Lane Change Trajectory Planning for Personalized Driving Comfort and Mobility Efficiency

2026-06-04

AI Summary

This work addresses the challenge of balancing comfort and efficiency in lane-changing maneuvers, where longitudinal and lateral motions are strongly coupled and exhibit significant inter-driver variability. To this end, the authors propose a neural network–driven personalized trajectory planner that integrates a third-order polynomial generator with a dual-head architecture: one branch ensures general trajectory feasibility, while the other learns individual driver preferences. A gating mechanism based on error-based winning logistic regression adaptively switches between these branches to enable context-aware dynamic adaptation. Evaluations in representative scenarios and Monte Carlo simulations demonstrate that the proposed method effectively balances ride comfort and traffic efficiency, and crucially, remains capable of generating feasible trajectories even in the absence of personalized driving data.

Abstract

Lane changing entails simultaneous longitudinal and lateral motions that affect driving comfort and mobility efficiency. Because these motions are tightly coupled and subject to substantial inter-vehicle variability, trajectory planning for lane-change maneuvers is characterized by a highly personalized nature. This study proposes a neural network-driven planner that integrates a third-order polynomial trajectory generator with a learning module that infers optimal trajectory parameters across diverse driving conditions. Using a shared backbone with dual heads, one head ensures all-condition operational guarantees, while the other captures driver-specific preferences for comfort or mobility efficiency. A head-gated switching mechanism, realized through a statistical gate based on error-winner logistic regression, adaptively selects the appropriate head under varying driving conditions, which enables context-aware lane-change trajectory planning. Representative cases and Monte Carlo simulations show that the proposed planner achieves personalized comfort and mobility during lane changes, while the baseline ensures feasible trajectories under driving conditions where personalized data are insufficient or inaccessible.

Problem

• lane change
• trajectory planning
• driving comfort
• mobility efficiency
• personalization

Innovation

• neural network-driven planner
• personalized trajectory planning
• dual-head architecture
• head-gated switching mechanism
• lane change maneuver