Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios

Abstract

Predicting driver rear-end risk-avoidance maneuvers in cut-in scenarios, especially dangerous precrash scenarios, benefits the customization of automatic driving, particularly automatic steering. This paper studies driver rear-end risk-avoidance behaviors in cut-in scenarios on a straight three-lane highway. Data from 24 participants in 1326 valid trials were collected using a motion-based driving simulator. An Eysenck Personality Questionnaire (revised for Chinese participants) was used to obtain the personality traits of the participants. Based on a statistical analysis, the candidate features used in the driver maneuver prediction were determined as a combination of objective risk indicators and driver characteristics. A decision tree-based model was constructed for maneuver prediction in cut-in scenarios. The prediction accuracy of the extracted classification rules was 79.2% for the training data set and 80.3% for the test data set. The most powerful predictive variables were extracted, and their effects on maneuver decisions were analyzed. The results show that driver characteristics strongly influence the prediction of maneuver decisions.

Toward Computational Simulations of Behavior During Automated Driving Takeovers: A Review of the Empirical and Modeling Literatures

“…Machine learning models. Hu et al (2017) developed a decision tree model to predict driver maneuvers during a cut-in scenario. Their model included kinematic variables, such as the distance and TTC to a leading vehicle in the adjacent lane, driver age, and personality factors, including extroversion and neuroticism.…”

Computational Modeling of Driving Behaviors: Challenges and Approaches

“…For example, Wu, Boyle, and Marshall [23] designed a logistic regression model to demonstrate that drivers' demographic information can predict their choice between steering and braking. Hu et al [24] used a decision tree to predict driver maneuvers in a cut-in scenario. Researchers used cognitive architecture to model drivers' behavior.…”

A Dynamic Bayesian Network for Vehicle Maneuver Prediction in Highway Driving Scenarios: Framework and Verification

“…naive Bayesian approach [19] , rule-based approach [20], decision tree-based approach [21], interacting multiple model filter [22,23], hidden Markov model [24][25][26] With traffic interaction convolutional neural network [27], long short-term memory network [28][29][30], interactive hidden Markov model [31], Bayesian network and its variations [32][33][34][35][36] Physics-based features mainly refer to detective states (e.g., position, velocity, acceleration) of surrounding vehicles. Because the motion of vehicles satisfies kinematic and dynamic laws, the historical states of vehicles with kinematic and dynamic laws can be used to infer possible future states (i.e., motion boundaries) of vehicles.…”

“…In [20], maneuver prediction is performed based on two types of features and ontology-based rules, which models priori driving knowledge. Similarly, the paper [21] adopts the decision tree method for predicting risk behaviors in cut-in scenes. However, these two methods [20,21] have high complexity and are difficult to be extended to other environments.…”

“…Similarly, the paper [21] adopts the decision tree method for predicting risk behaviors in cut-in scenes. However, these two methods [20,21] have high complexity and are difficult to be extended to other environments. In [22], a unified multi-model filtering algorithm for maneuver prediction and trajectory prediction is proposed.…”