Fully Spiking Neural Network for Legged Robots

TL;DR

This paper introduces a novel spiking neural network designed for legged robots, emphasizing improved inference speed, energy efficiency, and biological plausibility, demonstrating strong performance across simulated terrains.

Contribution

The paper presents a highly efficient SNN model for legged robots that surpasses traditional neural networks in speed, energy consumption, and biological interpretability.

Findings

Exceptional performance in simulated terrains

Enhanced inference speed and energy efficiency

Improved biological plausibility

Abstract

Recent advancements in legged robots using deep reinforcement learning have led to significant progress. Quadruped robots can perform complex tasks in challenging environments, while bipedal and humanoid robots have also achieved breakthroughs. Current reinforcement learning methods leverage diverse robot bodies and historical information to perform actions, but previous research has not emphasized the speed and energy consumption of network inference and the biological significance of neural networks. Most networks are traditional artificial neural networks that utilize multilayer perceptrons (MLP). This paper presents a novel Spiking Neural Network (SNN) for legged robots, showing exceptional performance in various simulated terrains. SNNs provide natural advantages in inference speed and energy consumption, and their pulse-form processing enhances biological interpretability. This study presents a highly efficient SNN for legged robots that can be seamless integrated into other learning models.