Driver intention recognition based on Continuous Hidden Markov Model

In order to make Advanced Driver Assistance Systems (ADAS) work effectively, a driver intention recognition system is proposed. Continuous Hidden Markov Model is applied to recognize drivers´ lane change maneuver. Subjects performed lane change maneuvers with driving simulator which simulated highway scenes, and various sensor data was collected simultaneously. A series of testings and comparisons were done to obtain the optimal model structure and feature set. Results show that, taking the steering wheel angel and the steering wheel angle velocity as the optimal observation signals, the accuracy can achieve up 80%.