Predicting Future Occupancy Grids in Dynamic Environment with Spatio-Temporal Learning

TL;DR

This paper introduces a spatio-temporal prediction network that forecasts future occupancy in dynamic urban environments over a 3-second horizon, outperforming current methods without relying on HD-Maps.

Contribution

The proposed approach predicts longer-term occupancy in complex scenes using a novel spatio-temporal network that leverages past environment data and semantic labels.

Findings

Predicts occupancy for 3 seconds ahead in complex urban scenes.

Outperforms state-of-the-art methods in accuracy.

Does not require HD-Maps or explicit dynamic object modeling.

Abstract

Reliably predicting future occupancy of highly dynamic urban environments is an important precursor for safe autonomous navigation. Common challenges in the prediction include forecasting the relative position of other vehicles, modelling the dynamics of vehicles subjected to different traffic conditions, and vanishing surrounding objects. To tackle these challenges, we propose a spatio-temporal prediction network pipeline that takes the past information from the environment and semantic labels separately for generating future occupancy predictions. Compared to the current SOTA, our approach predicts occupancy for a longer horizon of 3 seconds and in a relatively complex environment from the nuScenes dataset. Our experimental results demonstrate the ability of spatio-temporal networks to understand scene dynamics without the need for HD-Maps and explicit modeling dynamic objects. We publicly release our occupancy grid dataset based on nuScenes to support further research.