# Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets

## TL;DR

This paper introduces a deep learning method utilizing high-definition maps and efficient convolutional networks to accurately and quickly predict the future movements of vulnerable road users like pedestrians and bicyclists, enhancing self-driving vehicle safety.

## Contribution

It presents a novel deep learning approach that rasterizes HD maps for VRU motion prediction and proposes a fast architecture optimized for real-time inference.

## Key findings

- Improved prediction accuracy over baseline methods
- Reduced inference latency enabling real-time application
- Optimal rasterization approach identified through ablation study

## Abstract

Following detection and tracking of traffic actors, prediction of their future motion is the next critical component of a self-driving vehicle (SDV) technology, allowing the SDV to operate safely and efficiently in its environment. This is particularly important when it comes to vulnerable road users (VRUs), such as pedestrians and bicyclists. These actors need to be handled with special care due to an increased risk of injury, as well as the fact that their behavior is less predictable than that of motorized actors. To address this issue, in the current study we present a deep learning-based method for predicting VRU movement, where we rasterize high-definition maps and actor's surroundings into a bird's-eye view image used as an input to deep convolutional networks. In addition, we propose a fast architecture suitable for real-time inference, and perform an ablation study of various rasterization approaches to find the optimal choice for accurate prediction. The results strongly indicate benefits of using the proposed approach for motion prediction of VRUs, both in terms of accuracy and latency.