《计算机应用研究》|Application Research of Computers

基于出租车司机经验的约束深度强化学习算法路径挖掘

Mining fastest route using taxi drivers’ experience via constrained deep reinforcement learning

免费全文下载 (已被下载 次)  
获取PDF全文
作者 黄敏,毛锋,钱宇翔
机构 中山大学 智能工程学院 广东智能交通系统重点实验室,广州 510006
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)05-003-1298-05
DOI 10.19734/j.issn.1001-3695.2018.10.0810
摘要 利用出租车司机经验,提出约束深度强化学习算法(CDRL)在线计算不同时间段内OD间最快路线。首先描述了路段经验数据库(ERSD)的提取; 然后介绍了CDRL方法,包括可选择约束路段生成和深度Q-lear-ning算法两个阶段,在第一阶段,生成OD(起终点)间可选择约束路段,在第二阶段,设计深度Q-learning算法学习出租车司机的经验,并根据他们的出发时间计算给定OD间的最快路线;最后在广州CBD进行了应用实验。结果表明,CDRL方法计算在旅行时间上优于最短路径(SR)方法,且与最快路径(FR)方法计算路径差别不大;此外,CDRL方法在计算效率方面明显优于FR和SR方法,因此更适合OD间最快路径的在线计算。
关键词 最快路径挖掘; 路段经验数据库; 经验学习; 深度强化学习
基金项目 国家自然科学基金资助项目(U1611461,11574407)
广东省科技计划项目(2016A020223006)
中央高校基本科研业务费专项资金资助项目(17lgjc42)
本文URL http://www.arocmag.com/article/01-2020-05-003.html
英文标题 Mining fastest route using taxi drivers’ experience via constrained deep reinforcement learning
作者英文名 Huang Min, Mao Feng, Qian Yuxiang
机构英文名 Guangdong Provincial Key Laboratory of Intelligent Transportation System,School of Intelligent System Engineering,Sun Yat-sen University,Guangzhou 510006,China
英文摘要 This paper proposed constrained deep reinforcement learning(CDRL) to compute the fastest route online using taxi drivers' experience in different time period. Firstly, this paper described the extraction of experiential road segment database(ERSD). Then it introduced CDRL method, which mainly comprised of two phase: bounded condition of route and deep Q-learning algorithm. In the first phase, the task was to generate alternative constrained road segments of OD pair. In the se-cond phase, it devised deep Q-learning algorithm to learning the experience of taxi drivers, and computed the fastest route of a given OD according to their departure time. Lastly, this paper tested an empirical studies in CBD of Guangzhou. The results show that the routes computed by CDRL method is approximately equal to shortest route(SR) and fastest route(FR) method in travel time and route length. Furthermore, the CDRL method notably outperforms FR and SR in computing efficiency, so it is more suitable for online fastest route computation.
英文关键词 mining fastest route; experiential road segment database; experience learning; deep reinforcement learning
参考文献 查看稿件参考文献
 
收稿日期 2018/10/24
修回日期 2018/12/24
页码 1298-1302
中图分类号 TP301.6;U491
文献标志码 A