Fully Spiking Neural Network for Legged Robots
This work addresses energy efficiency and biological interpretability for legged robots, representing an incremental improvement over existing methods.
This paper tackles the problem of high inference speed and energy consumption in legged robots by introducing a novel Spiking Neural Network (SNN), which shows exceptional performance in various simulated terrains.
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.