现实工业生产应用中存在大量的混合变量优化问题,这类问题的决策变量既包含连续变量,又包含离散变量。由于决策变量为混合类型,导致问题的决策空间变得不规则,采用已有的方法很难进行有效求解。引入协同进化策略,提出一种基于竞争式协...现实工业生产应用中存在大量的混合变量优化问题,这类问题的决策变量既包含连续变量,又包含离散变量。由于决策变量为混合类型,导致问题的决策空间变得不规则,采用已有的方法很难进行有效求解。引入协同进化策略,提出一种基于竞争式协同进化的混合变量粒子群优化算法(competitive coevolution based PSO,CCPSO)。设计基于容忍度的搜索方向调整机制来判断粒子的进化状态,从而自适应地调整粒子的搜索方向,避免陷入局部最优,平衡了种群的收敛性和多样性;引入基于竞争式协同进化的学习对象生成机制,在检测到粒子进化停滞时为每个粒子生成新的学习对象,从而推动粒子的进一步搜索,提高了种群的多样性;采用基于竞争学习的预测策略为粒子选择合适的学习对象,充分利用了新旧学习对象的学习潜力,保证了算法的收敛速度。实验结果表明:相比其他主流的混合变量优化算法,CCPSO可以获得更优的结果。展开更多
论文研究核心目标是评估改进动态多种群粒子群算法(DMPG)在无人机路径规划中的应用效果,特别是在动态环境下的性能表现。该算法通过引入动态权重调整机制和多种群策略,旨在增强算法在动态环境下的适应性和优化性能。此外,本文还结合了...论文研究核心目标是评估改进动态多种群粒子群算法(DMPG)在无人机路径规划中的应用效果,特别是在动态环境下的性能表现。该算法通过引入动态权重调整机制和多种群策略,旨在增强算法在动态环境下的适应性和优化性能。此外,本文还结合了深度强化学习(DRL)技术,以提高无人机在复杂环境中的自主决策能力。通过构建详细的仿真环境,我们对DMPG算法进行了全面的性能评估,包括其避障能力、路径规划的效率以及对动态变化的响应速度。仿真结果显示,DMPG算法在动态环境中表现出色,不仅能够有效规避障碍物,而且在路径规划的全局性和鲁棒性方面均取得了显著提升。与现有的静态和动态路径规划算法进行比较,DMPG算法在平均路径长度、避障成功率以及任务完成时间等关键性能指标上均展现出了卓越的性能。这些发现为无人机路径规划的研究提供了新的见解,并为未来相关领域的研究和应用提供了有价值的参考。The core objective of this paper is to evaluate the application effect of improved Dynamic Multi Swarm Particle Swarm Optimization (DMPG) algorithm in UAV path planning, especially its performance in dynamic environments. This algorithm aims to enhance its adaptability and optimization performance in dynamic environments by introducing dynamic weight adjustment mechanisms and various swarm strategies. In addition, this article also combines deep reinforcement learning (DRL) technology to improve the autonomous decision-making ability of drones in complex environments. By constructing a detailed simulation environment, we conducted a comprehensive performance evaluation of the DMPG algorithm, including its obstacle avoidance ability, path planning efficiency, and response speed to dynamic changes. The simulation results show that the DMPG algorithm performs well in dynamic environments, not only effectively avoiding obstacles, but also achieving significant improvements in the global and robust aspects of path planning. Compared with existing static and dynamic path planning algorithms, the DMPG algorithm has demonstrated excellent performance in key performance indicators such as average path length, obstacle avoidance success rate, and task completion time. These findings provide new insights for the study of drone path planning and valuable references for future research and applications in related fields.展开更多
文摘现实工业生产应用中存在大量的混合变量优化问题,这类问题的决策变量既包含连续变量,又包含离散变量。由于决策变量为混合类型,导致问题的决策空间变得不规则,采用已有的方法很难进行有效求解。引入协同进化策略,提出一种基于竞争式协同进化的混合变量粒子群优化算法(competitive coevolution based PSO,CCPSO)。设计基于容忍度的搜索方向调整机制来判断粒子的进化状态,从而自适应地调整粒子的搜索方向,避免陷入局部最优,平衡了种群的收敛性和多样性;引入基于竞争式协同进化的学习对象生成机制,在检测到粒子进化停滞时为每个粒子生成新的学习对象,从而推动粒子的进一步搜索,提高了种群的多样性;采用基于竞争学习的预测策略为粒子选择合适的学习对象,充分利用了新旧学习对象的学习潜力,保证了算法的收敛速度。实验结果表明:相比其他主流的混合变量优化算法,CCPSO可以获得更优的结果。
文摘论文研究核心目标是评估改进动态多种群粒子群算法(DMPG)在无人机路径规划中的应用效果,特别是在动态环境下的性能表现。该算法通过引入动态权重调整机制和多种群策略,旨在增强算法在动态环境下的适应性和优化性能。此外,本文还结合了深度强化学习(DRL)技术,以提高无人机在复杂环境中的自主决策能力。通过构建详细的仿真环境,我们对DMPG算法进行了全面的性能评估,包括其避障能力、路径规划的效率以及对动态变化的响应速度。仿真结果显示,DMPG算法在动态环境中表现出色,不仅能够有效规避障碍物,而且在路径规划的全局性和鲁棒性方面均取得了显著提升。与现有的静态和动态路径规划算法进行比较,DMPG算法在平均路径长度、避障成功率以及任务完成时间等关键性能指标上均展现出了卓越的性能。这些发现为无人机路径规划的研究提供了新的见解,并为未来相关领域的研究和应用提供了有价值的参考。The core objective of this paper is to evaluate the application effect of improved Dynamic Multi Swarm Particle Swarm Optimization (DMPG) algorithm in UAV path planning, especially its performance in dynamic environments. This algorithm aims to enhance its adaptability and optimization performance in dynamic environments by introducing dynamic weight adjustment mechanisms and various swarm strategies. In addition, this article also combines deep reinforcement learning (DRL) technology to improve the autonomous decision-making ability of drones in complex environments. By constructing a detailed simulation environment, we conducted a comprehensive performance evaluation of the DMPG algorithm, including its obstacle avoidance ability, path planning efficiency, and response speed to dynamic changes. The simulation results show that the DMPG algorithm performs well in dynamic environments, not only effectively avoiding obstacles, but also achieving significant improvements in the global and robust aspects of path planning. Compared with existing static and dynamic path planning algorithms, the DMPG algorithm has demonstrated excellent performance in key performance indicators such as average path length, obstacle avoidance success rate, and task completion time. These findings provide new insights for the study of drone path planning and valuable references for future research and applications in related fields.
