A Reinforcement Learning-Based Model for Mapping and Goal-Directed Navigation Using Multiscale Place Fields
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917187775627264 |
|---|---|
| author | Dukenbaev, Bekarys Gerstenslager, Andrew Johnson, Alexander Minai, Ali A. |
| author_facet | Dukenbaev, Bekarys Gerstenslager, Andrew Johnson, Alexander Minai, Ali A. |
| contents | Autonomous navigation in complex and partially observable environments remains a central challenge in robotics. Several bio-inspired models of mapping and navigation based on place cells in the mammalian hippocampus have been proposed. This paper introduces a new robust model that employs parallel layers of place fields at multiple spatial scales, a replay-based reward mechanism, and dynamic scale fusion. Simulations show that the model improves path efficiency and accelerates learning compared to single-scale baselines, highlighting the value of multiscale spatial representations for adaptive robot navigation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03520 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Reinforcement Learning-Based Model for Mapping and Goal-Directed Navigation Using Multiscale Place Fields Dukenbaev, Bekarys Gerstenslager, Andrew Johnson, Alexander Minai, Ali A. Neural and Evolutionary Computing Artificial Intelligence Robotics Autonomous navigation in complex and partially observable environments remains a central challenge in robotics. Several bio-inspired models of mapping and navigation based on place cells in the mammalian hippocampus have been proposed. This paper introduces a new robust model that employs parallel layers of place fields at multiple spatial scales, a replay-based reward mechanism, and dynamic scale fusion. Simulations show that the model improves path efficiency and accelerates learning compared to single-scale baselines, highlighting the value of multiscale spatial representations for adaptive robot navigation. |
| title | A Reinforcement Learning-Based Model for Mapping and Goal-Directed Navigation Using Multiscale Place Fields |
| topic | Neural and Evolutionary Computing Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2601.03520 |