DeepAI AI Chat
Log In Sign Up

Hierarchical Recurrent Attention Networks for Structured Online Maps

12/22/2020
by   Namdar Homayounfar, et al.
UNIVERSITY OF TORONTO
MIT
Carnegie Mellon University
15

In this paper, we tackle the problem of online road network extraction from sparse 3D point clouds. Our method is inspired by how an annotator builds a lane graph, by first identifying how many lanes there are and then drawing each one in turn. We develop a hierarchical recurrent network that attends to initial regions of a lane boundary and traces them out completely by outputting a structured polyline. We also propose a novel differentiable loss function that measures the deviation of the edges of the ground truth polylines and their predictions. This is more suitable than distances on vertices, as there exists many ways to draw equivalent polylines. We demonstrate the effectiveness of our method on a 90 km stretch of highway, and show that we can recover the right topology 92% of the time.

READ FULL TEXT

page 1

page 4

page 6

page 7

page 8

12/21/2020

Convolutional Recurrent Network for Road Boundary Extraction

Creating high definition maps that contain precise information of static...
03/31/2021

Hierarchical Road Topology Learning for Urban Map-less Driving

The majority of current approaches in autonomous driving rely on High-De...
12/22/2020

DAGMapper: Learning to Map by Discovering Lane Topology

One of the fundamental challenges to scale self-driving is being able to...
04/03/2023

Online Lane Graph Extraction from Onboard Video

Autonomous driving requires a structured understanding of the surroundin...
07/05/2021

Learning a Model for Inferring a Spatial Road Lane Network Graph using Self-Supervision

Interconnected road lanes are a central concept for navigating urban roa...
09/15/2020

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

We propose a novel, connectivity-oriented loss function for training dee...