Enhancing Exploration Algorithms for Navigation with Visual SLAM

Authors

Yakovlev K. Bokovoy A. Muravyov K.

Annotation

Exploration is an important step in autonomous navigation of robotic systems. In this paper we introduce a series of enhancements for exploration algorithms in order to use them with vision-based simultaneous localization and mapping (vSLAM) methods. We evaluate developed approaches in photo-realistic simulator in two modes: with ground-truth depths and neural network reconstructed depth maps as vSLAM input. We evaluate standard metrics in order to estimate exploration coverage.

External links

DOI: 10.1007/978-3-030-86855-0_14

PDF at arXiv.org: https://arxiv.org/pdf/2110.09156

Microsoft Academic: https://academic.microsoft.com/paper/3203516484/

ResearchGate: https://www.researchgate.net/publication/355051573_Enhancing_Exploration_Algorithms_for_Navigation_with_Visual_SLAM

Semantic Scholar: https://api.semanticscholar.org/CorpusID:238417375

Reference link

Muravyev K., Bokovoy A., Yakovlev K. (2021) Enhancing Exploration Algorithms for Navigation with Visual SLAM. In: Kovalev S.M., Kuznetsov S.O., Panov A.I. (eds) Artificial Intelligence. RCAI 2021. Lecture Notes in Computer Science, vol 12948. Springer, Cham. Pages 197-212