Abstract :
Based on speed changing and lane changing, it is divided into 6 driving intentions in the 2 dimensions, which are speed-up and lane-changing, keep speed and lane-changing, speed-down and lane-changing, speed-up and keep lane, keep speed and keep lane, and speed-down and lane-changing. Considering the continuity of the vehicle movement, the Gaussian density function is used to improve 2D HMM, based on which the driving intentions were identified. The headway, object speed and lateral acceleration is the input, and output driving intentions. Speed-changing and lane changing or not are chose to the 2 dimensions of C-P2D-HMM´s hidden variable. The results of simulation show that the method is right and effective, whose identification accuracy is 98.84%. Otherwise, it can realize prediction by the transition probability to warn the abnormal driving and reduce traffic accidents caused by it.
Keywords :
Gaussian processes; accident prevention; driver information systems; hidden Markov models; identification; 2D HMM; C-P2D-HMM hidden variable; Gaussian density function; abnormal driving; continuous pseudo 2D hidden Markov model; driving intention identification; identification accuracy; keep lane; keep speed; lane changing; object speed; speed changing; speed down; traffic accident; transition probability; vehicle movement; Accuracy; Data models; Hidden Markov models; Predictive models; Probability distribution; Safety; Vehicles; Gaussian density function; P2D HMM; Traffic engineering; intention identify;
