Intelligent Decision Making in Autonomous Vehicles using Cognition Aided Reinforcement Learning
Intelligent Decision Making in Autonomous Vehicles using Cognition Aided Reinforcement Learning
复制标题
DOI：
10.1109/wcnc51071.2022.9771728
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Heena Rathore;V. Bhadauria
中科院分区：
文献类型：
--
作者：
Heena Rathore;V. Bhadauria
随着传感、计算和通信领域的最新进展加速了自动驾驶汽车（AV）的普及，它们与人类驾驶的车辆共享道路提出了一个迫切需要研究的挑战。自动驾驶汽车可以在确定性的编程行为方面表现出色，但人类驾驶员仍然具有优势，因为人类的认知能力已经进化了数千年。本文提出了认知辅助强化学习（CARL）算法，该算法利用了认知的五个原则-记忆，注意力，语言，感知和智力。传感器建立感知，数据促进记忆，安全信息支持语言。智能将信息与专注于具体行动的注意力融合在一起，以获得最大回报。仿真结果表明，与最先进的无模型强化学习算法相比，CARL的速度要快10倍。此外，通过使用元认知（学习如何学习的艺术）的原则，CARL在由具有不同程度自主性的车辆组成的异构环境中实现了最佳奖励。
As recent advances in sensing, computing, and communications expedite proliferation of autonomous vehicles (AV), their sharing the road with human driven vehicles presents a challenge that demands urgent investigation. AVs can excel at deterministic programmed behavior, still human drivers have the edge because of the faculty of cognition, which evolved over millennia. This paper presents Cognition Aided Reinforcement Learning (CARL) algorithm that harnesses inputs from five principles of cognition — memory, attention, language, perception, and intelligence. Sensors build perception, data facilitate memory, and safety messages enable language support. Intelligence fuses information with attention focused on specific actions for reward maximization. Simulation results show CARL to be 10 times faster as compared to the state of the art model-free reinforcement learning algorithms. Additionally, by using the principle of metacognition (art of learning how to learn), CARL achieves optimal rewards in a heterogeneous environment composed of vehicles with varying degrees of autonomy.