基于强化学习的无人驾驶匝道汇入模型
Autonomous Driving Ramp Merging Model Based on Reinforcement Learning
查看参考文献16篇
文摘
|
传统的强化学习方法受离散状态空间和离散动作空间的限制,不能很好地应用于匝道汇入场景。为此,构建一种基于强化学习的无人驾驶匝道汇入模型。使用深度Q网络构建强化学习模型,依据该模型将匝道汇入问题纳入强化学习问题的范畴后进行求解。实验结果表明,该模型可以针对不同的环境车辆速度采取不同的策略,从而提高无人驾驶在匝道汇入场景下的智能化决策水平。 |
其他语种文摘
|
The traditional reinforcement learning method is limited by discrete state space and discrete action space, and can not be applied to ramp merging scene. Therefore,a reinforcement learning based autonomous driving ramp merging model is constructed. The reinforcement learning model is built by deep Q network. The ramp merging problem is incorporated into the category of reinforcement learning problem and solved. Experimental results show that the model can adopt different strategies for different environment vehicle speeds,thus improving the intelligent decision-making level of the autonomous driving in ramp merging scene. |
来源
|
计算机工程
,2018,44(7):20-24,31 【扩展库】
|
DOI
|
10.19678/j.issn.1000-3428.0050990
|
关键词
|
无人驾驶
;
决策
;
匝道汇入
;
强化学习
;
深度Q网络
|
地址
|
1.
北京联合大学, 北京市信息服务工程重点实验室, 北京, 100101
2.
北京联合大学机器人学院, 北京, 100101
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1000-3428 |
学科
|
自动化技术、计算机技术 |
基金
|
国家自然科学基金“视听觉信息的认知计算
;
北京市教委科研基金
;
英国皇家工程院牛顿基金
;
北京市属高校高水平教师队伍建设支持计划项目
|
文献收藏号
|
CSCD:6285662
|
参考文献 共
16
共1页
|
1.
Urmson C. Autonomous driving in urban environments: boss and the urban challenge.
Journal of Field Robotics,2008,25(8):425-466
|
CSCD被引
71
次
|
|
|
|
2.
Dong C. Intention estimation for ramp merging control in autonomous driving.
Proceedings of 2017 IEEE Intelligent Vehicles Symposium,2017:1584-1589
|
CSCD被引
1
次
|
|
|
|
3.
Hafner M R. Cooperative collision avoidance at intersections: algorithms and experiments.
IEEE Transactions on Intelligent Transportation Systems,2013,14(3):1162-1175
|
CSCD被引
9
次
|
|
|
|
4.
Alonso J. Autonomous vehicle control systems for safe crossroads.
Transportation Research,Part C: Emerging Technologies,2011,19(6):1095-1110
|
CSCD被引
7
次
|
|
|
|
5.
Marinescu D. Onramp traffic merging using cooperative intelligent vehicles: a slot-based approach.
Proceedings of the15th IEEE International Conference on Intelligent Transportation Systems,2012:900-906
|
CSCD被引
1
次
|
|
|
|
6.
Wei J. Autonomous vehicle social behavior for highway entrance ramp management.
Proceedings of 2013 IEEE Intelligent Vehicles Symposium,2013:201-207
|
CSCD被引
1
次
|
|
|
|
7.
罗霞. 车联网环境下交叉口车辆路径优化控制研究.
计算机仿真,2017,34(4):166-171
|
CSCD被引
2
次
|
|
|
|
8.
Horst R V D.
Time-to-collision and collision avoidance systems,2018
|
CSCD被引
1
次
|
|
|
|
9.
Cosgun A. Towards full automated drive in urban environments: a demonstration in gomentum station,California.
Proceedings of2017 IEEE Intelligent Vehicles Symposium,2017:1120-1128
|
CSCD被引
1
次
|
|
|
|
10.
Isele D.
Navigating intersections with autonomous vehicles using deep reinforcement learning,2018
|
CSCD被引
1
次
|
|
|
|
11.
Littman M L. Reinforcement learning improves beha-viour from evaluative feedback.
Nature,2015,521(7553):445-451
|
CSCD被引
20
次
|
|
|
|
12.
赵冬斌. 深度强化学习综述:兼论计算机围棋的发展.
控制理论与应用,2016,33(6):701-717
|
CSCD被引
66
次
|
|
|
|
13.
Silver D. Mastering the game of go with deep neural networks and tree search.
Nature,2016,529(7587):484-489
|
CSCD被引
760
次
|
|
|
|
14.
Silver D. Mastering the game of go without human knowledge.
Nature,2017,550(7676):354-359
|
CSCD被引
429
次
|
|
|
|
15.
Mnih V.
Playing atari with deep reinforcement learning,2018
|
CSCD被引
7
次
|
|
|
|
16.
刘全. 深度强化学习综述.
计算机学报,2018,41(1):1-27
|
CSCD被引
193
次
|
|
|
|
|