01371144

Component

Driving behavior in traffic has been modeled quite successfully in simulation software using predefined car-following models rules. However, most car-following models are not capable of representing naturalistic driving behavior during safety-critical events, since they were designed to adhere to safe. Also, vehicle detailed lateral maneuvering have not been simulated in most simulation software. The proposed methodology in this paper focuses on establishing a traffic state-action mapping rule to simulate real driver actions including risky behavior that a driver would take during safety critical events instead of the predefined actions by car-following models. To analyze individual driver characteristics and extract driving behavior rules, a fuzzy rule based neural network is constructed with the objective of presenting driver action rules under associated traffic states. A special training approach Neuro-Fuzzy Actor Critic Reinforcement Learning (NFACRL) is proposed as a methodology to train an agent driver simulator. Vehicle longitudinal and lateral actions are estimated and used as output of this model. The simulated vehicle actions are compared with naturalistic data.

This paper was sponsored by TRB committee AND30 Simulation and Measurement of Vehicle and Operator Performance

01362476

12-4601

English

28p

2012

Transportation Research Board 91st Annual Meeting

Digital/other

Figures; References; Tables

Automatic data collection systems; Behavior; Drivers; Fuzzy algorithms; Machine learning; Neural networks; Traffic safety; Traffic simulation; Vehicle spacing

Highways; Operations and Traffic Management; Safety and Human Factors; I70: Traffic and Transport; I83: Accidents and the Human Factor

Transportation Research Board Annual Meeting 2012 Paper #12-4601

TRIS, TRB

Feb 8 2012 5:25PM