Hebbian Attractor Networks for Robot Locomotion

2026-03-23

AI Summary

This work addresses the challenge that artificial neural networks struggle to continuously adapt in dynamic environments as biological systems do. To this end, the authors propose the Hebbian Attractor Network (HAN), which uniquely integrates time-averaged pre- and postsynaptic activity with dual-timescale Hebbian plasticity and introduces a local weight normalization mechanism. The slow plasticity component stabilizes attractor dynamics, while the fast component generates oscillatory co-dynamic limit cycles. Experiments on the Unitree Go1 quadruped robot demonstrate that HAN significantly enhances adaptive locomotion control, revealing the critical role of plasticity timescales in shaping neural dynamics and control performance.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Biological neural networks continuously adapt and modify themselves in response to experiences throughout their lifetime - a capability largely absent in artificial neural networks. Hebbian plasticity offers a promising path toward rapid adaptation in changing environments. Here, we introduce Hebbian Attractor Networks (HAN), a class of plastic neural networks in which local weight update normalization induces emergent attractor dynamics. Unlike prior approaches, HANs employ dual-timescale plasticity and temporal averaging of pre- and postsynaptic activations to induce either co-dynamic limit cycles or fixed-point weight attractors. Using simulated locomotion benchmarks, we gain insight into how Hebbian update frequency and activation averaging influence weight dynamics and control performance. Our results show that slower updates, combined with averaged pre- and postsynaptic activations, promote convergence to stable weight configurations, while faster updates yield oscillatory co-dynamic systems. We further demonstrate that these findings generalize to high-dimensional quadrupedal locomotion with a simulated Unitree Go1 robot. These results highlight how the timing of plasticity shapes neural dynamics in embodied systems, providing a principled characterization of the attractor regimes that emerge in self-modifying networks.

Problem

• Hebbian plasticity
• attractor dynamics
• robot locomotion
• neural adaptation
• embodied intelligence

Innovation

• Hebbian plasticity
• attractor dynamics
• dual-timescale plasticity
• temporal averaging
• embodied intelligence