Learning hierarchical behavior and motion planning for autonomous driving

被引:16
|
作者
Wang, Jingke [1 ]
Wang, Yue [1 ]
Zhang, Dongkun [1 ]
Yang, Yezhou [2 ]
Xiong, Rong [1 ]
机构
[1] Zhejiang Univ, State Key Lab Ind Control & Technol, Hangzhou, Peoples R China
[2] Arizona State Univ, Sch Comp Informat & Decis Syst Engn, Tempe, AZ 85287 USA
基金
国家重点研发计划;
关键词
D O I
10.1109/IROS45743.2020.9341647
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Learning-based driving solution, a new branch for autonomous driving, is expected to simplify the modeling of driving by learning the underlying mechanisms from data. To improve the tactical decision-making for learning-based driving solution, we introduce hierarchical behavior and motion planning (HBMP) to explicitly model the behavior in learning-based solution. Due to the coupled action space of behavior and motion, it is challenging to solve HBMP problem using reinforcement learning (RL) for long-horizon driving tasks. We transform HBMP problem by integrating a classical sampling-based motion planner, of which the optimal cost is regarded as the rewards for high-level behavior learning. As a result, this formulation reduces action space and diversifies the rewards without losing the optimality of HBMP. In addition, we propose a sharable representation for input sensory data across simulation platforms and real-world environment, so that models trained in a fast event-based simulator, SUMO, can be used to initialize and accelerate the RL training in a dynamics based simulator, CARLA. Experimental results demonstrate the effectiveness of the method. Besides, the model is successfully transferred to the real-world, validating the generalization capability.
引用
收藏
页码:2235 / 2242
页数:8
相关论文
共 50 条
  • [31] MOTION PLANNING FOR AUTONOMOUS DRIVING WITH EXTENDED CONSTRAINED ITERATIVE LQR
    Shimizu, Yutaka
    Zhan, Wei
    Sun, Liting
    Chen, Jianyu
    Kato, Shinpei
    Tomizuka, Masayoshi
    [J]. PROCEEDINGS OF THE ASME DYNAMIC SYSTEMS AND CONTROL CONFERENCE, DSCC2020, VOL 1, 2020,
  • [32] Motion Planning Using Feasible and Smooth Tree for Autonomous Driving
    Chen, Weihuang
    Chen, Yuwei
    Wang, Shen'ao
    Kong, Fanjie
    Zhang, Xuchong
    Sun, Hongbin
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2024, 73 (05) : 6270 - 6282
  • [33] A Dynamic Motion Planning Framework for Autonomous Driving in Urban Environments
    Jiang, Yuncheng
    Jin, Xiaofeng
    Xiong, Yanfei
    Liu, Zhaoyong
    [J]. PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE, 2020, : 5429 - 5435
  • [34] Motion Planning for Autonomous Driving with Real Traffic Data Validation
    Chu, Wenbo
    Yang, Kai
    Li, Shen
    Tang, Xiaolin
    [J]. CHINESE JOURNAL OF MECHANICAL ENGINEERING, 2024, 37 (01)
  • [35] AUTONOMOUS BUS DRIVING A Novel Motion-Planning Approach
    Oliveira, Rui
    Lima, Pedro F.
    Cirillo, Marcello
    Wahlberg, Bo
    [J]. IEEE VEHICULAR TECHNOLOGY MAGAZINE, 2021, 16 (03): : 29 - 37
  • [36] Cooperating Modular Goal Selection and Motion Planning for Autonomous Driving
    Ahn, Heejin
    Berntorp, Karl
    Di Cairano, Stefano
    [J]. 2020 59TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2020, : 3481 - 3486
  • [37] Motion Planning under Uncertainty for On-Road Autonomous Driving
    Xu, Wenda
    Pan, Jia
    Wei, Junqing
    Dolan, John M.
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2014, : 2507 - 2512
  • [38] Accurate Localization and Motion Planning for Autonomous Driving at Urban Intersections
    Bhattacharyya, Prarthana
    Gu, Yanlei
    Bao, Jiali
    Kamijo, Shunsuke
    [J]. PROCEEDINGS OF THE ION 2017 PACIFIC PNT MEETING, 2017, : 447 - 458
  • [39] Runtime-Bounded Tunable Motion Planning for Autonomous Driving
    Gu, Tianyu
    Dolan, John M.
    Lee, Jin-Woo
    [J]. 2016 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2016, : 1301 - 1306
  • [40] Hybrid Strategy of Motion Planning with Kinematic Optimization for Autonomous Driving
    Huang, Weiwei
    Wu, Ning
    Song, Zhiwei
    Wu, Xiaojun
    Zhang, Qun
    Yao, Susu
    [J]. 2015 IEEE 18TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015, : 1666 - 1671