Neural self-organization for muscle-driven robots

TL;DR

This paper introduces self-organizing control principles for simulated muscle-driven robots, demonstrating how simple neural controllers and force-mediated muscle couplings can produce stable locomotive gaits.

Contribution

It presents a novel approach where minimal neural controllers and muscle couplings enable self-organized locomotion in simulated robots.

Findings

Stable limit cycles generate regular locomotive patterns.

Force-mediated muscle couplings suffice for gait stability.

Neural controllers with dynamical thresholds produce target muscle positions.

Abstract

We present self-organizing control principles for simulated robots actuated by synthetic muscles. Muscles correspond to linear motors exerting force only when contracting, but not when expanding, with joints being actuated by pairs of antagonistic muscles. Individually, muscles are connected to a controller composed of a single neuron with a dynamical threshold that generates target positions for the respective muscle. A stable limit cycle is generated when the embodied feedback loop is closed, giving rise to regular locomotive patterns. In the absence of direct couplings between neurons, we show that force-mediated intra- and inter-leg couplings between muscles suffice to generate stable gaits.