Radar-PointGNN: Graph Based Object Recognition for Unstructured Radar Point-cloud Data

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review


Perception systems for autonomous vehicles are reliant on a comprehensive sensor suite to identify objects in the environment. While object recognition systems in the LiDAR and camera modalities are reaching maturity, recognition models on sparse radar point measurements have remained an open research challenge. An object recognition model is here presented which imposes a graph structure on the radar point-cloud by connecting spatially proximal points and extracts local patterns by performing convolutional operations across the graph’s edges. The model’s performance is evaluated by the nuScenes benchmark and is the first radar object recognition model evaluated on the dataset. The results show that end-to-end deep learning solutions for object recognition in the radar domain are viable but currently not competitive with solutions based on LiDAR data.
Original languageEnglish
Title of host publication2021 IEEE Radar Conference
Subtitle of host publicationRadar on the Move, RadarConf 2021
Number of pages6
ISBN (Electronic)978-1-7281-7609-3
ISBN (Print)978-1-7281-7610-9
Publication statusPublished - 2021
Event2021 IEEE Radar Conference (RadarConf21): Radar on the Move - Atlanta, United States
Duration: 7 May 202114 May 2021

Publication series

NameIEEE National Radar Conference - Proceedings
ISSN (Print)1097-5659


Conference2021 IEEE Radar Conference (RadarConf21)
CountryUnited States

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care

Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.


  • object detection
  • object recognition
  • radar
  • geo-metric deep learning
  • nuScenes
  • geometric deep learning


Dive into the research topics of 'Radar-PointGNN: Graph Based Object Recognition for Unstructured Radar Point-cloud Data'. Together they form a unique fingerprint.

Cite this