The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B4-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2020, 329–335, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B4-2020-329-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2020, 329–335, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B4-2020-329-2020

  25 Aug 2020

25 Aug 2020

REINFORCEMENT LEARNING HELPS SLAM: LEARNING TO BUILD MAPS

N. Botteghi1, B. Sirmacek2, R. Schulte1, M. Poel3, and C. Brune4 N. Botteghi et al.
  • 1Robotics and Mechatronics, Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, The Netherlands
  • 2Jönköping AI Lab (JAIL), School of Engineering, Jönköping University, Sweden
  • 3Datamanagement and Biometrics, Faculty of Electric Engineering, Mathematics and Computer Science, University of Twente, The Netherlands
  • 4Applied Mathematics, Faculty of Electric Engineering, Mathematics and Computer Science, University of Twente, The Netherlands

Keywords: Simultaneous Localization and Mapping, Reinforcement Learning, Autonomous Exploration, Indoor Environments

Abstract. In this research, we investigate the use of Reinforcement Learning (RL) for an effective and robust solution for exploring unknown and indoor environments and reconstructing their maps. We benefit from a Simultaneous Localization and Mapping (SLAM) algorithm for real-time robot localization and mapping. Three different reward functions are compared and tested in different environments with growing complexity. The performances of the three different RL-based path planners are assessed not only on the training environments, but also on an a priori unseen environment to test the generalization properties of the policies. The results indicate that RL-based planners trained to maximize the coverage of the map are able to consistently explore and construct the maps of different indoor environments.