G2LTraj: A Global-to-Local Generation Approach for Trajectory Prediction

TL;DR

G2LTraj is a novel trajectory prediction method that combines global key step generation with local recursive filling, improving accuracy and kinematic feasibility in autonomous driving scenarios.

Contribution

The paper introduces G2LTraj, a global-to-local generation framework that reduces error accumulation and enhances kinematic constraints in trajectory prediction.

Findings

Improves prediction accuracy across multiple datasets.

Reduces error propagation compared to recursive methods.

Enhances kinematic feasibility with spatial and temporal constraints.

Abstract

Predicting future trajectories of traffic agents accurately holds substantial importance in various applications such as autonomous driving. Previous methods commonly infer all future steps of an agent either recursively or simultaneously. However, the recursive strategy suffers from the accumulated error, while the simultaneous strategy overlooks the constraints among future steps, resulting in kinematically infeasible predictions. To address these issues, in this paper, we propose G2LTraj, a plug-and-play global-to-local generation approach for trajectory prediction. Specifically, we generate a series of global key steps that uniformly cover the entire future time range. Subsequently, the local intermediate steps between the adjacent key steps are recursively filled in. In this way, we prevent the accumulated error from propagating beyond the adjacent key steps. Moreover, to boost the kinematical feasibility, we not only introduce the spatial constraints among key steps but also strengthen the temporal constraints among the intermediate steps. Finally, to ensure the optimal granularity of key steps, we design a selectable granularity strategy that caters to each predicted trajectory. Our G2LTraj significantly improves the performance of seven existing trajectory predictors across the ETH, UCY and nuScenes datasets. Experimental results demonstrate its effectiveness. Code will be available at https://github.com/Zhanwei-Z/G2LTraj.