# Deep Grid Net (DGN): A Deep Learning System for Real-Time Driving Context Understanding

## TL;DR

This paper introduces Deep Grid Net (DGN), a deep learning system that uses occupancy grids from Lidar data and Dempster-Shafer theory to understand driving context for autonomous vehicles, enabling strategy switching.

## Contribution

The paper presents a novel deep learning approach combining occupancy grids and Dempster-Shafer theory for real-time driving context understanding in autonomous cars.

## Key findings

- DGN outperforms similar classifiers in driving context estimation
- The neuroevolutionary approach effectively tunes DGN hyperparameters
- DGN enables dynamic switching of driving strategies

## Abstract

Grid maps obtained from fused sensory information are nowadays among the most popular approaches for motion planning for autonomous driving cars. In this paper, we introduce Deep Grid Net (DGN), a deep learning (DL) system designed for understanding the context in which an autonomous car is driving. DGN incorporates a learned driving environment representation based on Occupancy Grids (OG) obtained from raw Lidar data and constructed on top of the Dempster-Shafer (DS) theory. The predicted driving context is further used for switching between different driving strategies implemented within EB robinos, Elektrobit's Autonomous Driving (AD) software platform. Based on genetic algorithms (GAs), we also propose a neuroevolutionary approach for learning the tuning hyperparameters of DGN. The performance of the proposed deep network has been evaluated against similar competing driving context estimation classifiers.