A Reinforcement Learning-Based Model for Mapping and Goal-Directed Navigation Using Multiscale Place Fields
On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 2 of its 49 references that are in the map. First posted on arXiv 7 Jan 2026.
Builds on
2 of 49 references.
References · 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Building spatial world models from sparse transitional episodic memories
- 2024A transformer-based deep reinforcement learning approach to spatial navigation in a partially observable Morris Water Maze
- 2025EDEN: Entorhinal Driven Egocentric Navigation Toward Robotic Deployment
- 2025Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence Generator
- 2025From reactive to cognitive: brain-inspired spatial intelligence for embodied agents
- 2025Bio-Inspired Hybrid Map: Spatial Implicit Local Frames and Topological Map for Mobile Cobot Navigation ↗
- 2024Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps
- 2025Embodied World Models Emerge from Navigational Task in Open-Ended Environments