面向不确定性环境的自动驾驶运动规划: 机遇与挑战

Motion planning algorithm, as an important part of autonomous driving systems, draws increasing attention from researchers. However, most existing motion planning algorithms only consider their application in deterministic structured environments, neglecting potential uncertainties in dynamic traffic environments. In this paper, motion planning algorithms are divided into two categories for the uncertain environment: partially observable Markov decision process and probability occupancy grid map. The two categories are introduced for three aspects: theoretical foundation, solution algorithm and practical application. The strategy with the maximum discounted reward in the future is calculated by partially observable Markov decision process based on the current confidence state. Probability occupancy grid map utilizes probability to represent the occupancy status of corresponding grids, measuring the possibility of dynamic changes in traffic flow, and well representing the uncertainty. Finally, the main challenges and future research directions for motion planning in uncertain environments are summarized .