DiT1dLnet: A Fast and Accurate Diffusion Model Structure Based on Robot Behavior Imitation

A novel robot behavior generation method combining imitation learning with diffusion models elegantly addresses multi-modal action distributions, adapts to high-dimensional action spaces, and demonstrates impressive training stability. It significantly improves success rates across nine diverse tasks on three different robot simulation benchmarks, but comes with longer training times and slower inference speed. This paper proposes a novel architecture, DiT1dLnet, applied to DDPM for training and inference. DiT1dLnet improves accuracy across various robotic simulation tasks while accelerating training and inference speed by 50–100%. We benchmarked its performance on nine different tasks using three distinct robots.