期刊文献+

基于改进SARSA算法的航空器滑行路径规划

Aircraft Glide Path Planning Based on Improved SARSA Algorithm
下载PDF
导出
摘要 航空器滑行是机场运行中最重要的一环,缩短滑行时间也是提高机场运行效率的主要手段。为了改变仅依靠人工进行机坪管制的现状,文章针对航空器滑行的特殊环境,利用改进SARSA算法对航空器的滑行路径进行规划,并通过仿真验证了该算法在规划路径长度和迭代次数方面优于传统SARSA算法,进而更好地为管制员决策提供辅助参考。 Aircraft taxiing is the most important part of airport operation,and shortening taxiing time is also the main key to improve airport operation efficiency.In order to realize the efficient operation of the airport and change the current situation of relying only on manual apron control,this paper,aiming at the special environment of aircraft taxiing,uses the improved SARSA algorithm to plan the aircraft′s taxiing path,and verifies through simulation that the algorithm is superior to the traditional SARSA algorithm in terms of planning path length and iteration times,which can provide better decision-making assistance and reference for controllers.Efficiently plan shorter paths.
作者 张云景 王昊 王帅 孟斌 ZHANG Yunjing;WANG Hao;WANG Shuai;MENG Bin(School of Civil Aviation,Zhengzhou University of Aeronautics,Zhengzhou 450046,China;Hohai University,Nanjing 211100,China)
出处 《郑州航空工业管理学院学报》 2024年第1期43-48,共6页 Journal of Zhengzhou University of Aeronautics
基金 河南省科技攻关项目(212102210141,232102240101) 河南省科技智库项目(HNKJZK-2024-50B)。
关键词 强化学习 路径规划 模拟退火策略 SARSA算法 reinforcement learning path planning simulated annealing strategy SARSA algorithm
  • 相关文献

参考文献8

二级参考文献42

  • 1李宪强,马戎,张伸,侯砚泽,裴毅飞.蚁群算法的改进设计及在航迹规划中的应用[J].航空学报,2020(S02):213-219. 被引量:33
  • 2黄炳强,曹广益.基于人工势场法的移动机器人路径规划研究[J].计算机工程与应用,2006,42(27):26-28. 被引量:38
  • 3周躜,王腾飞,戴光明.机器人路径规划中的双向Dijkstra二叉树算法[J].计算机工程,2007,33(10):36-37. 被引量:5
  • 4HAYKIN S. Cognitive radio: brain-empowered wireless communications[J]. IEEE Journal on Selected Areas in Communications, 2005,23 (2) : 201-220.
  • 5KAELBLING L P, LITTMAN M L, MOORE A W. Reinforcement learning: a survey[J].Journal of Artificial Intelligence Research, 1996 (4) :237-285.
  • 6NIE J, HAYKIN S. A Q-learning-based dynamic channel assignment technique for mobile communication systems[J]. IEEE Trans on Vehicular Technology, 1999, 48: 1676-1687.
  • 7WATKINS C J C H. Learning from delayed rewards[D]. Cambridge: Cambridge University, 1989.
  • 8WATKINS C J C H, DAYAN P. Q-learning[J]. Machine Learning, 1992,8:279-292.
  • 9NGAI D C K, YUNG N H C. Double action Q-learning for obstacle avoidance in a dynamically changing environment[C]. Las Vegas: Proceedings of the 2005 IEEE Intelligent Vehicles Symposium, 2005.
  • 10NGAI D C K, YUNG N H C. Performance evaluation of double action Q-Learning in moving obstacle avoidance problem[C]. Hawaii:Proceedings of the 2005 IEEE International Conference on Systems, Man, and Cybernetics, 2005.

共引文献26

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部