UniPlanner: A Unified Motion Planning Framework for Autonomous Vehicle Decision-Making Systems via Multi-Dataset Integration

TL;DR

UniPlanner is a novel motion planning framework that integrates multiple datasets for autonomous vehicles, enhancing robustness and safety by leveraging cross-dataset trajectory correlations and innovative learning modules.

Contribution

It introduces the first multi-dataset integrated planning framework with three novel modules for robust, cross-dataset autonomous vehicle decision-making.

Findings

Achieves unified cross-dataset learning for motion planning.

Effectively leverages trajectory correlations across datasets.

Enhances planning robustness and safety.

Abstract

Motion planning is a critical component of autonomous vehicle decision-making systems, directly determining trajectory safety and driving efficiency. While deep learning approaches have advanced planning capabilities, existing methods remain confined to single-dataset training, limiting their robustness in planning. Through systematic analysis, we discover that vehicular trajectory distributions and history-future correlations demonstrate remarkable consistency across different datasets. Based on these findings, we propose UniPlanner, the first planning framework designed for multi-dataset integration in autonomous vehicle decision-making. UniPlanner achieves unified cross-dataset learning through three synergistic innovations. First, the History-Future Trajectory Dictionary Network (HFTDN) aggregates history-future trajectory pairs from multiple datasets, using historical trajectory similarity to retrieve relevant futures and generate cross-dataset planning guidance. Second, the Gradient-Free Trajectory Mapper (GFTM) learns robust history-future correlations from multiple datasets, transforming historical trajectories into universal planning priors. Its gradient-free design ensures the introduction of valuable priors while preventing shortcut learning, making the planning knowledge safely transferable. Third, the Sparse-to-Dense (S2D) paradigm implements adaptive dropout to selectively suppress planning priors during training for robust learning, while enabling full prior utilization during inference to maximize planning performance.