Planetary global localization is necessary for long-range rover missions in which communication with command center operator is throttled due to the long distance. There has been number of researches that address this problem by exploiting and matching rover surroundings with global digital elevation maps (DEM). Using conventional methods for matching, however, is challenging due to artifacts in both DEM rendered images, and/or rover 2D images caused by DEM low resolution, rover image illumination variations and small terrain features. In this work, we use train CNN discriminator to match rover 2D image with DEM rendered images using conditional Generative Adversarial Network architecture (cGAN). We then use this discriminator to search an uncertainty bound given by visual odometry (VO) error bound to estimate rover optimal location and orientation. We demonstrate our network capability to learn to translate rover image into DEM simulated image and match them using Devon Island dataset. The experimental results show that our proposed approach achieves ~74% mean average precision.

Abstract
 1. Introduction
 2. Long-Range Deep 2D GlobalLocalization Network
  2.1 Generator
  2.2 Discriminator
  2.3 Training Procedure
 3. Experimental Results
 4. Conclusion
 References

• 아하메드 엠.나기브(Intelligent Systems Research Institute, School of Information and Communication Engineering Sungkyunkwan University) | Ahmed M.Naguib
• 투안 아인 뉴엔(Intelligent Systems Research Institute, School of Information and Communication Engineering Sungkyunkwan University) | Tuan Anh Nguyen
• 나임 울 이슬람(Intelligent Systems Research Institute, School of Information and Communication Engineering Sungkyunkwan University) | Naeem Ul Islam
• 김재웅(Intelligent Systems Research Institute, School of Information and Communication Engineering Sungkyunkwan University) | Jaewoong Kim
• 이석한(Intelligent Systems Research Institute, School of Information and Communication Engineering Sungkyunkwan University) | Sukhan Lee Corresponding author