ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation

TL;DR

ManiCM introduces a one-step diffusion-based model for real-time 3D robotic manipulation, significantly speeding up inference while maintaining high success rates across diverse tasks.

Contribution

This work presents ManiCM, a novel consistency model that enables single-step inference in diffusion-based robotic manipulation, addressing runtime inefficiency in high-dimensional tasks.

Findings

Accelerates inference speed by 10 times on average.

Maintains competitive success rates across 31 manipulation tasks.

Demonstrates effectiveness of consistency distillation in action prediction.

Abstract

Diffusion models have been verified to be effective in generating complex distributions from natural images to motion trajectories. Recent diffusion-based methods show impressive performance in 3D robotic manipulation tasks, whereas they suffer from severe runtime inefficiency due to multiple denoising steps, especially with high-dimensional observations. To this end, we propose a real-time robotic manipulation model named ManiCM that imposes the consistency constraint to the diffusion process, so that the model can generate robot actions in only one-step inference. Specifically, we formulate a consistent diffusion process in the robot action space conditioned on the point cloud input, where the original action is required to be directly denoised from any point along the ODE trajectory. To model this process, we design a consistency distillation technique to predict the action sample directly instead of predicting the noise within the vision community for fast convergence in the low-dimensional action manifold. We evaluate ManiCM on 31 robotic manipulation tasks from Adroit and Metaworld, and the results demonstrate that our approach accelerates the state-of-the-art method by 10 times in average inference speed while maintaining competitive average success rate.