適応的予測アンサンブル：運動予測の分布外汎化性能の向上
Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecasting
深層学習とルールベースの予測を組み合わせ、入力シーンに応じて動的に最適な予測を選択する適応的予測アンサンブル（APE）を提案し、自動運転の軌道予測における分布外汎化性能を改善した。
著者: Jinning Li, Jiachen Li, Sangjae Bae, David Isele
分類: cs.RO, cs.AI, cs.CV, cs.LG
原文アブストラクト
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.
