为提高多机器鱼在未知复杂水域中的探测质量和效率，提出了基于T细胞效应的环境免疫协作探测模型和算法。首先基于Jerne的独特型免疫网络假设构建多机器鱼基本免疫协作探测网络模型；然后根据已探测区域的环境信息，借鉴生物T细胞效应，构建多机器鱼的互联耦合免疫协作探测网络模型；最后进行算法设计和实验测试。实验结果表明，与基于免疫机理的完全探测算法和基于生物熵的免疫协作探测算法相比，文中算法的覆盖率平均提高了7.6%，重复探测率平均降低了32.8%，平均探测步数平均降低了11.6%，平均重复探测步数平均降低了24.7%，验证了未知复杂环境中多机器鱼互联耦合免疫协作探测网络模型的有效性。
To enhance the detection quality and efficiency of underwater multi-robot fish in unknown complex environments. A model and algorithm for immune collaborative environment detection based on T cell effector function are proposed. Firstly, a basic immune collaborative detection network model for multi-robot fish is constructed based on Jerne's idiotype immune network hypothesis. Then, an interconnected coupled immune detection network model for multi-robot fish is constructed on the basis of biological T cell effect. Finally, algorithm design and experimental testing are conducted. The experimental results indicate that, compared to the fully detection algorithm based on immune mechanism and the immune cooperative detection algorithm based on biological entropy, the algorithm proposed in this paper has an average increase in the coverage rate of 7.6%, a decrease in the average repeated detection rate of 32.8%, a decrease in the average detection steps of 11.6%, and a decrease in the average repeated detection steps of 24.7%. This validates the effectiveness of the immune collaborative detection network model of multi-robot fish in unknown complex environments.
2025,47(4): 154-162 收稿日期：2024-4-2
DOI：10.3404/j.issn.1672-7649.2025.04.025
分类号：TP242；TP391.41
基金项目：工信部高技术船舶项目（[2019]360）；张家港市产业链创新产品攻关计划（ZKC2206）；张家港市产学研预研资金（ZKYY2253，ZKYY2328）
作者简介：江亚峰(1990-),男,硕士,讲师,研究方向为人工智能、装备控制
参考文献：
[1] LINDQVIST B, KARLSSON S, KOVAL A, et al. Multimodality robotic systems: integrated combined legged-aerial mobility for subterranean search-and-rescue[J]. Robotics and Autonomous Systems, 2022(154): 104134.
[2] MARTORELL T A, GUERRERO S J, OLIVER C G. Coordination of marine multi robot systems with communication constraints[J]. Applied Ocean Research, 2024(142): 103848.
[3] GIL E B, RODRIGUES G N, PELLICCIONE P, et al. Mission specification and decomposition for multi-robot systems[J]. Robotics and Autonomous Systems, 2023(163): 104386.
[4] 王钧琪, 张小俊. 基于GA-MTSP的多机器人同步覆盖路径规划[J]. 制造业自动化, 2023, 45(3): 109-113.
[5] 孟彩茹, 杜金鹏, 张维民, 等. 填埋场裸膜红外巡检机器人最优路径规划[J]. 科学技术与工程, 2022, 22(30): 13338-13344.
[6] ZHAO S, HWANG S H. Complete coverage path planning scheme for autonomous navigation ROS-Based Robots[J]. ICT Express, 2024, 10(1): 83-89.
[7] ZHAO M, LU H, CHENG S, et al. A multi-robot cooperative exploration algorithm considering working efficiency and working load[J]. Applied Soft Computing, 2022, 128: 109482.
[8] GARG V, SHUKLA A, TIWARI R. AERPSO - an adaptive exploration robotic PSO based cooperative algorithm for multiple target searching[J]. Expert Systems with Applications, 2022, 209: 118245.
[9] 包海默, 胡晓惠, 宋梅萍, 等. 尾鳍驱动型水下机器人发展综述[J]. 包装工程, 2023, 44(18): 128-146.
[10] 吴靖宇, 朱世强, 宋伟, 等. 基于改进单元分解法的全覆盖路径规划[J]. 系统工程与电子技术, 2023, 45(12): 3949-3957.
[11] 董雅文, 杨静雯, 刘文慧, 等. 基于改进A*算法的机器人全覆盖衔接路径规划[J]. 传感器与微系统, 2023, 42(9): 125-128.
[12] JERNE N K. The Immune System[J]. Scientific American, 1973, 229(1): 52-63.
[13] 蒋亚平, 张安康, 黎星. 人工免疫系统的研究进展与展望[J]. 信息安全与通信保密, 2021(2): 83-92.
[14] FARMER J D, Parked N H, PERELSON A S. The immue system, adaptation, and machine learning[J]. Physica D, 1986, 22(1-3): 187-204.
[15] 陈一鸣, 申燚, 黄艇, 等. 基于生物熵的免疫协作探测算法[J]. 信息技术, 2019, 43(12): 1-5.
[16] ZHOU Z W, LUO D L, SHAO J, et al. Immune genetic algorithm based Multi-UAV cooperative target search with event-triggered mechanism[J]. Physical Communication, 2020, 41: 101103.
