Development of bus intelligent dispatching system based on reinforcement learning

被引:0
作者
Zou, L [1 ]
Xu, LM [1 ]
Zhu, LX [1 ]
机构
[1] S China Univ Technol, Coll Traff & Commun, Guangzhou 510640, Peoples R China
来源
ICEMI 2005: CONFERENCE PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ELECTRONIC MEASUREMENT & INSTRUMENTS, VOL 2 | 2005年
关键词
bus dispatching; reinforcement learning; intelligent transportation systems;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The Bus Intelligent Dispatching System (BIDS) is established according to the status of bus operating including vehicle location and number of passengers, making the best use of Reinforcement Learning (RL). The information about vehicle location can be got by Global Position System (GPS) receivers installed on buses. The infrared beams on buses can get the number of passengers on buses. We use a team of RL agents, each of which is responsible for controlling one route. Finally, the developed algorithm is implemented with ten bus routes of Guangzhou City. The results demonstrate the power of RL on bus dispatching problem.
引用
收藏
页码:372 / 376
页数:5
相关论文
共 6 条
[1]  
BEOM HB, 1995, IEEE T SMC, V25, P169
[2]  
CAIRONI PVC, 1997, INT J INTELL SYST, P659
[3]   Bus dispatching at timed transfer transit stations using bus tracking technology [J].
Dessouky, M ;
Hall, R ;
Nowroozi, A ;
Mourikas, K .
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 1999, 7 (04) :187-208
[4]   Optimal holding times at transfer stations [J].
Hall, R ;
Dessouky, M ;
Lu, Q .
COMPUTERS & INDUSTRIAL ENGINEERING, 2001, 40 (04) :379-397
[5]  
RUMMERY G, 1994, MACH LEARN, P279
[6]  
WATKINS CJCH, 1992, MACH LEARN, V8, P279, DOI 10.1007/BF00992698