首页> 外文期刊>Applied Ocean Research >3D path planning for underwater vehicles using five evolutionary optimization algorithms avoiding static and energetic obstacles
【24h】

3D path planning for underwater vehicles using five evolutionary optimization algorithms avoiding static and energetic obstacles

机译:使用五种进化优化算法避免水下和静态障碍的水下车辆3D路径规划

获取原文
获取原文并翻译 | 示例
           

摘要

In this paper, optimal paths in environments with obstacles for underwater vehicles are computed using a numerical solution of the nonlinear optimal control problem (NOCP). The underwater vehicle is modeled with six-dimensional nonlinear and coupled equations of motion, controlled by DC motors in all degrees of freedom. An energy performance index combined with a time consumption index is used. Both fixed and free final times are considered. Solving NOCP leads to a two point boundary value problem (TPBVP). Five intelligent evolutionary algorithms (EAs), which include genetic algorithm, memetic algorithm, particle swarm optimization, ant colony optimization and shuffled frog leaping algorithm, are applied to solve the NOCP. For comparison, a conjugate gradient penalty method is also used to solve the TPBVP. The simulation results show that the trajectories obtained by the intelligent methods are better than those of conjugate gradient method. After analyzing a simple path planning problem, the time-energy-optimal path planning problem in energetic environments is propounded and solved by EAs. The problem of static obstacle collision avoidance in an energetic environment is also studied.
机译:在本文中,使用非线性最优控制问题(NOCP)的数值解来计算水下航行器有障碍物的环境中的最优路径。水下航行器采用六维非线性和耦合运动方程建模,这些方程由直流电动机在所有自由度下控制。使用了能量性能指标和时间消耗指标。固定时间和自由时间都将被考虑。解决NOCP会导致两点边界值问题(TPBVP)。应用遗传算法,模因算法,粒子群算法,蚁群算法和蛙跳算法等五种智能进化算法求解NOCP。为了进行比较,还使用了共轭梯度罚分法来求解TPBVP。仿真结果表明,智能方法获得的轨迹要优于共轭梯度法。在分析了一个简单的路径规划问题之后,通过EA提出并解决了高能环境中的时间能量最优路径规划问题。还研究了在高能环境中避免静态障碍物碰撞的问题。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号