路径优化问题是智能运输领域中的核心问题，合理的路径能有效提高运输效率，节约时间成本。基于对连续型和离散型的Hopfield神经网络特点进行分析，设计了一种基于连续型的Hopfield神经网络的路径规划方法，用于无人机路线规划。首先对神经网络的结构进行了说明，其次引入能量函数，用于定义神经网络的稳定性。再将目标函数映射为能量函数，将问题的变量对应到神经元的状态，那么当能量函数趋于最小值时，目标函数的最优解便随即得出。最后对案例进行仿真实验，得出最优解，验证了该方法的有效性和实用性。
Path optimization is the core problem in the field of intelligent transportation. A reasonable path can effectively improve transportation efficiency and save time and cost. Based on the analysis of the characteristics of continuous Hopfield neural network and discrete Hopfield neural network, a path planning method based on continuous Hopfield neural network is designed for UAV route planning. Firstly, the structure of neural network is explained. Secondly, the energy function is introduced to define the stability of neural network. And then map the objective function to the energy function, and correspond the variable of the problem to the state of the neuron. When the value of the energy function tends to the minimum, the optimal solution of the objective function is obtained immediately. Finally, the optimal solution is obtained through the simulation of an example, the results show that the proposed method is effective and practical.
