Pedestrian-vehicle interactions are critical problems in the development of autonomous driving technologies. However, there is still a lack of comprehensive understanding of pedestrian behaviors during pedestrian-vehicle interactions, especially considering the impact of group behaviors. This study proposes an Actor-Relation-Graph-based Game-Adversarial Inverse Reinforcement Learning (AR2G-AIRL) algorithm to understand pedestrian behaviors during pedestrian-vehicle interactions, considering the influence of surrounding pedestrians and vehicles. Specifically, we first identify pedestrian-vehicle interactions from a naturalistic driving dataset as the data basis. Subsequently, the AR2G-AIRL algorithm is constructed with three components: Actor-Relation Graphs (ARGs) to capture the features within groups, evolutionary game theory to extract the features between groups, and the Adversarial Inverse Reinforcement Learning (AIRL) algorithm to recover the reward function. The experiment results illustrate that the AR2G-AIRL algorithm can accurately simulate pedestrian behaviors during pedestrian-vehicle interactions and outperform all the baseline methods and ablation studies. Meanwhile, the trajectory and ARG weight visualization results demonstrate the importance of surrounding pedestrians under diverse interactions. Moreover, the analysis of the recovered reward function validates the “safety in numbers” effect and reveals the basic patterns of pedestrians interacting with vehicles without surrounding pedestrians and the heterogeneous impact of the size and morphologies of pedestrian groups on pedestrian behaviors. These results highlight the importance of incorporating group behaviors, offering insights into enhancing road safety and the efficiency of autonomous systems.

Aiming at the dynamic conflict and driving authority allocation problems in the human-automation shared steering control (SSC) system, this paper proposed a framework for decision-making and control integration that considering risk perception and game theory. Firstly, by introducing the risk perception field, the complex and variable driving risk is precisely quantified, and the drivers are divided into skilled, normal and unpracticed according to their driving skill. Taking the driving risk acceptance as the core element, combined with the driving skill, a two-layer architecture integrating decision-making and control is constructed. The upper path planning module efficiently generates candidate trajectories based on preview time and driving risk acceptance. The lower control module uses model predictive control (MPC) and non-cooperative Stackelberg game to realize steering interaction while ensuring the priority of driver’s intention. Meanwhile, a dynamic authority allocation strategy based on driving risk and driving skill is established. Finally, to fully verify the effectiveness of the proposed method, two double lane change (DLC) scenarios with the same and different reference trajectories were designed, and four evaluation indicators were proposed, including comfort and driving conflict. The experimental results show that compared with the Nash game, the Stackelberg-based method can guarantee the driver’s dominance, alleviate the human-automation conflict, reduce the driver’s workload and increase the driving smoothness.

Freeway ramp merging control in the mixed traffic consisting of connected and automated vehicles (CAVs) and human-driven vehicles (HDVs) is one of the bottlenecks in the development of autonomous driving (AD) technologies due to complex multi-vehicle interactions. To address this, we propose a decentralized human-like control framework to help CAVs merge smoothly and interact more effectively with HDVs in a mixed-traffic environment. First, a stochastic potential game model is proposed to characterize the uncertainty of HDVs’ actions and optimize individual actions while considering their impact on the global system. A model predictive controller (MPC) is designed to minimize the accumulated cost of the potential function over a time horizon. Next, a distributed algorithm is developed to solve the proposed optimization problem in parallel while reducing the computational burden. To capture the characteristics of human driving behavior and help CAVs take more human-like actions, we calibrate the parameters in the proposed model using a real-world trajectory dataset. The performance of the proposed method is tested in a realistic two-lane merging zone scenario. Experimental results show that the proposed method enables CAVs to merge smoothly and ultimately improves traffic efficiency in merging zones. Additionally, the solution quickly converges to the optimal result using the proposed distributed algorithm, supporting its application in decentralized AD systems.

Recently, the limited capacity of the Urban Rail Transit (URT) has failed to meet passenger travel demands, especially in peak hours, which leads to crowded stations and oversaturated metro networks. Considering the diverse scenarios of the multimodal public transportation network and the need for rapid generation of strategies, this study proposes a deep reinforcement learning (RL) algorithm that guides passenger route selection in the multimodal transit network to operate better. The proposed RL algorithm, consisting of graph representation learning, convolution neural network, and self-attention mechanism, is used to generate the route guidance strategy for passengers, aiming to alleviate the congestion of the multimodal transit network, improve passengers’ travel experience, and reduce CO$_{2}$emissions. Based on the multimodal transit network in Beijing, the simulation results demonstrate that the RL algorithm can well perceive the states and generate adaptive route guidance strategies that can decrease the section load rates, improve network-wide passengers’ travel experience, and reduce CO$_{2}$emissions. Even in cases where passengers are not fully compliant with the route guidance, the proposed algorithm remains effective.

A better understanding of travel pattern variability is important for public transport (PT) authorities to improve passenger experience and service provision. Although many studies have examined the travel pattern variability of PT users, these studies are often limited to a short analysis period or to only one dimension of travel behavior. In addition, there is limited knowledge of how the demographic characteristics of PT users are associated with their travel pattern variability. To address these limitations, we develop a novel measure that simultaneously considers multiple dimensions of travel behavior to quantify the intrapersonal variability in weekly PT usage. Moreover, we examine interpersonal variability by identifying clusters of users who share similar weekly profiles. Based on smart card transaction data for 52 weeks and an anonymous cardholder database (including age and gender) from Shizuoka, Japan, we analyze the intrapersonal and interpersonal variability in weekly PT usage as well as the role of gender and age in travel pattern variability. The results indicate that gender and age play an important role in the travel pattern variability of PT users. Female users exhibit higher intrapersonal variability than their male counterparts. Weekly patterns are the most diverse for users aged 70 or over, followed by the users aged 65–69. Regarding interpersonal variability, we identify five clusters of users, each characterized by a distinct weekly profile and associated with certain age and gender.

The emergence of electric buses (EBs) is expected to alleviate traffic pollution. However, the promotion of EBs requires a long transition period; during this period, EBs cannot wholly replace conventional buses (CBs). In addition, compared with CBs, EBs have long charging times and short cruising ranges, resulting in short operating times being available for the scheduling process. Therefore, to effectively schedule EBs and CBs, we propose a joint optimal scheduling model for a mixed bus fleet under micro driving conditions. First, we estimate the bus trip time under micro driving conditions. To ensure that all bus transportation tasks can be executed as planned, we propose a buffer time setting method for bus transportation tasks. On this basis, we construct an optimization model, which is used for the joint optimal scheduling of EBs and CBs under different mixing rates. A heuristic procedure based on the genetic algorithm is designed to solve the model. The proposed methodology is validated based on data from Beijing Public Transport, China. The results show that the proposed model considering micro driving conditions is superior to the conventional model in terms of rationality and reliability.