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

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, multimodal, 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.

A New Evolution Model for Weighted Directed Networks

“…HyperSeg [23] utilizes a hypernetwork as an encoder to provide parameters for a decoder, achieving outstanding performance in semantic segmentation. CVAE-H [24] further extends the application of hypernetworks to the field of autonomous driving. Building on the successful experiences documented in previous literature, this paper explores the application of hypernetworks to amodal completion.…”