Li Tao, Zhang Chunze, Zhang Guibin, Zhou Qin, Hou Ji, Diao Wei, Meng Wanwan, Zhang Xujin
Southwest Research Institute for Hydraulic and Water Transport Engineering, Chongqing Jiaotong University, Chongqing, People's Republic of China.
The College of River and Ocean Engineering, Chongqing Jiaotong University, Chongqing, People's Republic of China.
Bioinspir Biomim. 2025 Jan 16;20(2). doi: 10.1088/1748-3190/ada59c.
The study of fish swimming behaviours and locomotion mechanisms holds significant scientific and engineering value. With the rapid advancements in artificial intelligence, a new method combining deep reinforcement learning (DRL) with computational fluid dynamics has emerged and been applied to simulate the fish's adaptive swimming behaviour, where the complex fish behaviour is decoupled to focus on the fish's response to the hydrodynamic field, and the simulation is driven by reward-based objectives to model the fish's swimming behaviour. However, the scale of this cross-disciplinary method is directly affected by the efficiency of the DRL model. To promote it to more general application scenarios, there is a pressing need for further research on more efficient and economical network architectures to address the challenge of approximating state-value function in high-dimensional, dynamic, and uncertain environments. Building upon a previously proposed computational platform for the simulation of fish autonomous swimming behaviour, we integrated Kolmogorov-Arnold Networks(KANs) and tested their performance in point-to-point swimming and Kármán gait swimming environments. Experimental results demonstrated that, compared to long short-term memory Networks(LSTMs) and multilayer perceptron networks(MLPs), the introduction of KANs significantly enhanced the perception and decision-making abilities of the intelligent fish in complex fluid environments. With a smaller network scale, in the point-to-point swimming case, KANs effectively approximated the state-value function, achieving average reward improvements of up to 88.0% and 94.1% over MLPs and LSTMs networks, respectively, and increased by 766.7% and 105.6% in the Kármán gait swimming case. Under comparable network sizes, the intelligent fish with KANs exhibited faster learning capabilities and more stable swimming performance in complex fluid settings.
鱼类游泳行为和运动机制的研究具有重要的科学和工程价值。随着人工智能的快速发展，一种将深度强化学习（DRL）与计算流体动力学相结合的新方法应运而生，并被应用于模拟鱼类的自适应游泳行为，其中复杂的鱼类行为被解耦，以专注于鱼类对流体动力场的响应，并且模拟由基于奖励的目标驱动，以对鱼类的游泳行为进行建模。然而，这种跨学科方法的规模直接受到DRL模型效率的影响。为了将其推广到更广泛的应用场景，迫切需要对更高效、更经济的网络架构进行进一步研究，以应对在高维、动态和不确定环境中逼近状态值函数的挑战。基于先前提出的用于模拟鱼类自主游泳行为的计算平台，我们集成了柯尔莫哥洛夫 - 阿诺德网络（KANs），并在点对点游泳和卡门步态游泳环境中测试了它们的性能。实验结果表明，与长短期记忆网络（LSTMs）和多层感知器网络（MLPs）相比，引入KANs显著增强了智能鱼在复杂流体环境中的感知和决策能力。在较小的网络规模下，在点对点游泳情况下，KANs有效地逼近了状态值函数，分别比MLPs和LSTMs网络实现了高达88.0%和94.1%的平均奖励提升，在卡门步态游泳情况下分别提升了766.7%和105.6%。在可比的网络规模下，具有KANs的智能鱼在复杂流体环境中表现出更快的学习能力和更稳定的游泳性能。
