Back to AI News
arxiv

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.

AI Brief

It provides concrete comparative evidence on how biologically plausible spiking learning rules perform against backpropagation for real humanoid locomotion control.

arXiv:2611.26074v1 Announce Type: new Abstract: Artificial Spiking Neural Networks have gained remarkable attention in the last few years due to their proven ability in simulating biological neural cultures and producing similar activity and trends. Nevertheless, whether they can be trained for humanoid locomotion while retaining biological plausibility and robust performance at once remains an open question. We study this problem by proposing a biologically inspired spiking network, trained by different learning schemes and tested on the H1-2 Unitree Humanoid. These schemes differ in how recurrent weights are trained. Ordered from most to least biologically faithful, they are: a fixed reservoir mimicking an in-vitro neural culture, where recurrent weights are kept frozen and only a linear readout is trained, the same network but with its synapses trained by reward-modulated spike timing dependent plasticity and eligibility propagation, and finally backpropagation through time as a non biological baseline for comparison. All schemes relied on distillation of a reinforcement learning expert policy with dataset aggregation. We show that e-prop reached 100% survival rate matching backpropagation through time, whereas both the fixed reservoir and the reward-modulated STDP, though the closest to biological cultures, plateaued at a much lower performance (~43.7% and ~11% survival). We explore in further detail which trends a real culture could and could not produce until now. Finally we demonstrate brief bipedal stepping on a full size humanoid H1-2.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!