arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2104.13617cs.ROcs.AIcs.LG
收藏

基于多Agent深度强化学习的端到端交叉口处理

End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning

University of Parma(帕尔马大学);University of Bologna(博洛尼亚大学);VisLab srl, an Ambarella Inc. company(VisLab 公司,安霸公司旗下企业)

Alessandro Paolo Capasso, Paolo Maramotti, Anthony Dell'Eva, Alberto Broggi

摘要:

通过交叉路口导航是自动驾驶汽车的主要挑战性任务之一。然而,对于大多数由交通信号灯控制的交叉口,可以通过一种简单的基于规则的方法来解决这个问题,在该方法中,自主车辆的行为与交通信号灯状态密切相关。在这项工作中,我们专注于实现一个系统,能够通过十字路口,只有交通标志提供导航。我们提出了一个多智能体系统,该系统使用连续的无模型深度强化学习算法来训练神经网络,以预测每个时间步长的加速度和转向角。我们证明,代理学习的基本规则需要处理的交叉点,通过了解环境中的其他学习者的优先级,并沿着他们的路径安全驾驶。此外,我们的系统和基于规则的方法之间的比较证明,我们的模型取得了更好的效果,特别是在密集的交通条件。最后,我们使用真实记录的交通数据在现实世界的场景中测试我们的系统,证明我们的模块能够推广到看不见的环境和不同的交通条件。

英文摘要:

Navigating through intersections is one of the main challenging tasks for an autonomous vehicle. However, for the majority of intersections regulated by traffic lights, the problem could be solved by a simple rule-based method in which the autonomous vehicle behavior is closely related to the traffic light states. In this work, we focus on the implementation of a system able to navigate through intersections where only traffic signs are provided. We propose a multi-agent system using a continuous, model-free Deep Reinforcement Learning algorithm used to train a neural network for predicting both the acceleration and the steering angle at each time step. We demonstrate that agents learn both the basic rules needed to handle intersections by understanding the priorities of other learners inside the environment, and to drive safely along their paths. Moreover, a comparison between our system and a rule-based method proves that our model achieves better results especially with dense traffic conditions. Finally, we test our system on real world scenarios using real recorded traffic data, proving that our module is able to generalize both to unseen environments and to different traffic conditions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑