HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling

TL;DR

HYPER is a hybrid trajectory prediction framework that models evolving human intent using a discrete-continuous system, improving accuracy and coverage in multi-modal trajectory forecasting.

Contribution

It introduces a novel hybrid model that captures changing human intent over time and employs neural proposal distributions for adaptive sampling, enhancing trajectory prediction.

Findings

Outperforms state-of-the-art models on Argoverse dataset

Effectively models evolving intent over longer horizons

Achieves a better balance between accuracy and coverage

Abstract

Modeling multi-modal high-level intent is important for ensuring diversity in trajectory prediction. Existing approaches explore the discrete nature of human intent before predicting continuous trajectories, to improve accuracy and support explainability. However, these approaches often assume the intent to remain fixed over the prediction horizon, which is problematic in practice, especially over longer horizons. To overcome this limitation, we introduce HYPER, a general and expressive hybrid prediction framework that models evolving human intent. By modeling traffic agents as a hybrid discrete-continuous system, our approach is capable of predicting discrete intent changes over time. We learn the probabilistic hybrid model via a maximum likelihood estimation problem and leverage neural proposal distributions to sample adaptively from the exponentially growing discrete space. The overall approach affords a better trade-off between accuracy and coverage. We train and validate our model on the Argoverse dataset, and demonstrate its effectiveness through comprehensive ablation studies and comparisons with state-of-the-art models.