Hebbian Attractor Networks for Robot Locomotion
This work addresses the challenge of lifelong adaptation in robotics by providing a principled framework for self-modifying networks, though it is incremental in building on Hebbian plasticity concepts.
The paper tackled the problem of enabling artificial neural networks to adapt rapidly in changing environments by introducing Hebbian Attractor Networks (HANs), which use dual-timescale plasticity and temporal averaging to induce emergent attractor dynamics, and demonstrated their application in simulated robot locomotion, including quadrupedal tasks.
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.