TrajFlow: A Generative Framework for Occupancy Density Estimation Using Normalizing Flows

TL;DR

TrajFlow introduces a novel generative framework using normalizing flows and neural differential equations to accurately estimate occupancy densities of agents in traffic, improving trajectory forecasting and downstream task performance.

Contribution

The paper presents a new marginal density modeling approach with a neural differential equation architecture for better accuracy and continuous sampling in trajectory prediction.

Findings

Higher accuracy on trajectory forecasting benchmarks.

Enables fully continuous sampling of future locations.

Improves downstream tasks like occupancy grid computation.

Abstract

For intelligent transportation systems and autonomous vehicles to operate safely and efficiently, they must reliably predict the future motion and trajectory of surrounding agents within complex traffic environments. At the same time, the motion of these agents is inherently uncertain, making accurate prediction difficult. In this paper, we propose \textbf{TrajFlow}, a generative framework for estimating the occupancy density of dynamic agents. Our framework utilizes a causal encoder to extract semantically meaningful embeddings of the observed trajectory, as well as a normalizing flow to decode these embeddings and determine the most likely future location of an agent at some time point in the future. Our formulation differs from existing approaches because we model the marginal distribution of spatial locations instead of the joint distribution of unobserved trajectories. The advantages of a marginal formulation are numerous. First, we demonstrate that the marginal formulation produces higher accuracy on challenging trajectory forecasting benchmarks. Second, the marginal formulation allows for fully continuous sampling of future locations. Finally, marginal densities are better suited for downstream tasks as they allow for the computation of per-agent motion trajectories and occupancy grids, the two most commonly used representations for motion forecasting. We present a novel architecture based entirely on neural differential equations as an implementation of this framework and provide ablations to demonstrate the advantages of a continuous implementation over a more traditional discrete neural network based approach. The code is available at https://github.com/UMN-Choi-Lab/TrajFlow.