Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecasting
This work addresses the critical issue of unreliable trajectory prediction in autonomous driving when faced with unseen scenarios, offering a hybrid solution that enhances robustness and generalization, though it appears incremental as it builds on existing methods.
The paper tackles the problem of poor out-of-distribution generalization in deep learning-based motion forecasting for autonomous driving by proposing the Adaptive Prediction Ensemble (APE), which integrates deep learning and rule-based experts with a learned routing function, resulting in improved zero-shot generalization across datasets like Waymo and Argoverse, particularly for long-horizon predictions and OOD scenarios.
Deep learning-based trajectory prediction models for autonomous driving often struggle with generalization to out-of-distribution (OOD) scenarios, sometimes performing worse than simple rule-based models. To address this limitation, we propose a novel framework, Adaptive Prediction Ensemble (APE), which integrates deep learning and rule-based prediction experts. A learned routing function, trained concurrently with the deep learning model, dynamically selects the most reliable prediction based on the input scenario. Our experiments on large-scale datasets, including Waymo Open Motion Dataset (WOMD) and Argoverse, demonstrate improvement in zero-shot generalization across datasets. We show that our method outperforms individual prediction models and other variants, particularly in long-horizon prediction and scenarios with a high proportion of OOD data. This work highlights the potential of hybrid approaches for robust and generalizable motion prediction in autonomous driving. More details can be found on the project page: https://sites.google.com/view/ape-generalization.