LAUSR

Lane-changing behaviour is one of the most important and basic driving behaviours. Intelligent and connected vehicles must face lane-changing scenarios to achieve autonomous driving. To improve the rationality of lane-changing trajectory planning for intelligent vehicles, by analysing numerous real vehicle lane-changing trajectories in the German HighD natural driving dataset, a dimensionless lateral quantification balance index is proposed to realise a comprehensive and objective evaluation of the degree of human-likeness of lane change trajectory planning. Focused on the lateral kinematic characteristics of lane changing, a lane-changing trajectory extraction method based on the peak-to-peak value of lateral acceleration is proposed. Lateral displacement, lateral velocity, lateral acceleration and lane-changing duration are extracted from natural driving data, and the correlations between the parameters are revealed to deduce the lateral quantification balance index. With several common parametric lane-changing trajectory models of intelligent vehicles, such as sine, quintic polynomial, Gaussian and hyperbolic tangent and fifth-order Bessel models, as examples, the index values of each lane-changing trajectory model are calculated and obtained. Results show that the proposed index can balance the different requirements in lane-changing efficiency and comfort of the trajectory parameters during the lane-changing process, thus achieving a comprehensive quantitative evaluation of lateral stability, efficiency and comfort. This research establishes an intuitive and concise objective function for human-like trajectory planning and provides a basis for trajectory tracking control and real-time dynamic correction of intelligent vehicles.