Route Optimization via Environment-Aware Deep Network and Reinforcement Learning

被引:11
|
作者
Guo, Pengzhan [1 ]
Xiao, Keli [1 ]
Ye, Zeyang [2 ]
Zhu, Wei [1 ]
机构
[1] SUNY Stony Brook, 100 Nicolls Rd, Stony Brook, NY 11794 USA
[2] Samsung Res Amer, 665 Clyde Ave, Mountain View, CA 94043 USA
关键词
Route recommendation; route optimization; deep learning; reinforcement learning; COVID-19; TAXI; PREDICTION;
D O I
10.1145/3461645
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Vehicle mobility optimization in urban areas is a long-standing problem in smart city and spatial data analysis. Given the complex urban scenario and unpredictable social events, our work focuses on developing a mobile sequential recommendation system to maximize the profitability of vehicle service providers (e.g., taxi drivers). In particular, we treat the dynamic route optimization problem as a long-term sequential decision-making task. A reinforcement-learning framework is proposed to tackle this problem, by integrating a self-check mechanism and a deep neural network for customer pick-up point monitoring. To account for unexpected situations (e.g., the COVID-19 outbreak), our method is designed to be capable of handling related environment changes with a self-adaptive parameter determination mechanism. Based on the yellow taxi data in New York City and vicinity before and after the COVID-19 outbreak, we have conducted comprehensive experiments to evaluate the effectiveness of our method. The results show consistently excellent performance, from hourly to weekly measures, to support the superiority of our method over the state-of-the-art methods (i.e., with more than 98% improvement in terms of the profitability for taxi drivers).
引用
收藏
页数:21
相关论文
共 50 条
  • [1] Playing FPS Games With Environment-Aware Hierarchical Reinforcement Learning
    Song, Shihong
    Weng, Jiayi
    Su, Hang
    Yan, Dong
    Zou, Haosheng
    Zhu, Jun
    [J]. PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3475 - 3482
  • [2] Environment-aware Sensor Fusion using Deep Learning
    Silva, Caio Fischer
    Borges, Paulo V. K.
    Castanho, Jose E. C.
    [J]. ICINCO: PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, VOL 2, 2019, : 88 - 96
  • [3] Network Topology Optimization via Deep Reinforcement Learning
    Li, Zhuoran
    Wang, Xing
    Pan, Ling
    Zhu, Lin
    Wang, Zhendong
    Feng, Junlan
    Deng, Chao
    Huang, Longbo
    [J]. IEEE TRANSACTIONS ON COMMUNICATIONS, 2023, 71 (05) : 2847 - 2859
  • [4] Environment-Aware Reinforcement Learning Based VANET Communications Against Jamming and Interference
    Lin, Zhiping
    Yan, Xiaohao
    Xiao, Liang
    Yan, Shi
    Tang, Yuliang
    Liu, Jun
    [J]. 2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 5717 - 5722
  • [5] NetRL: Task-Aware Network Denoising via Deep Reinforcement Learning
    Xu, Jiarong
    Yang, Yang
    Pu, Shiliang
    Fu, Yao
    Feng, Jun
    Jiang, Weihao
    Lu, Jiangang
    Wang, Chunping
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (01) : 810 - 823
  • [6] Route optimization of construction machine by deep reinforcement learning
    Tanabe, Shunya
    Sun, Zeyuan
    Nakatani, Masayuki
    Uchimura, Yutaka
    [J]. IEEJ Transactions on Industry Applications, 2019, 139 (04): : 401 - 408
  • [7] Haisor: Human-aware Indoor Scene Optimization via Deep Reinforcement Learning
    Sun, Jia-Mu
    Yang, Jie
    Mo, Kaichun
    Lai, Yu-Kun
    Guibas, Leonidas
    Gao, Lin
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2024, 43 (02):
  • [8] An Isolation-aware Online Virtual Network Embedding via Deep Reinforcement Learning
    Gohar, Ali
    Rong, Chunming
    Lee, Sanghwan
    [J]. 2023 IEEE/ACM 23RD INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND INTERNET COMPUTING WORKSHOPS, CCGRIDW, 2023, : 89 - 95
  • [9] Environment-Aware Adaptive Reinforcement Learning-Based Routing for Vehicular Ad Hoc Networks
    Jiang, Yi
    Zhu, Jinlin
    Yang, Kexin
    Marin, Sergio Toral
    [J]. SENSORS, 2024, 24 (01)
  • [10] Synthesizing Environment-Aware Activities via Activity Sketches
    Liao, Yuan-Hong
    Puig, Xavier
    Boben, Marko
    Torralba, Antonio
    Fidler, Sanja
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 6284 - 6292