Evidential Occupancy Grid Map Augmentation using Deep Learning

01/16/2018
by   Sascha Wirges, et al.
0

A detailed environment representation is a crucial component of automated vehicles. Using single range sensor scans, data is often too sparse and subject to occlusions. Therefore, we present a method to augment occupancy grid maps from single views to be similar to evidential occupancy maps acquired from different views using Deep Learning. To accomplish this, we estimate motion between subsequent range sensor measurements and create an evidential 3D voxel map in an extensive post-processing step. Within this voxel map, we explicitly model uncertainty using evidence theory and create a 2D projection using combination rules. As input for our neural networks, we use a multi-layer grid map consisting of the three features detections, transmissions and intensity, each for ground and non-ground measurements. Finally, we perform a quantitative and qualitative evaluation which shows that different network architectures accurately infer evidential measures in real-time.

READ FULL TEXT

page 1

page 3

page 6

research
05/02/2018

Object Detection and Classification in Occupancy Grid Maps using Deep Convolutional Networks

A detailed environment perception is a crucial component of automated ve...
research
05/13/2020

Exploiting Multi-Layer Grid Maps for Surround-View Semantic Segmentation of Sparse LiDAR Data

In this paper, we consider the transformation of laser range measurement...
research
01/15/2020

3D Object Segmentation for Shelf Bin Picking by Humanoid with Deep Learning and Occupancy Voxel Grid Map

Picking objects in a narrow space such as shelf bins is an important tas...
research
06/05/2020

MRFMap: Online Probabilistic 3D Mapping using Forward Ray Sensor Models

Traditional dense volumetric representations for robotic mapping make si...
research
01/31/2019

Capturing Object Detection Uncertainty in Multi-Layer Grid Maps

We propose a deep convolutional object detector for automated driving ap...
research
08/08/2023

Vehicle Motion Forecasting using Prior Information and Semantic-assisted Occupancy Grid Maps

Motion prediction is a challenging task for autonomous vehicles due to u...
research
02/15/2021

Corneal Pachymetry by AS-OCT after Descemet's Membrane Endothelial Keratoplasty

Corneal thickness (pachymetry) maps can be used to monitor restoration o...

Please sign up or login with your details

Forgot password? Click here to reset