Simkuns Arturs, Saltanovs Rodions, Ivanovs Maksims, Kadiķis Roberts. Deep Learning-Emerged Grid Cells-Based Bio-Inspired Navigation in Robotics. Sensors, 25(5), MDPI, 2025.
Bibtex citāts:
Bibtex citāts:
@article{19817_2025,
author = {Simkuns Arturs and Saltanovs Rodions and Ivanovs Maksims and Kadiķis Roberts},
title = {Deep Learning-Emerged Grid Cells-Based Bio-Inspired Navigation in Robotics},
journal = {Sensors},
volume = {25},
issue = {5},
publisher = {MDPI},
year = {2025}
}
author = {Simkuns Arturs and Saltanovs Rodions and Ivanovs Maksims and Kadiķis Roberts},
title = {Deep Learning-Emerged Grid Cells-Based Bio-Inspired Navigation in Robotics},
journal = {Sensors},
volume = {25},
issue = {5},
publisher = {MDPI},
year = {2025}
}
Anotācija: Grid cells in the brain’s entorhinal cortex are essential for spatial navigation and have inspired advancements in robotic navigation systems. This paper first provides an overview of recent research on grid cell-based navigation in robotics, focusing on deep learning models and algorithms capable of handling uncertainty and dynamic environments. We then present experimental results where a grid cell network was trained using trajectories from a mobile unmanned ground vehicle (UGV) robot. After training, the network’s units exhibited spatially periodic and hexagonal activation patterns characteristic of biological grid cells, as well as responses resembling border cells and head-direction cells. These findings demonstrate that grid cell networks can effectively learn spatial representations from robot trajectories, providing a foundation for developing advanced navigation algorithms for mobile robots. We conclude by discussing current challenges and future research directions in this field. © 2025 Elsevier B.V., All rights reserved.
Žurnāla kvartile: Q1