Controlling the Humanoid Robot H1-2 With a Simulated Biologically Plausible Network
Researchers trained a biologically inspired spiking neural network to control the Unitree H1-2 humanoid, comparing three learning schemes that differ in how recurrent weights are trained. Ordered from most to least biologically faithful, these are a fixed reservoir with only a linear readout trained, reward-modulated spike-timing-dependent plasticity with eligibility propagation, and backpropagation through time as a non-biological baseline. All schemes used distillation of a reinforcement learning expert policy with dataset aggregation. E-prop reached a 100% survival rate matching backpropagation through time, while the fixed reservoir and reward-modulated STDP plateaued at roughly 43.7% and 11% survival, and the work demonstrates brief bipedal stepping on the full-size H1-2.
It provides concrete comparative evidence on how biologically plausible spiking learning rules perform against backpropagation for real humanoid locomotion control.
Comments & Questions (0)
No comments yet
Be the first to comment!