CVAE-H: Conditionalizing Variational Autoencoders via Hypernetworks and Trajectory Forecasting for Autonomous Driving

TL;DR

CVAE-H is a novel probabilistic model using hypernetworks to generate diverse, context-aware future predictions of road agents, improving autonomous driving scene understanding.

Contribution

The paper introduces CVAE-H, a hypernetwork-based conditional VAE that enhances trajectory prediction for autonomous driving by capturing multi-modal, context-dependent behaviors.

Findings

CVAE-H produces diverse, accurate trajectory predictions.

The model effectively captures multi-modal behaviors in various environments.

CVAE-H outperforms baseline methods in prediction accuracy.

Abstract

The task of predicting stochastic behaviors of road agents in diverse environments is a challenging problem for autonomous driving. To best understand scene contexts and produce diverse possible future states of the road agents adaptively in different environments, a prediction model should be probabilistic, multi-modal, context-driven, and general. We present Conditionalizing Variational AutoEncoders via Hypernetworks (CVAE-H); a conditional VAE that extensively leverages hypernetwork and performs generative tasks for high-dimensional problems like the prediction task. We first evaluate CVAE-H on simple generative experiments to show that CVAE-H is probabilistic, multi-modal, context-driven, and general. Then, we demonstrate that the proposed model effectively solves a self-driving prediction problem by producing accurate predictions of road agents in various environments.