Occupancy Grid Artefact Removal and Error Correction using GANs

Leon Davies*, Baihua Li, Mohamad Saada, Simon Solvsten, Qinggang Meng

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Occupancy Grid Mapping is a form of Simultaneous Localisation and Mapping (SLAM) in which the world around a robot is visually represented as a grid map. This form of map can be compared to a floor plan in which features within an environment such as walls are labelled in place. Certain issues such as noise, artefacts, linear error, angular error, and incomplete rooms make this representation difficult to appropriate. Generative Adversarial Networks (GAN) [1] in the past have proven successful in and reliable methods for noise reduction, artefact removal [2], and partial observation completion [3]. We demonstrate a novel data creation process to mass produce samples of erroneous and ideal occupancy grid maps. We use this data to build two GAN models based on well-known frameworks CycleGAN [4] and CUT [5] for the task of occupancy grid cleaning. We demonstrate the generalisability of our models through making predictions of 'clean' maps on samples of real data from the Radish Dataset [6].

Original languageEnglish
Title of host publication2024 4th International Conference on Computer, Control and Robotics, ICCCR 2024
Place of PublicationShanghai, China
PublisherIEEE
Publication date2024
Pages96-100
ISBN (Print)9798350373158
ISBN (Electronic)9798350373141, 9798350373134
DOIs
Publication statusPublished - 2024
Event4th International Conference on Computer, Control and Robotics, ICCCR 2024 - Shanghai, China
Duration: 19. Apr 202421. Apr 2024

Conference

Conference4th International Conference on Computer, Control and Robotics, ICCCR 2024
Country/TerritoryChina
CityShanghai
Period19/04/202421/04/2024

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Keywords

  • CUT
  • CycleGan
  • Dataset
  • Deep Learning
  • Deep Reinforcement Learning
  • GAN
  • Image to Image translation
  • Machine Learning
  • SLAM

Fingerprint

Dive into the research topics of 'Occupancy Grid Artefact Removal and Error Correction using GANs'. Together they form a unique fingerprint.

Cite this