NEAT-NC: NEAT guided Navigation Cells for Robot Path Planning

arXiv cs.RO / 4/17/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes NEAT-NC, a biologically inspired path-planning method that uses “navigation cells” to build an internal representation of space for robots.
It adapts the NEAT (Neuro-Evolution of Augmenting Topology) algorithm by evolving recurrent neural networks meant to emulate parts of the hippocampal system.
The approach takes navigation cells as inputs and is evaluated across both static and dynamic environments to test robustness and generalization.
Results indicate NEAT’s adaptability to complex, varying scenarios, suggesting the method could support real-time dynamic path planning in robotics and games.
Overall, the study positions biological spatial-cognition theories as a practical way to improve learning-based navigation in changing conditions.

Abstract

To navigate a space, the brain makes an internal representation of the environment using different cells such as place cells, grid cells, head direction cells, border cells, and speed cells. All these cells, along with sensory inputs, enable an organism to explore the space around it. Inspired by these biological principles, we developed NEATNC, a Neuro-Evolution of Augmenting Topology guided Navigation Cells. The goal of the paper is to improve NEAT algorithm performance in path planning in dynamic environments using spatial cognitive cells. This approach uses navigation cells as inputs and evolves recurrent neural networks, representing the hippocampus part of the brain. The performance of the proposed algorithm is evaluated in different static and dynamic scenarios. This study highlights NEAT's adaptability to complex and different environments, showcasing the utility of biological theories. This suggests that our approach is well-suited for real-time dynamic path planning for robotics and games.