Learning Control Policies of Driverless Vehicles from UAV Video Streams in Complex Urban Environments
Learning Control Policies of Driverless Vehicles from UAV Video Streams in Complex Urban Environments
复制标题
DOI：
10.3390/rs11232723
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Katie Inder;V. D. Silva;Xiyu Shi
中科院分区：
文献类型：
--
作者：
Katie Inder;V. D. Silva;Xiyu Shi
我们的驾驶方式和今天的交通正在经历根本性的变化。智能移动设想通过先进的数字技术，如机器人技术，人工智能和物联网，提高传统交通的效率。智能移动技术发展的核心是互联自动驾驶汽车（CAV）的出现，其中车辆能够自主地在环境中导航。为了实现这一目标，自动驾驶汽车必须安全，受到乘客和其他驾驶员的信任。然而，实际上不可能在它们可能遇到的所有可能的交通条件下训练自动驾驶车辆。本文的工作提出了一种使用基础设施来帮助CAV学习驾驶策略的替代解决方案，特别是对于复杂的路口，这需要当地的经验和知识来处理。该提案是通过利用从监控设备捕获的关于路口车辆运动的数据，在路口对人类驾驶的车辆进行数据驱动的模仿学习，来学习安全驾驶政策。所提出的框架是通过处理视频数据集捕获无人机（UAV）从欧洲各地的三个路口，其中包含车辆轨迹。提出了一种基于长短期记忆神经网络的模拟学习算法，用于车辆安全轨迹的学习和预测。所提出的框架可以用于智能移动性的许多目的，例如增强无人驾驶车辆中的智能控制算法，为保险目的对驾驶员行为进行基准测试，以及为城市规划提供见解。
The way we drive, and the transport of today are going through radical changes. Intelligent mobility envisions to improve the efficiency of traditional transportation through advanced digital technologies, such as robotics, artificial intelligence and Internet of Things. Central to the development of intelligent mobility technology is the emergence of connected autonomous vehicles (CAVs) where vehicles are capable of navigating environments autonomously. For this to be achieved, autonomous vehicles must be safe, trusted by passengers, and other drivers. However, it is practically impossible to train autonomous vehicles with all the possible traffic conditions that they may encounter. The work in this paper presents an alternative solution of using infrastructure to aid CAVs to learn driving policies, specifically for complex junctions, which require local experience and knowledge to handle. The proposal is to learn safe driving policies through data-driven imitation learning of human-driven vehicles at a junction utilizing data captured from surveillance devices about vehicle movements at the junction. The proposed framework is demonstrated by processing video datasets captured from uncrewed aerial vehicles (UAVs) from three intersections around Europe which contain vehicle trajectories. An imitation learning algorithm based on long short-term memory (LSTM) neural network is proposed to learn and predict safe trajectories of vehicles. The proposed framework can be used for many purposes in intelligent mobility, such as augmenting the intelligent control algorithms in driverless vehicles, benchmarking driver behavior for insurance purposes, and for providing insights to city planning.