论文标题
使用深度加固学习的智能回旋处插入
Intelligent Roundabout Insertion using Deep Reinforcement Learning
论文作者
论文摘要
自动驾驶研究中的一个重要主题是操纵计划系统的开发。车辆必须相互互动和谈判，以便在时间和安全方面进行最佳选择。为此，我们提出了一个能够在繁忙的回旋处进行协商的机动计划模块。所提出的模块基于一个训练有素的神经网络，以预测整个操作的整个过程中何时以及如何进入回旋处。我们的模型经过新的A3C实施，我们将在合成环境中称为延迟的A3C（D-A3C），在该环境中，车辆以逼真的方式移动具有相互作用功能。此外，对系统进行了训练，以使代理具有独特的可调行为，并模仿驾驶员具有自己的驾驶风格的现实世界情景。同样，可以使用不同的侵略性水平进行操作，这对于管理繁忙的方案特别有用，在管理繁忙的情况下，基于规则的策略将导致不确定的等待。
An important topic in the autonomous driving research is the development of maneuver planning systems. Vehicles have to interact and negotiate with each other so that optimal choices, in terms of time and safety, are taken. For this purpose, we present a maneuver planning module able to negotiate the entering in busy roundabouts. The proposed module is based on a neural network trained to predict when and how entering the roundabout throughout the whole duration of the maneuver. Our model is trained with a novel implementation of A3C, which we will call Delayed A3C (D-A3C), in a synthetic environment where vehicles move in a realistic manner with interaction capabilities. In addition, the system is trained such that agents feature a unique tunable behavior, emulating real world scenarios where drivers have their own driving styles. Similarly, the maneuver can be performed using different aggressiveness levels, which is particularly useful to manage busy scenarios where conservative rule-based policies would result in undefined waits.
