Adaptive Prediction Ensemble

Adaptive Prediction Ensemble:

Improving Out-of-Distribution Generalization of Motion Forecasting

Jinning Li, Jiachen Li, Sangjae Bae, David Isele

Abstract

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.

Overview of the Algorithm

The model structures of the learned routing function and the deep learning-based prediction algorithm share the same backbone of scene encoder, and are trained concurrently. In this way, the routing function shares the same level of powerful scene understanding ability with the motion prediction algorithm, while trained concurrently on all footprint prediction outputs increases its exposure to diverse anomalous trajectory predictions and hence more capability on differentiating prediction quality.

Improving prediction algorithm by Adaptive Prediction Ensemble is inspired by (a) An example scenario where vanilla rule-based prediction algorithm outperforms deep NN prediction algorithm (MTR). (b) A comparison of the error (minADE) between deep NN and rule-based prediction. The rule-based method outperforms deep NN in a considerable amount of scenarios, which are the ones below the red line.

APE Performance Visualization

The above figures show trajectory prediction visualization curated by the learning-based routing function:

(a)(b) Cases where the learning based algorithm (MTR) generalizes better than the rule-based method (constant velocity model).

(c)(d) Cases where the rule-based method (constant velocity model) generalizes better than the learning based algorithm (MTR).

Google Sites

Report abuse