🤖 AI Summary
Existing central pattern generator (CPG) models lack integration of neural plasticity mechanisms and astrocytic homeostatic regulation, limiting biologically plausible self-organization of locomotor gaits. To address this, we propose an astrocyte-modulated spiking neural network CPG model—the first to embed astrocyte-mediated dynamic inhibition within the CPG architecture, coupled with reward-modulated spike-timing-dependent plasticity (STDP) to enable synaptic plasticity-driven gait learning. Validated via multi-body physics simulation on a quadrupedal robot, the model autonomously generates stable diagonal trotting gaits. Compared to state-of-the-art reinforcement learning approaches, it achieves a 23.3× reduction in computational power consumption, markedly enhancing energy efficiency and biological plausibility. This work bridges a critical gap in neuromorphic CPG modeling by establishing a plasticity-enabled, astrocyte-integrated framework for adaptive, low-power locomotor control.
📝 Abstract
Neuromorphic computing systems, where information is transmitted through action potentials in a bio-plausible fashion, is gaining increasing interest due to its promise of low-power event-driven computing. Application of neuromorphic computing in robotic locomotion research have largely focused on Central Pattern Generators (CPGs) for bionics robotic control algorithms - inspired from neural circuits governing the collaboration of the limb muscles in animal movement. Implementation of artificial CPGs on neuromorphic hardware platforms can potentially enable adaptive and energy-efficient edge robotics applications in resource constrained environments. However, underlying rewiring mechanisms in CPG for gait emergence process is not well understood. This work addresses the missing gap in literature pertaining to CPG plasticity and underscores the critical homeostatic functionality of astrocytes - a cellular component in the brain that is believed to play a major role in multiple brain functions. This paper introduces an astrocyte regulated Spiking Neural Network (SNN)-based CPG for learning locomotion gait through Reward-Modulated STDP for quadruped robots, where the astrocytes help build inhibitory connections among the artificial motor neurons in different limbs. The SNN-based CPG is simulated on a multi-object physics simulation platform resulting in the emergence of a trotting gait while running the robot on flat ground. $23.3 imes$ computational power savings is observed in comparison to a state-of-the-art reinforcement learning based robot control algorithm. Such a neuroscience-algorithm co-design approach can potentially enable a quantum leap in the functionality of neuromorphic systems incorporating glial cell functionality.
