UniPlanner: A Unified Motion Planning Framework for Autonomous Vehicle Decision-Making Systems via Multi-Dataset Integration
This work addresses robustness issues in autonomous vehicle decision-making by enabling cross-dataset learning, though it appears incremental as it builds on existing deep learning approaches.
The paper tackles the problem of limited robustness in autonomous vehicle motion planning due to single-dataset training by proposing UniPlanner, a unified framework for multi-dataset integration, which improves planning performance through innovations like a gradient-free trajectory mapper and sparse-to-dense paradigm.
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.