Driver Cut-in Behavior

To understand and simulate driver's cut-in control behaviors, we propose a platoon-oriented cut-in behavior model.

To understand and simulate the driver decisions on whether to continue the cut-in and when to execute the lane-change during the cut-in process, we propose a two-layer prediction-based decision model.

To handle cut-ins, we propose an intention prediction-based control method for the VPs by considering the tradeoff between the platoon integrity and traffic safety.

We investigate how to classify and analyze the driving style of the cut-in process.

Research objective: to mimic driver's cut-in control behaviors towards a platoon.

Novelties: (1) The 1st work on lane-change against a platoon, vs one vehicle in car-following model or none vehicle in steering model by STOA; (2) Personalized human-like ADAS.

Modeling idea: We build a combined model by integrating a lateral and a longitudinal control model into the QN cognitive architecture

Research objective: 1) to model drivers decisions on whether to continue the cut-in/ when to execute the lane change; 2) to represent different decision driving styles

Novelties: The 1st work investigating driver decision behavior in the cut-in process

Modeling idea: we build a two-layer prediction-based decision model by combining a dynamic prediction module, a continuity decision module, and an execution decision module.

Research objective: to control the platoon to prevent cut-ins while keeping road safety.

Novelties: (1) The 1st work considering the tradeoff between platoon efficacy and road safety; (2) The 1st work incorporating the prediction of the driver intention

Cut-in prediction part: a SVM-based algorithm is designed to predict the cut-in intention of human drivers; a trajectory prediction algorithm is used to predict the trajectory of the HDV

FSM-based predictive control part: an FSM and an MPC algorithm are built to implement the control objectives of the proposed method.

Research objective: to help identify and simulate the cut-ins with different driving styles.

Novelties: The 1st work to analyze the driving style of the cut-in behavior

The principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) methods are employed to reduce the dimensionality of the features. The k-means++ algorithm is applied to cluster the driving style of the cut-ins.