The logistics demands of industries represented by e-commerce have experienced explosive growth in recent years. Vehicle path-planning plays a crucial role in optimization systems for logistics and distribution. A path-planning scheme suitable for an actual scenario is the key to reducing costs and improving service efficiency in logistics industries. In complex application scenarios, however, it is difficult for conventional heuristic algorithms to ensure the quality of solutions for vehicle routing problems. This study proposes a joint approach based on the genetic algorithm and graph convolutional network for solving the capacitated vehicle routing problem with multiple distribution centers. First, we use the heuristic method to modularize the complex environment and encode each module based on the constraint conditions. Next, the graph convolutional network is adopted for feature embedding for the graph representation of the vehicle routing problem, and multiple decoders are used to increase the diversity of the solution space. Meanwhile, the REINFORCE algorithm with a baseline is employed to train the model, ensuring quick returns of high-quality solutions. Moreover, the fitness function is calculated based on the solution to each module, and the genetic algorithm is employed to seek the optimal solution on a global scale. Finally, the effectiveness of the proposed framework is validated through experiments at different scales and comparisons with other algorithms. The experimental results show that, compared to the single decoder GCN-based solving method, the method proposed in this paper improves the solving success rate to 100% across 15 generated instances. The average path length obtained is only 11% of the optimal solution produced by the GCN-based multi-decoder method.
For the pursuit-evasion game of an interceptor pursuing an incoming missile with strong maneuverability in the process of missile combat, a differential game model and its solving method were proposed. Firstly, a particle dynamics model of the missile pursuit-evasion system was given. Secondly, based on the differential game theory, a detailed differential game model of missile combat was established. Thirdly, aiming at the difficulty in analytical solution, an improved high-precision fifth-order Gauss-Labatto polynomial collocation method was proposed to approach the differential equation. Finally, the proposed method was verified numerically with an example.
In this paper, we introduce an agent rescue scheduling approach grounded in proximal policy optimization, coupled with a singularity-free predefined-time control strategy. The primary objective of this methodology is to bolster the efficiency and precision of rescue missions. Firstly, we have designed an evaluation function closely related to the average flying distance of agents, which provides a quantitative benchmark for assessing different scheduling schemes and assists in optimizing the allocation of rescue resources. Secondly, we have developed a scheduling strategy optimization method using the Proximal Policy Optimization (PPO) algorithm. This method can automatically learn and adjust scheduling strategies to adapt to complex rescue environments and varying task demands. The evaluation function provides crucial feedback signals for the PPO algorithm, ensuring that the algorithm can precisely adjust the scheduling strategies to achieve optimal results. Thirdly, aiming to attain stability and precision in agent navigation to designated positions, we formulate a singularity-free predefined-time fuzzy adaptive tracking control strategy. This approach dynamically modulates control parameters in reaction to external disturbances and uncertainties, thus ensuring the precise arrival of agents at their destinations within the predefined time. Finally, to substantiate the validity of our proposed approach, we crafted a simulation environment in Python 3.7, engaging in a comparative analysis between the PPO and the other optimization method, Deep Q-network (DQN), utilizing the variation in reward values as the benchmark for evaluation.