.png){kind=icon}
.png){kind=icon}
Return
Integrated optimization for vehicle trajectory reconstruction under cooperative perception environment
.png){kind=icon}
PRE
AI
T
W
Y
DOI：10.1016/j.trc.2026.105522.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Vehicle trajectories provide detailed information about vehicle movements and interactions, which are essential for various transportation applications. However, collecting complete vehicle trajectory data requires high costs. Reconstructing complete vehicle trajectories from partial observations is thus a more cost-effective alternative. Previous studies on trajectory reconstruction primarily focused on vehicle longitudinal behaviors, usually neglecting lane-change (LC) maneuvers. This study proposes an integrated optimization-based vehicle trajectory reconstruction model that considers LC and overtaking behaviors under a cooperative perception environment with very low market penetration rates (MPRs) of connected and automated vehicles (CAVs) and varying packet loss rates (PLRs) of vehicle-to-everything (V2X) communication. A Mixed Integer Linear Programming (MILP) problem is constructed with the objective of minimizing the errors between reconstructed trajectories and observed trajectories, which converts the trajectory reconstruction problem into a joint trajectory generation problem. Moreover, this study considers a cooperative perception environment where partial observed trajectories are collected from CAV perception sensors. Different from other studies that implemented oversimplified detection models to generate observed trajectories without considering the real-world complexity and variability of detection patterns from perception sensors, in this study, we adopt distance-dependent true positive rates (TPRs) as detection performance metric to mimic CAV detection, computed using BEVFusion detection outputs on the nuScenes dataset. The proposed formulation streamlines the entire process and can be applied to various road geometries and traffic conditions. Numerical studies using both NGSIM highway and urban arterial datasets demonstrate the model's effectiveness in reconstructing vehicle trajectories under 2%-5% CAV MPRs with varying PLRs. Additional sensitivity analysis was conducted to evaluate the impact of 1) vehicle occlusion in CAV detection model; 2) varying traffic conditions (i.e., demand levels); and 3) weights of different terms in the objective function on the trajectory reconstruction accuracy. Under similar reconstruction rates of unobserved trajectories and road segment lengths, the proposed method outperforms existing studies by a significant margin in terms of both longitudinal position accuracy and LC time prediction. The source code is publicly available at https://github.com/Purdue-CART-Lab/CP-TrajRecon-Opt.
Keywords:
Trajectory Reconstruction
Connected and Automated Vehicles
Cooperative Perception
BEVFusion
Lane Change
Mixed Integer Linear Programming
Journal
IF:
7.9
Papers:
4.7K
Citations:
3.2W
Organization
Cited Papers