This paper is on decision making of autonomous vehicles for handling roundabouts. The round intersection is introduced first followed by the Markov Decision Processes (MDP), the Partially Observable Markov Decision Processes (POMDP) and the Object Oriented Partially Observable Markov Decision Process (OOPOMDP). The Partially Observable Monte-Carlo Planning algorihtm (POMCP) algorithm is introduced and OOPOMDP is applied to decision making for autonomous vehicles in round intersections. Decision making is formulated as a POMDP problem and the penalty function is formulated and set followed by improvement of decision making with policy prediction. The augmented objective state and policy based state transition is introduced simulations are used to demonstrate the effectiveness of the proposed method.

翻译：本文研究自主车辆在环形交叉口的决策问题。首先介绍环形交叉口，随后阐述马尔可夫决策过程(MDP)、部分可观测马尔可夫决策过程(POMDP)及面向对象的部分可观测马尔可夫决策过程(OOPOMDP)。引入部分可观测蒙特卡洛规划(POMCP)算法，并将OOPOMDP应用于环形交叉口场景下自主车辆的决策制定。将决策问题建模为POMDP问题，建立并设置惩罚函数，进而通过策略预测改进决策效果。本文引入增广目标状态与基于策略的状态转移机制，并通过仿真实验验证所提方法的有效性。