Neural dynamics of robust legged robots

TL;DR

This paper explores how neural networks control legged robots, identifying key reflexes and neural patterns that help robots maintain balance and recover from disturbances.

Contribution

The study introduces a framework combining model-based and sampling-based methods to analyze neural network activity in robust robot locomotion.

Findings

An agile hip reflex helps robots regain balance after lateral perturbations.

Recurrent neural dynamics are linked to robust behavior and identified via sampling-based ablation.

Sensory feedback channels' influence on reflexive behavior is quantified using model gradients.

Abstract

Legged robot control has improved in recent years with the rise of deep reinforcement learning, however, much of the underlying neural mechanisms remain difficult to interpret. Our aim is to leverage bio-inspired methods from computational neuroscience to better understand the neural activity of robust robot locomotion controllers. Similar to past work, we observe that terrain-based curriculum learning improves agent stability. We study the biomechanical responses and neural activity within our neural network controller by simultaneously pairing physical disturbances with targeted neural ablations. We identify an agile hip reflex that enables the robot to regain its balance and recover from lateral perturbations. Model gradients are employed to quantify the relative degree that various sensory feedback channels drive this reflexive behavior. We also find recurrent dynamics are implicated in robust behavior, and utilize sampling-based ablation methods to identify these key neurons. Our framework combines model-based and sampling-based methods for drawing causal relationships between neural network activity and robust embodied robot behavior.

Figures