Interaction-Aware Decision-Making for Automated Vehicles Using Social Value Orientation
Interaction-Aware Decision-Making for Automated Vehicles Using Social Value Orientation
复制标题
DOI：
10.1109/tiv.2022.3189836
复制
发表时间：
2023-02-01
影响因子：
8.2
通讯作者：
Wei, Chongfeng
中科院分区：
文献类型：
--
作者：
Crosato, Luca;Shum, Hubert P. H.;Wei, Chongfeng
有行人时的运动控制算法对于开发安全可靠的自动驾驶车辆 (AV) 至关重要。传统的运动控制算法依赖于手动设计的决策策略，忽略了自动驾驶汽车和行人之间的相互交互。另一方面，深度强化学习的最新进展允许自动学习策略，而无需手动设计。为了解决有行人存在的决策问题，作者引入了一种基于社会价值取向和深度强化学习（DRL）的框架，该框架能够生成不同驾驶风格的决策政策。该策略是在模拟环境中使用最先进的 DRL 算法进行训练的。还介绍了一种适合 DRL 训练的新型计算高效行人模型。我们进行实验来验证我们的框架，并对两种不同的无模型深度强化学习算法获得的策略进行比较分析。模拟结果显示了所开发的模型如何表现出自然的驾驶行为，例如短暂停车，以方便行人过马路。
Motion control algorithms in the presence of pedestrians are critical for the development of safe and reliable Autonomous Vehicles (AVs). Traditional motion control algorithms rely on manually designed decision-making policies which neglect the mutual interactions between AVs and pedestrians. On the other hand, recent advances in Deep Reinforcement Learning allow for the automatic learning of policies without manual designs. To tackle the problem of decision-making in the presence of pedestrians, the authors introduce a framework based on Social Value Orientation and Deep Reinforcement Learning (DRL) that is capable of generating decision-making policies with different driving styles. The policy is trained using state-of-the-art DRL algorithms in a simulated environment. A novel computationally-efficient pedestrian model that is suitable for DRL training is also introduced. We perform experiments to validate our framework and we conduct a comparative analysis of the policies obtained with two different model-free Deep Reinforcement Learning Algorithms. Simulations results show how the developed model exhibits natural driving behaviours, such as short-stopping, to facilitate the pedestrian's crossing.