In high-speed automatic driving scenarios, the recognition of lane change intention of surrounding vehicles is a key issue. Most studies adopted relevant features and classification algorithms to predict lane change maneuver. These conventional methods are effective in frequent lane change scenarios. However, considering the variance of individual driving characteristics and measurement uncertainty, false intention recognition remains a major problem to be resolved. Hence we proposed an approach to reduce false lane change recognition by introducing the predicted trajectories of the target vehicles. A rule-based approach is used to infer an initial lane change intention and a sampling-based approach generated a predicted trajectory according to the inferred intention. Considering the physical inertia, a constant acceleration motion model is used to generate another reference trajectory. The preparatory lane change intention updates in real time if the predicted trajectory deviates from the reference trajectory. Experiment results demonstrate the capacity of proposed approach to improve the performance of the lane change intention recognition.

CICTP