Brain-Inspired Spatial Continuous State Encoding for Efficient Spiking-Based Navigation

Spiking neural networks (SNNs) show great potential in mapless navigation tasks due to their low power consumption, but the continuous representation of spatial information poses a challenge to SNN training. Neuroscience findings reveal that spatial cognition cells encode spatial information through population spike patterns. Inspired by this, we propose a navigation method based on SNNs, leveraging spatial cognition cells, which include grid cells (GCs), head direction cells (HDCs), and boundary vector cells (BVCs). Our method integrates spike-based information to achieve precise navigation goal encoding and egocentric environment perception, significantly improving SNN navigation capabilities in complex environments. Simulation and real-world experiments demonstrate that our method achieves significant improvements in navigation success rate and energy efficiency, showcasing superior adaptability across environments. Our work provides a novel approach to developing efficient brain-inspired navigation systems.

Authors

• Qingao Chai
• Jiashuo Wang
• Runhao Jiang
• Bo Yang
• Rui Yan
• Huajin Tang

Keywords

• Training
• Power demand
• Navigation
• Spiking neural networks
• Reinforcement learning
• Encoding
• Vectors
• Energy efficiency
• Cognition
• Robotics and automation
• Neural Network
• Spatial Information
• Complex Environment
• Grid Cells
• Cell Binding
• Navigation System
• Navigation Task
• Head Direction Cells
• Collision
• Artificial Neural Network
• Neurons In Layer
• Firing Rate
• Simulation Environment
• Precise Information
• Preferred Direction
• Path Planning
• Reduce Energy Consumption
• Robot Control
• Deep Reinforcement Learning
• Goal Position
• Historical Maps
• LiDAR Scans
• Spike Trains
• Simultaneous Localization And Mapping
• Obstacle Avoidance
• Navigation Errors
• Angular Orientation
• Policy Network
• Energy Consumption