Diffusion-Based Imaginative Coordination for Bimanual Manipulation

TL;DR

This paper introduces a diffusion-based framework for bimanual manipulation in robotics, combining video and action prediction to improve coordination and success rates in complex tasks.

Contribution

It proposes a novel multi-frame latent prediction strategy and a unidirectional attention mechanism to enhance bimanual coordination efficiency.

Findings

Achieved 24.9% success rate increase on ALOHA benchmark.

Improved RoboTwin success rate by 11.1%.

Increased real-world task success by 32.5%.

Abstract

Bimanual manipulation is crucial in robotics, enabling complex tasks in industrial automation and household services. However, it poses significant challenges due to the high-dimensional action space and intricate coordination requirements. While video prediction has been recently studied for representation learning and control, leveraging its ability to capture rich dynamic and behavioral information, its potential for enhancing bimanual coordination remains underexplored. To bridge this gap, we propose a unified diffusion-based framework for the joint optimization of video and action prediction. Specifically, we propose a multi-frame latent prediction strategy that encodes future states in a compressed latent space, preserving task-relevant features. Furthermore, we introduce a unidirectional attention mechanism where video prediction is conditioned on the action, while action prediction remains independent of video prediction. This design allows us to omit video prediction during inference, significantly enhancing efficiency. Experiments on two simulated benchmarks and a real-world setting demonstrate a significant improvement in the success rate over the strong baseline ACT using our method, achieving a \textbf{24.9\%} increase on ALOHA, an \textbf{11.1\%} increase on RoboTwin, and a \textbf{32.5\%} increase in real-world experiments. Our models and code are publicly available at https://github.com/return-sleep/Diffusion_based_imaginative_Coordination.