A Stochastic Driver Pedal Behavior Model Incorporating Road Information

Human driver's pedal behavior is difficult to model because it is the output of a very complicated virtual stochastic system. This paper provides a new way to describe driver's pedal behavior after decomposing it into a sequence of actions. By considering the vehicle and road information as the inputs and the pedal action as the output, an input-output hidden Markov model (IOHMM) is used to describe the pedal behavior. The state transition and output distribution functions are designed, and the relation between the input and the key variables of the output distributions is analyzed and modeled using statistical methods. The model parameters can be identified for individual drivers using the generalized estimation-maximization method. One-step probability prediction test shows that the proposed model can capture and distinguish each individual driver's driving style. The prediction capability of the proposed model is evaluated by comparing it with the human driver data collected on a driving simulator along with three other models. The results show that the proposed IOHMM-based driver pedal behavior model performs well in prediction horizons from 1 to 60 s.