Author(s)

ShuoPei Yang, YaNing Zhao^*, ShiYuan Li

Affiliation(s)

Lingjing Jushen (Ningbo) Electronic Technology Co., Ltd., Ningbo 31500, Zhejiang, China.

Corresponding Author

YaNing Zhao

ABSTRACT

This paper aims to address the planning and control challenges faced by underwater vehicles in complex tasks by designing a hybrid algorithm architecture. At the high level, the architecture employs reinforcement learning for task allocation and utilizes a multi-objective evolutionary algorithm for scheduling optimization. At the low level, a control strategy integrating adaptive PID with deep reinforcement learning is designed. Subsequently, dynamic coordination between levels and parameter self-adaptation are achieved through an event-driven switching mechanism and an online learning framework. Experimental results demonstrate that the proposed architecture significantly outperforms baseline algorithms in terms of task completion efficiency, energy consumption, and robustness, providing both theoretical and practical support for underwater vehicle technology.

KEYWORDS

Underwater vehicle; Hybrid architecture; Reinforcement learning; Task planning; Autonomous control

CITE THIS PAPER

ShuoPei Yang, YaNing Zhao, ShiYuan Li. Design and implementation of a hybrid algorithm architecture for underwater vehicles facing complex tasks. World Journal of Information Technology. 2025, 3(3): 89-98. DOI: https://doi.org/10.61784/wjit3057.

REFERENCES

[1] Vasilescu I, Varshavskaya P, Kotay K, et al. Autonomous modular optical underwater robot (AMOUR): design, prototype and feasibility study. IEEE International Conference on Robotics and Automation, 2006: 1603-1609.

[2] Luo XH, Li QP, Zhang ZT, et al. Research on the underwater noise radiation of high pressure water jet propulsion. Ocean Engineering, 2021, 219: 108438.

[3] Zhang XG, Dang HX, Li B, et al. Research on inflation and floating-up process of unmanned underwater vehicle based on collaborative simulation technology. Applied Ocean Research, 2020, 105: 102411.

[4] Wang K, Wang M, Zhao Y. Carrier design and motion control of marine underwater robot. Journal of Coastal Research, 2020, 107(SI): 181-184.

[5] Rober N, Hammond M, Cichella V, et al. 3D path following and L1 adaptive control for underwater vehicles. Ocean Engineering, 2022, 253.

[6] Zhu D, Yang SX, Biglarbegian M. A fuzzy logic-based cascade control without actuator saturation for the unmanned underwater vehicle trajectory tracking. Journal of Intelligent & Robotic Systems, 2022, 106(2).

[7] Dadios EP, Almero VJ, Concepcion RS, et al. Low-cost underwater camera: design and development. JACIII, 2022, 26(5).

[8] Veiga S, Lorenzo J, Trinidad A, et al. Kinematic analysis of the underwater undulatory swimming cycle: a systematic and synthetic review. International Journal of Environmental Research and Public Health, 2022, 19(19).

[9] Yang ZD, Li Z, Jiang XH, et al. Focal and global knowledge distillation for detectors. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022: 4633-4642.

[10] Zhou ZJ, Ou DJ, Zhou XC, et al. Fuzzy PID control system for grinding end-effector based on improved PSO. Modular Machine Tool & Automatic Manufacturing Technique, 2022(4): 57-61.

[11] Dong MX, Kong XZ. Research on leakage compensation of electro-hydraulic proportional valve-controlled cylinder system based on fuzzy PID control. Machine Tool & Hydraulics, 2022, 50(16): 143-149.

[12] Birk A, Doernbach T, Mueller C, et al. Dexterous underwater manipulation from onshore locations: streamlining efficiencies for remotely operated underwater vehicles. IEEE Robotics and Automation Magazine, 2018, 25(4): 24-33.

[13] Brantner G, Khatib O. Controlling Ocean One: human-robot collaboration for deep-sea manipulation. Journal of Field Robotics, 2021, 38(1): 28-51.

[14] Zhu YC, Yang CJ, Tu ZP, et al. A haptic shared control architecture for tracking of a moving object. IEEE Transactions on Industrial Electronics, 2023, 70(5): 5034-5043.

[15] Di Lillo P, Simetti E, Wanderlingh F, et al. Underwater intervention with remote supervision via satellite communication: developed control architecture and experimental results within the DexROV Project. IEEE Transactions on Control Systems Technology, 2021, 29(1): 108-123.

[16] Yang CJ, Zhu YC, Chen YH. A review of human-machine cooperation in the robotics domain. IEEE Transactions on Human-Machine Systems, 2022, 52(1): 12-25.

[17] Youakim D, Ridao P, Palomeras N, et al. Autonomous underwater free-floating manipulation using MoveIt. IEEE Robotics & Automation Magazine, 2017(99): 1.