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 language | English |
---|---|
Title of host publication | 2024 4th International Conference on Computer, Control and Robotics, ICCCR 2024 |
Place of Publication | Shanghai, China |
Publisher | IEEE |
Publication date | 2024 |
Pages | 96-100 |
ISBN (Print) | 9798350373158 |
ISBN (Electronic) | 9798350373141, 9798350373134 |
DOIs | |
Publication status | Published - 2024 |
Event | 4th International Conference on Computer, Control and Robotics, ICCCR 2024 - Shanghai, China Duration: 19. Apr 2024 → 21. Apr 2024 |
Conference
Conference | 4th International Conference on Computer, Control and Robotics, ICCCR 2024 |
---|---|
Country/Territory | China |
City | Shanghai |
Period | 19/04/2024 → 21/04/2024 |
Bibliographical note
Publisher Copyright:© 2024 IEEE.
Keywords
- CUT
- CycleGan
- Dataset
- Deep Learning
- Deep Reinforcement Learning
- GAN
- Image to Image translation
- Machine Learning
- SLAM