# Multi-Step Prediction of Occupancy Grid Maps with Recurrent Neural Networks

## TL;DR

This paper presents a novel RNN-based approach for multi-step prediction of drivable space in occupancy grid maps, improving accuracy by incorporating motion features and difference learning, aiding autonomous vehicle navigation.

## Contribution

The paper introduces a difference learning method with RNNs that enhances multi-step OGM prediction accuracy, effectively handling static and moving objects in autonomous driving scenarios.

## Key findings

- Significant accuracy improvement over state-of-the-art methods.
- Effective removal of egomotion by transforming OGMs into a common frame.
- Accurate prediction of both static and moving objects in OGMs.

## Abstract

We investigate the multi-step prediction of the drivable space, represented by Occupancy Grid Maps (OGMs), for autonomous vehicles. Our motivation is that accurate multi-step prediction of the drivable space can efficiently improve path planning and navigation resulting in safe, comfortable and optimum paths in autonomous driving. We train a variety of Recurrent Neural Network (RNN) based architectures on the OGM sequences from the KITTI dataset. The results demonstrate significant improvement of the prediction accuracy using our proposed difference learning method, incorporating motion related features, over the state of the art. We remove the egomotion from the OGM sequences by transforming them into a common frame. Although in the transformed sequences the KITTI dataset is heavily biased toward static objects, by learning the difference between subsequent OGMs, our proposed method provides accurate prediction over both the static and moving objects.