Learning Continuous Environment Fields via Implicit Functions

TL;DR

This paper introduces a continuous environment field representation learned via neural implicit functions, enabling agents and humans to navigate and predict trajectories in 2D and 3D scenes with high plausibility and efficiency.

Contribution

It presents a novel neural implicit environment field that encodes reaching distances and guides agent and human trajectory predictions in complex scenes.

Findings

The environment field accurately guides agent navigation in 2D mazes.

The method produces plausible human trajectories in 3D indoor environments.

The approach is efficient and outperforms existing trajectory prediction methods.

Abstract

We propose a novel scene representation that encodes reaching distance -- the distance between any position in the scene to a goal along a feasible trajectory. We demonstrate that this environment field representation can directly guide the dynamic behaviors of agents in 2D mazes or 3D indoor scenes. Our environment field is a continuous representation and learned via a neural implicit function using discretely sampled training data. We showcase its application for agent navigation in 2D mazes, and human trajectory prediction in 3D indoor environments. To produce physically plausible and natural trajectories for humans, we additionally learn a generative model that predicts regions where humans commonly appear, and enforce the environment field to be defined within such regions. Extensive experiments demonstrate that the proposed method can generate both feasible and plausible trajectories efficiently and accurately.