Hierarchical Road Topology Learning for Urban Map-less Driving

TL;DR

This paper introduces a hierarchical graph-based model for online extraction of road topology from vehicle sensors, enabling map-less autonomous driving in complex urban environments without relying on pre-existing HD maps.

Contribution

The paper proposes a novel hierarchical graph learning approach within a convolutional network for real-time road network extraction, improving scalability and robustness over traditional map-dependent methods.

Findings

Successfully handles complex urban road topologies

Operates in real-time without user intervention

Reduces dependence on high-definition pre-mapped data

Abstract

The majority of current approaches in autonomous driving rely on High-Definition (HD) maps which detail the road geometry and surrounding area. Yet, this reliance is one of the obstacles to mass deployment of autonomous vehicles due to poor scalability of such prior maps. In this paper, we tackle the problem of online road map extraction via leveraging the sensory system aboard the vehicle itself. To this end, we design a structured model where a graph representation of the road network is generated in a hierarchical fashion within a fully convolutional network. The method is able to handle complex road topology and does not require a user in the loop.