An Enabling Decision-Making Scheme by Considering Trajectory Prediction and Motion Uncertainty

Decision-making plays a crucial role in enabling automated driving and its performance is highly dependent on accurate motion prediction. Most existing motion prediction methods employ black-box neural network approaches, which may introduce high uncertainty and thus compromise driving safety. This study proposes a decision-making framework that takes motion prediction into account while considering predicted motion uncertainty. First, a multi-modal trajectory prediction method is introduced by combining the motion trend of the ego vehicle to reduce trajectory uncertainty. Then a two-dimensional dynamic risk assessment approach based on the Gaussian distribution is developed to quantify potential collision risk by analyzing occupancy relationship in space-time. Additionally, elementary motion patterns of automated driving in dynamic traffic environments are analyzed, and a decision-making method integrating finite state machines and the Markov decision process is established. Taking into account future motion uncertainty, it can dynamically adjust the ego vehicle's driving state in advance to ensure driving safety. Finally, the effectiveness of the proposed decision-making framework is verified under different driving scenarios extracted from the NGSIM dataset, demonstrating satisfying results in avoiding potential driving risks.

I. Introduction

Automated vehicles have attracted great attention as a promising means to enhancing the safety and efficiency of the ground transportation system [1]. While automated vehicles have demonstrated success in certain driving scenarios, their applications in complex traffic environments still face formidable challenges. One obstacle is the potential collision risk originating from the uncertainty of future motions of surrounding vehicles [2], [3]. Automated vehicles should be able to make proper decisions in response to dynamic changes of driving scenarios to ensure driving safety. Decision-making is a critical and complex task as it needs to efficiently assess current traffic conditions and accurately predict future motions of other traffic participants [4], [5]. Otherwise, automated vehicles would face substantial risks if the prediction of the lane change maneuvers of surrounding vehicles is unreliable, as illustrated in Fig. 1.