Adaptive Task-Oriented Locomotion Control of a 2D Planar Robotic Fish Model Using Deep Reinforcement Learning and Sensory-Feedback CPG Network
Biomimetics · 01.08.2026 · 11 (8) · 534
DOI: 10.3390/biomimetics11080534 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomimetics, online erschienen am 01.08.2026. Verfasst von Gonca Ozmen Koca und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechatronics Engineering, Faculty of Technology, Firat University, 23200 Elazig, Turkey. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fırat University, Firat University.
Abstract (Originalsprache)
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–CPG 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–CPG 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 ± 12.81% under constant current and 96.88 ± 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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mechatronics Engineering, Faculty of Technology, Firat University, 23200 Elazig, Turkey.
- Department of Electrical and Electronics Engineering, Faculty of Engineering and Natural Sciences, Malatya Turgut Ozal University, 44900 Malatya, Turkey.
- Department of Electrical and Electronics Engineering, Faculty of Engineering, Fatih Sultan Mehmet Vakif University, 34015 Istanbul, Turkey.
ORCID-Profile: Gonca Ozmen Koca, Cafer Bal, Mustafa Ay, Zuhtu Hakan Akpolat
Förderung
- Fırat University
- Firat University
Zitieren
APA
Ozmen Koca, G., Korkmaz, D., Bal, C., Ay, M., & Akpolat, Z. H. (2026). Adaptive Task-Oriented Locomotion Control of a 2D Planar Robotic Fish Model Using Deep Reinforcement Learning and Sensory-Feedback CPG Network. Biomimetics, 11(8), 534. https://doi.org/10.3390/biomimetics11080534
Vancouver
Ozmen Koca G, Korkmaz D, Bal C, Ay M, Akpolat ZH. Adaptive Task-Oriented Locomotion Control of a 2D Planar Robotic Fish Model Using Deep Reinforcement Learning and Sensory-Feedback CPG Network. Biomimetics. 2026;11(8):534. doi:10.3390/biomimetics11080534
BibTeX
@article{OzmenKoca2026,
author = {Ozmen Koca, Gonca and Korkmaz, Deniz and Bal, Cafer and Ay, Mustafa and Akpolat, Zuhtu Hakan},
title = {Adaptive Task-Oriented Locomotion Control of a 2D Planar Robotic Fish Model Using Deep Reinforcement Learning and Sensory-Feedback CPG Network},
journal = {Biomimetics},
year = {2026},
volume = {11},
number = {8},
pages = {534},
doi = {10.3390/biomimetics11080534}
}
EUVIMED