Brain-inspired Action Generation with Spiking Transformer Diffusion Policy Model

TL;DR

This paper introduces a novel brain-inspired diffusion policy model using Spiking Transformer Neural Networks and diffusion models to generate robot action trajectories, outperforming existing methods in robotic manipulation tasks.

Contribution

The paper proposes the STMDP model combining SNNs, diffusion models, and Transformers, along with a new decoder module, advancing brain-inspired robotics.

Findings

Outperforms existing Transformer-based diffusion policies.

Achieved 8% improvement in the Can task.

Demonstrates effectiveness across four robotic manipulation tasks.

Abstract

Spiking Neural Networks (SNNs) has the ability to extract spatio-temporal features due to their spiking sequence. While previous research has primarily foucus on the classification of image and reinforcement learning. In our paper, we put forward novel diffusion policy model based on Spiking Transformer Neural Networks and Denoising Diffusion Probabilistic Model (DDPM): Spiking Transformer Modulate Diffusion Policy Model (STMDP), a new brain-inspired model for generating robot action trajectories. In order to improve the performance of this model, we develop a novel decoder module: Spiking Modulate De coder (SMD), which replaces the traditional Decoder module within the Transformer architecture. Additionally, we explored the substitution of DDPM with Denoising Diffusion Implicit Models (DDIM) in our frame work. We conducted experiments across four robotic manipulation tasks and performed ablation studies on the modulate block. Our model consistently outperforms existing Transformer-based diffusion policy method. Especially in Can task, we achieved an improvement of 8%. The proposed STMDP method integrates SNNs, dffusion model and Transformer architecture, which offers new perspectives and promising directions for exploration in brain-inspired robotics.