Xiaojing Du

With the development of the connected autonomous bus, the interactions between the bus and social vehicle during the mandatory lane changing for bus exiting become more diverse and complex. This research investigates the evolutionary dynamics of behavioral decision-making for the bus and social vehicle in different scenarios. The evolutionary game model for the connected autonomous bus and social vehicle is built, as do the human-driven bus and social vehicle, and the connected autonomous bus under different penetration rates and social vehicle. The results of numerical experiments reveal that the connected autonomous bus chooses to change lanes in most instances, and the strategies of the human-driven bus show conservative tendencies. Such tendencies are weakened when the connected autonomous bus and human-driven bus are mixed. As for the social vehicle in different scenarios, the strategies that balance overall traffic safety and efficiency are promoted. This research provides some references for intelligent decision-making of lane changing in urban public transportation.

Three hybrid deep spatio-temporal models are proposed to accurately predict traffic flow under normal conditions, on holidays and under adverse weather. Each of the proposed models consists of the global and target parts, and fuses the weather and traffic flow data obtained from the target and upstream sections. The convolutional neural network (CNN), and the gated recurrent unit (GRU) and convolutional long short-term memory (ConvLSTM) neural networks are selected to analyze the spatio-temporal characteristics of traffic flow data. Then, the three proposed models are verified using three actual cases, including traffic flow prediction under normal conditions, on holidays and under adverse weather. Moreover, the characteristics of traffic flow data on the Independence Day and Thanksgiving Day are discussed, as do the patterns of traffic flow data under heavy rain and strong wind. The experimental results show that: the three new models usually perform better than the existing models under all the situations; different holidays and different types of adverse weather have various impacts on the characteristics of traffic volume and speed data.

To improve public transportation operations, this research investigates the lane-changing behaviors for buses exiting at bus bay stops. Game theory is utilized to analyze the interactions between bus and social vehicle drivers. A two-player noncooperative, non-zero-sum mixed-strategy game model is formulated to consider the time saving and collision avoidance payoffs for both players in the game. The characteristic of mass passengers carried by buses is also taken into account in the payoffs. The maximum likelihood estimation is used to calibrate the formulated model using the vehicle trajectory data collected from Lvboqiao bus bay stop, Dalian, China. The validation results reveal that the formulated model can effectively predict the lane-changing decisions with a high level of accuracy. Besides mixed strategies, the players in the game may have dominant strategies, which are the best choices that have nothing to do with the strategies that other players may adopt. In both mixed and dominant strategies, bus drivers are more inclined to choose the strategy of not changing a lane, and social vehicle drivers tend to choose the strategy of not giving way to the bus. The tendencies to choose strategies by both players are consistent with the actual decisions made by drivers. It is proven that the formulated game model is highly reliable to describe bus drivers’ exiting behaviors at bus bay stops and can offer the decent theoretical support for both players to make better decisions.