Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Driving Decision and Control for Autonomous Lane Change based on Deep Reinforcement Learning #34

Open
DeepTecher opened this issue Apr 25, 2019 · 0 comments

Comments

@DeepTecher
Copy link
Owner

Driving Decision and Control for Autonomous Lane Change based on Deep Reinforcement Learning

提交日期: 2019-04-23
研究机构:北理工、加州大学
作者:Tianyu Shi, Pin Wang, Xuxin Cheng, Ching-Yao Chan
摘要:为了实现高级自动化,自动驾驶汽车需要学习在复杂情况下做出决策并控制其运动。由于状态空间的不确定性和复杂性,大多数经典的基于规则的方法无法解决复杂决策任务的问题。深度强化学习在游戏和机器人等许多领域都取得了巨大成就。然而,强化学习算法的直接应用仍然面临着处理复杂自动驾驶任务的挑战。在本文中,我们提出了一种基于深层次强化学习的体系结构,用于决策和控制车道变换情况。我们将决策和控制过程分为两个相关的过程:1)何时进行变道操纵2)如何进行机动。具体而言,我们应用深度Q网络(DQN),在决定是否进行机动的任务中考虑安全性。此外,我们设计了两个类似的Deep Q学习框架,其中使用二次逼近器来决定如何选择舒适的间隙并且只需跟随前面的车辆。最后,生成多项式车道变换轨迹,并且实现用于路径跟踪的纯跟踪控制。我们从决策层和控制层证明了该框架在仿真中的有效性。所提出的架构还有可能扩展到其他自动驾驶场景。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant