mlsanityData to 7 Oct 2026

Hierarchical Road Topology Learning for Urban Map-less Driving

arXiv 2104.00084 ↗First posted 31 Mar 2021cs.RO cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 12 of its 29 references that are in the map. First posted on arXiv 31 Mar 2021.

Builds on

12 of 29 references.

References · 12

  1. 2017LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentationcited by 212
  2. 2018Towards End-to-End Lane Detection: an Instance Segmentation Approachcited by 129
  3. 2018RoadTracer: Automatic Extraction of Road Networks from Aerial Imagescited by 102
  4. 2017VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognitioncited by 56
  5. 2020DAGMapper: Learning to Map by Discovering Lane Topologycited by 49
  6. 2020Hierarchical Recurrent Attention Networks for Structured Online Mapscited by 38
  7. 2020Convolutional Recurrent Network for Road Boundary Extractioncited by 33
  8. 2020DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localizationcited by 28
  9. 2016Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomycited by 27
  10. 2019Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environmentscited by 7
  11. 2018Improved Semantic Stixels via Multimodal Sensor Fusioncited by 3
  12. 2019Slanted Stixels: A way to represent steep streetscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1.

4 papers.

  1. 2023Learning and Aggregating Lane Graphs for Urban Automated Drivingcited by 20
  2. 2024Lane Graph Extraction from Aerial Imagery via Lane Segmentation Refinement with Diffusion Modelscited by 4
  3. 2023Learning to Predict Navigational Patterns from Partial Observationscited by 3
  4. 2022ROMNet: Renovate the Old Memoriescited by 0