水深点与等深线协同综合的强化学习方法
A reinforcement learning method for collaborative generalization of soundings and depth contours
宋子康 1贾帅东 2梁志诚 3张立华 2梁川4
作者信息
- 1. 海军大连舰艇学院军事海洋与测绘系,辽宁大连 116018;海图信息中心,天津 300450
- 2. 海军大连舰艇学院军事海洋与测绘系,辽宁大连 116018;海军大连舰艇学院海洋测绘工程军队重点实验室,辽宁大连 116018
- 3. 91001部队,北京 100036
- 4. 海军大连舰艇学院军事海洋与测绘系,辽宁大连 116018;91937部队,浙江舟山 316041
- 折叠
摘要
针对当前海图中水深点与等深线两要素的自动综合过程相对独立,二者相互影响考虑不够充分,导致结果不够理想的问题,提出一种水深点与等深线协同综合的强化学习方法.首先,获取用于水深点与等深线协同综合的训练样本;然后,构建并训练强化学习模型,挖掘水深点与等深线在综合过程中的相互影响关系;最后,利用训练后的模型,动态自适应调整水深点与等深线的综合策略.试验结果表明,在航海安全保证的可靠性、制图综合结果的图理性、海底地貌表达的准确性及海图要素分布的美观性等方面,强化学习法的性能均要优于当前常见的简单综合法、冲突避免法及协调水深法,更适用于处理水深点与等深线的协同综合问题.
Abstract
Nowadays,the existing methods of automatic cartographic generalization usually generalize soundings and depth con-tours separately,which easily leads to unsatisfactory generalization results.To address this problem,a reinforcement learning method for collaborative generalization of soundings and depth contours is proposed.Firstly,training samples for collaborative generalization are obtained.Simultaneously,a reinforcement learning model is constructed based on the cartographic con-straints and the related algorithms.Then,the constructed model is trained by using the sample data,so that the interaction be-tween soundings and depth contours can be explored in the generalization process.Finally,the generalization algorithms of soundings and depth contours can be adaptively adjusted by utilizing the trained model,so that the mutual influence relationship between soundings and depth contours can be fully considered in the generalization process.The experimental results show that:compared with current common methods,the proposed method can effectively improve the quality of the cartographic generalization results,and is more suitable for the collaborative generalization of soundings and depth contours.
关键词
海图制图/海底地貌综合/水深点自动选取/等深线自动化简/强化学习Key words
nautical cartography/submarine topographical generalization/automatic sounding selection/automatic depth con-tour simplification/reinforcement learning引用本文复制引用
基金项目
国家自然科学基金(41901320)
国家自然科学基金(41871369)
国家自然科学基金(42071439)
出版年
2024
NETL
NSTL
万方数据