Boosting Brain-inspired Path Integration Efficiency via Learning-based Replication of Continuous Attractor Neurodynamics

TL;DR

This paper introduces a learning-based method to replicate brain-inspired neural dynamics for path integration, significantly improving efficiency while maintaining accuracy, thus advancing practical brain-inspired navigation systems.

Contribution

It presents a lightweight neural network approach to replicate continuous attractor neural network patterns, enhancing efficiency in brain-inspired navigation without sacrificing accuracy.

Findings

Replicated neurodynamic patterns of navigation cells using lightweight ANNs.

Achieved about 17.5% efficiency improvement on general devices.

Matched NeuroSLAM's positioning accuracy in benchmark tests.

Abstract

The brain's Path Integration (PI) mechanism offers substantial guidance and inspiration for Brain-Inspired Navigation (BIN). However, the PI capability constructed by the Continuous Attractor Neural Networks (CANNs) in most existing BIN studies exhibits significant computational redundancy, and its operational efficiency needs to be improved; otherwise, it will not be conducive to the practicality of BIN technology. To address this, this paper proposes an efficient PI approach using representation learning models to replicate CANN neurodynamic patterns. This method successfully replicates the neurodynamic patterns of CANN-modeled Head Direction Cells (HDCs) and Grid Cells (GCs) using lightweight Artificial Neural Networks (ANNs). These ANN-reconstructed HDC and GC models are then integrated to achieve brain-inspired PI for Dead Reckoning (DR). Benchmark tests in various environments, compared with the well-known NeuroSLAM system, demonstrate that this work not only accurately replicates the neurodynamic patterns of navigation cells but also matches NeuroSLAM in positioning accuracy. Moreover, efficiency improvements of approximately 17.5% on the general-purpose device and 40~50% on the edge device were observed, compared with NeuroSLAM. This work offers a novel implementation strategy to enhance the practicality of BIN technology and holds potential for further extension.