DOI":"10.1016\/j.neucom.2024.129328","article-title":"Enhancing hexapod robot mobility on challenging terrains: Optimizing CPG-generated gait with reinforcement learning","volume":"622","author":"Huang","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"6115","DOI":"10.1109\/LRA.2024.3399999","article-title":"A Novel Design Methodology of CPG Model for a Salamander-Like Robot","volume":"9","author":"Liu","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1109\/TRO.2025.3539173","article-title":"Integrating Contact-Aware CPG System for Learning-Based Soft Snake Robot Locomotion Controllers","volume":"41","author":"Liu","year":"2025","journal-title":"IEEE Trans. Robot."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"112864","DOI":"10.1016\/j.chaos.2022.112864","article-title":"Toward biomorphic robotics: A review on swimming central pattern generators","volume":"165","author":"Tsybina","year":"2022","journal-title":"Chaos Solitons Fractals"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s10846-022-01797-9","article-title":"A Wire-driven Elastic Robotic Fish and its Design and CPG-Based Control","volume":"107","author":"Liao","year":"2023","journal-title":"J. Intell. Robot. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1080\/20464177.2019.1638703","article-title":"Locomotion control of a biomimetic robotic fish based on closed loop sensory feedback CPG model","volume":"20","author":"Korkmaz","year":"2019","journal-title":"J. Mar. Eng. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"106334","DOI":"10.1016\/j.oceaneng.2019.106334","article-title":"CPG-based autonomous swimming control for multi-tasks of a biomimetic robotic fish","volume":"189","author":"Bal","year":"2019","journal-title":"Ocean Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Su, S., Chen, Y., Li, C., Ni, K., and Zhang, J. (2024). Intelligent Control Strategy for Robotic Manta via CPG and Deep Reinforcement Learning. Drones, 8.","DOI":"10.3390\/drones8070323"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1707","DOI":"10.1007\/s40747-022-00883-7","article-title":"Multi-objective evolutionary design of central pattern generator network for biomimetic robotic fish","volume":"9","author":"Li","year":"2023","journal-title":"Complex Intell. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"045226","DOI":"10.1088\/2631-8695\/ae4672","article-title":"Start-up and gait transitions in bio-inspired fish robots via modified CPG with coupled Hopf oscillators","volume":"8","author":"Ngo","year":"2026","journal-title":"Eng. Res. Express"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"121667","DOI":"10.1016\/j.oceaneng.2025.121667","article-title":"A reinforcement learning-based control approach with lightweight feature for robotic fish heading control in complex environments: Real-world training","volume":"335","author":"Chen","year":"2025","journal-title":"Ocean Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"116259","DOI":"10.1016\/j.oceaneng.2023.116259","article-title":"Reinforcement learning based CPG-controlled method with high adaptability and robustness: An experimental study on a robotic fishtail","volume":"289","author":"Chen","year":"2023","journal-title":"Ocean Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"107056","DOI":"10.1016\/j.compfluid.2026.107056","article-title":"High-efficiency autonomous swimming control of robotic fish in vortex streets: A physics-informed DRL framework","volume":"313","author":"Liu","year":"2026","journal-title":"Comput. Fluids"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"12670","DOI":"10.1109\/TIE.2023.3239937","article-title":"Multiagent-Reinforcement-Learning-Based Stable Path Tracking Control for a Bionic Robotic Fish With Reaction Wheel","volume":"70","author":"Qiu","year":"2023","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"120322","DOI":"10.1016\/j.oceaneng.2025.120322","article-title":"Deep reinforcement learning enabling a BCFbot to learn various undulatory patterns","volume":"320","author":"Hameed","year":"2025","journal-title":"Ocean Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2334","DOI":"10.1109\/JIOT.2024.3472700","article-title":"UPEGSim: An RL-Enabled Simulator for Unmanned Underwater Vehicles Dedicated in the Underwater Pursuit-Evasion Game","volume":"12","author":"Xu","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"105262","DOI":"10.1016\/j.robot.2025.105262","article-title":"AUV decision-making in bistatic sonar target tracking via deep reinforcement learning","volume":"197","author":"Zhan","year":"2026","journal-title":"Robot. Auton. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1007\/s42235-022-00309-7","article-title":"Design of Deep Reinforcement Learning Controller Through Data-assisted Model for Robotic Fish Speed Tracking","volume":"20","author":"Duraisamy","year":"2023","journal-title":"J. Bionic Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1496","DOI":"10.1109\/OJIES.2025.3606965","article-title":"Propulsion Control of Bionic Robotic Fish Based on Deep Deterministic Policy Gradient Algorithm","volume":"6","author":"Xu","year":"2025","journal-title":"IEEE Open J. Ind. Electron. Soc."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1022","DOI":"10.1109\/TCDS.2025.3540071","article-title":"Decentralized Reinforcement Learning for Multiple Robotic Fish in Cooperative Pursuit Task","volume":"17","author":"Feng","year":"2025","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, J., Kang, S., and Yu, J. (2024). Target-Following Control of a Biomimetic Autonomous System Based on Predictive Reinforcement Learning. Biomimetics, 9.","DOI":"10.3390\/biomimetics9010033"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"131173","DOI":"10.1016\/j.neucom.2025.131173","article-title":"Path planning based on improved deep Q-network algorithm for bionic robotic fish with ocean currents","volume":"653","author":"Tian","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Koca, G.O., Bal, C., Korkmaz, D., Bingol, M.C., Ay, M., Akpolat, Z.H., and Yetkin, S. (2018). Three-dimensional modeling of a robotic fish based on real carp locomotion. Appl. Sci., 8.","DOI":"10.3390\/app8020180"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Fossen, T.I. (2011). Handbook of Marine Craft Hydrodynamics and Motion Control, Wiley.","DOI":"10.1002\/9781119994138"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s42235-023-00424-z","article-title":"Bioinspired Closed-loop CPG-based Control of a Robotic Manta for Autonomous Swimming","volume":"21","author":"Hao","year":"2024","journal-title":"J. Bionic Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"116118","DOI":"10.1016\/j.oceaneng.2023.116118","article-title":"A CPG-based framework for flexible locomotion control and propulsion performance evaluation of underwater undulating fin platform","volume":"288","author":"Zhang","year":"2023","journal-title":"Ocean Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1080\/01691864.2013.867283","article-title":"Development of adaptive locomotion of a caterpillar-like robot based on a sensory feedback CPG model","volume":"28","author":"Li","year":"2014","journal-title":"Adv. Robot."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s10846-024-02080-9","article-title":"A Bioinspired Control Strategy Ensures Maneuverability and Adaptability for Dynamic Environments in an Underactuated Robotic Fish","volume":"110","author":"Manduca","year":"2024","journal-title":"J. Intell. Robot. Syst."},{"key":"ref_29","first-page":"1587","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","volume":"Volume 80","author":"Fujimoto","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"}],"container-title":["Biomimetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/8\/534\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T04:32:34Z","timestamp":1785904354000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/8\/534"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,1]]},"references-count":29,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["biomimetics11080534"],"URL":"https:\/\/doi.org\/10.3390\/biomimetics11080534","relation":{},"ISSN":["2313-7673"],"issn-type":[{"value":"2313-7673","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,1]]}}}